Kreara

2021-06-21T22:46:00.000-07:00

Overview

KREARA Solutions is a clinical data management and biometrics solution provider based out of the beautiful campus of Technopark, Trivandrum. Originally established as a statistical services vendor in April 2004, Kreara soon gained traction in the field of clinical trials and got ourselves well versed with the ICH/GCP and CFR PART 11 regulatory requirements. Since then Kreara has been using custom built software applications and standard statistical packages like SAS for providing end-to-end data management and biometric solutions to the pharmaceutical companies and contract research organizations in India, USA and Europe. Kreara was officially incorporated in April 2004.

Our mission is to become the Number 1 CRO in the country providing supplementary services for clinical trials and ultimately help our clients to make affordable and quality health care to the masses a reality.

2010-07-01T05:12:00.001-07:00

Dynamic concatenation of transposed variables

Prepared by Jose Abraham

The transpose procedure in SAS changes multiple values in rows (for a column) into columns, and can also change multiple columns’ values into multiple rows values for a single column. The number of variables (columns) to be created in the output file is based on the maximum number of observations (rows) in a variable (column) to be transposed. If the prefix= option is not specified, then the transposed variables have names Col1, Col2 etc…. i.e. if the dataset has 4 observations in a variable, then on transposing 4 variables namely Col1, Col2, Col3 and Col4 are obtained against each value of the by variable (labparam, lab_id in the below example).

In certain situations, it is required to concatenate the columns obtained during transposing. This can be attained simply by setting the dataset and concatenating the variables using the concatenation operator (||).

e.g. Newvar= Col1|| ‘,’||Col2|| ‘,’||Col3|| ‘,’||Col4;

This procedure may however not produce desirable results if any of the four columns have missing values. If suppose Col3 and Col4 have missing values then consecutive ‘,’ will be presented as the last few characters in the variable Newvar.

The concatenation is thus done by determining the maximum number of Col variables in the transposed dataset and then concatenating the non missing variables to create the new variable against each of the by variables.

Consider the following example from a clinical trial analysis, where the laboratory values are collected at different laboratories. For different laboratories, the reference ranges adopted for parameters are different.Such a dataset is shown below

While obtaining descriptive statistics for different lab parameters, the lab ranges are to be presented in the report as a sub header of the following form.

e.g. Param1

Lab-A: 0-35 g/L (Age 0-99)

Lab-B: 0-34 g/L (Age 0-18), 0-35 g/L (Age 18-60), 0-36 g/L (Age 60-99)

For different laboratory groups the number of ranges will be different, so it is necessary to dynamically concatenate the ranges for each lab for each parameter. The steps involved in this process are given below

Dataset with the lab ranges is transposed.
*Transposing the data to get the reference ranges horizontally;
proc transpose data=range out=range_trn;
by labparam lab_id;
var range;
run;
Select the information about the number of columns in the transposed dataset with the help of sashelp.vcolumn dataset. A macro variable named ‘coln’ is created with the maximum number of ‘Col’ variables as its value.
*Creating a macro variable with maximum number of columns;
data _null_;
set sashelp.vcolumn end=last;
where trim(libname) = 'WORK' and trim(memname) ='RANGE_TRN' and upcase(substr(name,1,3))='COL';
if last then call symput('coln',trim(left(put(_n_,6.))));
run;
Set the transposed dataset and giving array reference to the ‘Col’ variables. Concatenate the ranges with using a do loop and then remove the preceding comma by taking substring of the concatenated variable. A variable named ‘labrange’ is created by concatenating with the lab_id.
data range_con;
length convar $400;
array cols {&coln.} $50 col1-col&coln.;
set range_trn;
do i=1 to dim(cols);
if not missing(cols[i]) then convar= trim(convar)||', '||cols[i];
end;
convar=substr(left(convar),2);
Labrange=trim(left(lab_id))||':'|| compbl(convar);
keep labparam lab_id labrange;
run;

The dataset range_con contains the concatenated ‘labrange’ variable.

*Transposing the dataset to present the ranges for different lab_id's in different variables;

proc transpose data= range_con out=lab_rng(drop=_name_);

id lab_id;

by labparam;

var labrange;

run;

The output dataset obtained during transposing is of the following form

By merging it with the descriptive statistics dataset and using ‘labparam’ and the variables containing the concatenated lab ranges (here LAB_A and LAB_B) as by variables in proc report creates a report which contains descriptive statistics for one parameter per page. By using the ‘#byval’ option in the title statement we can obtain the sub headers of the following type.

Param1

Lab-A: 0-35 g/L (Age 0-99)

Lab-B: 0-34 g/L (Age 0-18), 0-35 g/L (Age 18-60), 0-36 g/L (Age 60-99)

2010-07-01T01:38:00.001-07:00

Project specific SAS shortcuts

Prepared by Jose Abraham

As a SAS programmer, an important concept to know when opening and saving SAS programs is the ‘SasInitialFolder’. The location of this folder is the path name where SAS reads or stores files when a specific drive and pathname is not given. The name of this path appears in a small panel located in the lower right-hand corner of our SAS session. This can be changed at any time with a double-click within that rectangle to access a dialogue box, then entering the drive and path to the desired folder in the space provided or by moving through the folders as done while searching for a particular file. But the change which is made is not permanent. During the next invocation of the SAS System, the current folder will by default present the current folder path that was permanently set. In SAS v8 for windows, the default folder may be something like “C:\Documents and Settings\<user name>\My Documents\My SAS Files\V8” or a path which is in the drive where SAS is installed (e.g. “E:\SAS Installation”). When trying to open or save a program in a SAS session, this default folder will be shown and changing this folder to the desired folder may consume some amount of our valuable time. Here is the way to save this time and also to make project specific SAS shortcuts, which will allow opening and saving SAS programs of that project from the ‘SAS Programs’ folder which is set for that project. The steps to set the current folder to a new location are given below. The folder which is to be set should be created before going through the following steps. 1. Create a shortcut of SAS by clicking on the ‘Start’ menu and select ‘SAS’ from ‘All Programs’, right click on it and then select ‘Send to Desktop’. Then a new SAS shortcut icon will be created in the desktop.2. Right click on the icon and select ‘Rename’ and give a name related to the project.3. Again right click on the icon and select ‘Properties’ and click on the ‘Shortcuts’ tab.4. In the ‘Target’ box, go to the far end of the right-hand side of what is seen in that by pressing the ‘End’ button. Type one space, and enter the following command exactly as you see it here: -sasInitialFolder="."5. The current or working SAS folder will be the pathname that is specified in the 'Start in' field (located just below the 'Target' field). To designate the choice of the current folder, enter the drive and pathname of it within that box. This folder needs to exist on the specified directory.e.g. “G:\Project1\SAS programs”6. Click on ‘Apply’ and then click ‘OK’. The shortcut is now ready for use for the particular project and it will direct to the specified folder on clicking ‘File-> Open’ or ‘File->Save As”.

2010-06-08T06:45:00.001-07:00

Index, Indexc and Indexw functions

Prepared by Meena R S

The INDEX, INDEXC and INDEXW functions are used for determining the character matches. These functions are useful for testing purposes. The index and indexc functions can indicate if a string of characters is present in a target variable. Both functions return the position number of the match in the target variable. A zero indicates that the search argument is not present in the target variable.

For finding a special character such as a letter, a group of letters, or special characters, Index functions can be used and it is case sensitive. The syntax is,

INDEX (source, excerpt)

The INDEXC function allows multiple arguments and will identify the first occurrence of any of the characters in any of the arguments, but otherwise functions similarly to the index function.

/* Example: 1 */

/* Results*/

The INDEXW function searches source, from left to right, for the first occurrence of excerpt and returns the position in source of the substring's first character. If the substring is not found in source, INDEXW returns a value of 0. If there are multiple occurrences of the string, INDEXW returns only the position of the first occurrence.

The INDEXW function is case sensitive function that performs exactly the same function as the INDEX function, with one significant exception. The indexw function searches for strings that are words, whereas the index function searches for patterns as separate words or as parts of other words.

/* Example: 2 */

/* Results */

Result Explanation

The above program demonstrates the difference between INDEX and INDEXW functions. In the first observation in the table above, the INDEX function returns a 1 because the letters "the" as part of the word "there" begin the string. Since the INDEXW function needs either white space at the beginning or end of a string to delimit a word, it returns a 12, the position of the word "the" in the string. Observation 3 emphasizes the fact that a punctuation mark does not serve as a word separator. Finally, since the string "the" does not appear anywhere in the fourth observation, both functions return a 0.

2010-06-08T00:26:00.001-07:00

Read from multiple external files in one data step by using FILEVAR= option

Prepared by Jose Abraham

External files are usually read into SAS one by one using separate data steps for each external file. But multiple external files which have the same structure can be easily read into SAS in one data step by using FILEVAR= and END= options in the INFILE statement. Following example illustrates how to read multiple external files where the locations of the external files are stored in another external file.

Consider we have demographic information of subjects from three different centers stored in three external files. All the three external files have the same structure as given below

The data values are aligned in columns and there are no missing values. The layout follows.

We have another external file which contains the location information of these external files. Suppose these files are stored in the 'demog' folder in the E-drive, and the following external file (dmgfiles) which contains the locations is also in it.

Following SAS data step reads the three external files in one DATA step by using the names which are specified in the external file 'dmgfiles'. This reads the list to determine the external files it should read.

Data step working:

1.First INFILE statement specifies the name of the external file containing the list of filenames that the DATA step should read.

2.First INPUT statement reads the name of the external files with modified list input. A width (60) which is sufficient to hold the name of the external file is specified.

3.Second INFILE statement specifies a text, dummy, and this act as a placeholder for the file specification which is always required on the INFILE statement. The actual specification for the input file comes from the value of the variable assigned by the FILEVAR= option.

a.The FILEVAR= option is set to 'dmgfiles', the variable that contains the name of the external file that the current iteration of the data step should read.

b.END= option defines a variable that SAS sets to 1 when it reads the last data line in the currently opened external file. The END= variable is initialized to 0 and retains the value until it detects that the current input data line is the last in the external file. SAS then sets the variable to 1.

c.When the FILEVAR= option is included in the INFILE statement, SAS resets the END= variable to 0 when the value of the FILEVAR= variable changes (If SAS did not reset the value of the END= variable to 0 each time it opened a new external file, the DATA step would stop after reading the first external file).

4.The do while loop is controlled by testing the value of the END= variable. The loop stops after SAS reads the last data line in the currently opened external file.

5.Name of the file from which the records are read (source file name) is assigned into a variable 'Source'.

6.The above data step iterates four times: one for each of the dmg files (dmg01, dmg02, dmg03) and a fourth time in which it detects that there are no more data lines in the external file that contains the filenames.

7.The default behavior of SAS is that it writes an observation to a data set only at the end of each iteration of the DATA step. An explicit OUTPUT statement is specified to avoid this and output all data values read form the external file.

8.The output dataset 'demogdat' obtained is as follows

Source	Ctrn	Subjid	Age	Sex	Race
E:\demog\dmg01.txt	001	001_01	29	Male	Caucasian
E:\demog\dmg01.txt	001	001_02	28	Female	Caucasian
E:\demog\dmg01.txt	001	001_03	25	Male	Caucasian
E:\demog\dmg02.txt	002	002_01	27	Male	Asian
E:\demog\dmg02.txt	002	002_02	28	Male	Asian
E:\demog\dmg02.txt	002	002_03	25	Female	Asian
E:\demog\dmg03.txt	003	003_01	27	Female	Asian
E:\demog\dmg03.txt	003	003_02	28	Male	Asian
E:\demog\dmg03.txt	003	003_03	25	Female	Asian

2009-08-21T02:51:00.000-07:00

Macro Variable Resolution Using Multiple Ampersands

Prepared by Meena R S (meena@kreara.com)

The SAS macro consists of two basic parts: macros and macro variables. The names of macro variables are prefixed with an ampersand (&) while the names of macros are prefixed with percent sign (%). Prior to the execution of the SAS code the macro variables are resolved. The resolved values are then substituted back into the code.

The macro variable references that have been described with one ampersand preceding the macro variable name are direct reference to a macro variable. In indirect referencing, more than one ampersand precedes a macro variable reference. The macro processor follows specific rules in resolving references with multiple ampersands.

The rules that the macro processor uses to resolve macro variable reference that contain multiple ampersands follow

Macro variable references are resolved from left to right
Two ampersands (&&) resolve to one ampersand (&)
Multiple leading ampersands cause the macro processor to rescan the reference until no more ampersands can be resolved.

Consider the example below.

Options symbolgen;

%let section4 =operating system;

%let n=4;

%put &&section&n;

For the above code, on the first pass the two ampersands are resolved to one and &n is resolved to 4, yielding &section4. On the second pass the macro variable reference &section4 resolves to operating system.

The following figure shows the process of resolving the macro variable reference in the program.

%let a =freight;

%let b=passenger;

%let c=special;

%let code=a;

%put &code;

%put &&code;

%put &&&code;

The following demonstrates how the macro variables with multiple ampersands are resolved.

2009-08-21T01:07:00.000-07:00

Combining SAS data sets using UPDATE statement

Prepared by Rajeev V (rajeev@kreara.com)

UPDATE is an executable type SAS statement generally used in DATA steps. By updating a SAS dataset replaces the values of variables in one dataset with values from another dataset. The dataset containing the original information is the master data set, and the data set containing the new information is the transaction data set. UPDATE performs much the same function as merge with two exceptions:

Ø Only two datasets can be combined using UPDATE statement

Ø If the observation of a variable in the transaction dataset (i.e. data set containing new information) is missing, then the updated dataset containing the value of the observation same as in the master dataset

Syntax

DATA updated data set;

UPDATE master-data-set transaction-data-set;

BY variable-list;

RUN;

Where Master-data-set names the SAS data set that is used as the master file. Transaction-data-set names the SAS dataset that contains the changes to be applied to the master data set. Variable-list specifies the variables by which observations are matched.

Basic use of UPDATE statement

Consider two datasets, Lab1 and Lab2. Both data sets have four subjects with information about their blood pressure at two different times. The first dataset Lab1 contains the subject id, name of the subject and Blood pressure reading. The second dataset contain the latest blood pressure reading for the same subjects but the name of the subjects is not given.

It is required to replace the latest Blood pressure values in LAB1 with the values in LAB2. Here LAB1 is known as Master data set and LAB2 is transaction dataset.

Lab 1

Subject Name BP

001 AAA 120

002 BBB 130

003 CCC 140

004 DDD 150

Lab 2

Subject BP

001 160

002 160

003 160

004 160

The following program updates LAB1 (Master Dataset) with LAB2 (Transaction dataset).

DATA lab1_updated;

UPDATE lab1 lab2;

BY Subject;

RUN;

Printed output of lab1_updated is given below;

In the above example it is found that the latest blood pressure value is populated into updated dataset based on the BY variable Subject identifier.

Suppose Lab1 contains a duplicate observation. For example,

Lab 1

Subject Name BP

001 AAA 120

002 BBB 130

003 CCC 140

004 DDD 150

DATA lab1_updated;

UPDATE lab1 lab2;

BY Subject;

RUN;

If the above program is executed updating will not work for duplicate BY value.

That means if master data set contains two observations with the same value of the BY variable, the first observation is updated and the second observation is ignored. SAS writes a warning message to the log when the data step executes.

Printed output of lab1_updated is given below;

Observations two and three have duplicate values of BY variable subject identifier. However, the value of variable Blood pressure was not updated in the second occurrence of the duplicate BY value.

A situation may arise where a missing observation can occur in master dataset or in transaction dataset. Below example illustrates updating when dataset contains unmatched and missing observations.

Lab A

Subject Name BP

001 AAA .

002 BBB 130

003 CCC 140

004 DDD 150

Lab B

Subject BP

001 160

002 .

003 160

004 160

In the above dataset Lab A (Master Dataset) contains missing value corresponding to the subject 001 and the Lab B (Transaction dataset) contains missing value corresponding to the subject 002. The output of the below code gives the latest known BP value for each subject.

DATA lab1_updated;

UPDATE LabA LabB;

BY Subject;

RUN;

Printed output is given below;

The following is a more advanced example where the UPDATE statement is used to “flatten” a dataset containing different variable data values for a key spread across several observations. The goal is to combine non-missing values into one record per unique key value. The master dataset structure is read, but the OBS=0 option stops the DATA step from reading any data from it. The same dataset is then uploaded as transaction dataset, flattening non-missing observations for each unique key into one observation.

DATA lab;

INPUT Subject $ Calcium Albumin Chloride;

CARDS;

001 2.25 . .

001 . 49 .

001 . . 100

002 3.1 . .

002 . 50 90

002 . . .

;

RUN;

DATA lab;

UPDATE lab (obs=0) lab;

BY subject;

RUN;

Output is given below;

2009-08-20T22:47:00.000-07:00

INFILE OPTIONS

Prepared by Sreeja E V(sreeja@kreara.com)

Infile has a number of options available.

FLOWOVER

FLOWOVER is the default option on INFILE statement. Here, when the INPUT statement reaches the end of non-blank characters without having filled all variables, a new line is read into the Input Buffer and INPUT attempts to fill the rest of the variables starting from column one. The next time an INPUT statement is executed, a new line is brought into the Input Buffer.

Consider the following text file containing three variables id, type and amount.

11101 A

11102 A 100

11103 B 43

11104 C

11105 C 67

The following SAS code uses the flowover option which reads the next non missing values for missing variables.

data B;

infile "External file" flowover;

input id $ type $ amount;

run;

which creates the following dataset

MISSOVER

When INPUT reads a short line, MISSOVER option on INFILE statement does not allow it to move to the next line. MISSOVER option sets all the variables without values to missing.

data B;

infile "External file" missover;

input id $ type $ amount;

run;

which creates the following dataset

TRUNCOVER

Causes the INPUT statement to read variable-length records where some records are shorter than the INPUT statement expects. Variables which are not assigned values are set to missing.

Difference between TRUNCOVER and MISSOVER

Both will assign missing values to variables if the data line ends before the variable’s field starts. But when the data line ends in the middle of a variable field, TRUNCOVER will take as much as is there, whereas MISSOVER will assign the variable a missing value.

Consider the text file below containing a character variable chr.

ccc

dddd

eeeee

ffffff

Consider the following SAS code

data trun;

infile "External file" truncover;

input chr $3. ;

run;

When using truncover option we get the following dataset

data miss;

infile ""External file" missover;

input chr $3. ;

run;

While using missover option we get the output

2009-08-18T23:38:00.000-07:00

An alternative method for pre-load format with PROC SQL

Prepared by Sujith K G (sujith@kreara.co m)

Preloadfmt is an option which works with proc means, proc tabulate and proc summary. This option requests SAS to pre-load all the format values for a class variable even if the particular value is not presented in the dataset i.e. it enables count to be presented as 0 for a particular category of the variable which is missing in the dataset.

Proc Sql is a widely used SAS procedure. In Proc Sql neither is the Preloadfmt option available nor is there any other option that supports the preload function. The following example describes a method for obtaining the preloadfmt functionality.

The concept is to take the Cartesian product of the class variables for which the results have to be obtained.

The following dataset presents 15 subjects falling into two groups of subjects with four different treatment groups applied between them,

data eg01;

input id grp $ trt $;

cards;

01 A TRT1

02 B TRT3

03 A TRT4

04 A TRT1

05 B TRT1

06 A TRT3

07 A TRT4

08 B TRT1

09 A TRT1

10 A TRT3

12 B TRT3

13 A TRT1

14 B TRT2

15 A TRT4

;

run;

*Defining formats for treatment and group;

proc format;

value $trtc

"TRT1"="Treatment 1"

"TRT2"="Treatment 2"

"TRT3"="Treatment 3"

"TRT4"="Treatment 4";

value $grpc

"A"="Group A"

"B"="Group B";

run;

*Determining the frequency;

proc freq data=eg01 noprint;

table grp * trt /out=eg02(drop=percent);

run;

*Proc format procedure used for getting dataset with available formats in the session;

proc format cntlout=formats;

run;

The dataset formats contains information of all the formats which is used in this session.

proc sql;

*The Cartesian product;

*Here the formats dataset is separated into two one which contains Group classes and another with treatment classes and the two datasets are joined to form the Cartesian product;

create table fmtcomp as

select a.START label="Group" as grp, b.START label="Treatment" as trt

from formats(where=(fmtname='GRPC')) as a, formats(where=(fmtname='TRTC')) as b;

quit;

The resultant dataset contains all the combinations from the two variables.

proc sql;

*The Cartesian product;

*Here the formats dataset is separated into two one which contains Group classes and another with treatment classes and the two datasets are joined to form the Cartesian product;

create table fmtcomp as

select a.START label="Group" as grp, b.START label="Treatment" as trt

from formats(where=(fmtname='GRPC')) as a, formats(where=(fmtname='TRTC')) as b;

quit;

The final data set is obtained as,

2009-03-13T00:02:00.000-07:00

Shift table

Prepared by Mohanan K K

Laboratory test results are commonly labeled as "low", "high" or "normal" depending on whether the observed value is below the lower reference limit, above the upper reference limit or between the limits. These categorical outcomes are commonly summarized using shift tables. A laboratory shift table is a tabular display that can show how a population’s laboratory data change, or ‘shift’, over time. A shift table can provide this information at a glance.

The following example illustrates how a shift table presents changes in laboratory values from visit to visit. Here we consider the laboratory parameter chloride, in the laboratory group bio-chemistry. The normal range for the parameter is 98 to 107. Then the laboratory values obtained for chloride are categorized as low, normal and high according as described above. Here the lab values less than or equal to 98 are flagged as Low, the lab values within 97 and 107 are flagged as Normal and the lab values above 107 as high. There are three visits in this example screening, visit 1 and visit 2. The screening is considered as baseline visit so here we consider two cases

1. Changes occurred in lab values from screening to visit 1
2. Changes occurred in lab values from screening to visit 2

*********************************************************;

*Program name: Shift table;
*Purpose: Illustrate how a shift table create and present;
*********************************************************;
*Give formats for Visits;
proc format;
value vsyn 0='Screening'
1='Visit-1'
2='Vist-2';
*Give formats for categories;
value flg -1='Low'
0='Normal'
1='High';
run;

data lab;
length labgrp $20 labparam $20;
format visit vsyn. flag flg.;
input SUBNO VISIT labgrp&$ labparam&$ val low high;
if val <=low then flag=-1; else if val>low and val<=high then flag=0; else if val>high then flag=1;
cards;

1 0 Bio chemistry Chloride (MMOL/L) 108 98 107
1 1 Bio chemistry Chloride (MMOL/L) 101 98 107
2 0 Bio chemistry Chloride (MMOL/L) 105 98 107
2 1 Bio chemistry Chloride (MMOL/L) 97 98 107
3 0 Bio chemistry Chloride (MMOL/L) 101 98 107
3 1 Bio chemistry Chloride (MMOL/L) 100 98 107
4 0 Bio chemistry Chloride (MMOL/L) 104 98 107
4 1 Bio chemistry Chloride (MMOL/L) 106 98 107
5 0 Bio chemistry Chloride (MMOL/L) 101 98 107
5 1 Bio chemistry Chloride (MMOL/L) 108 98 107
6 0 Bio chemistry Chloride (MMOL/L) 103 98 107
6 1 Bio chemistry Chloride (MMOL/L) 103 98 107
7 0 Bio chemistry Chloride (MMOL/L) 105 98 107
7 1 Bio chemistry Chloride (MMOL/L) 104 98 107
8 0 Bio chemistry Chloride (MMOL/L) 97 98 107
8 1 Bio chemistry Chloride (MMOL/L) 108 98 107
9 0 Bio chemistry Chloride (MMOL/L) 100 98 107
9 1 Bio chemistry Chloride (MMOL/L) 100 98 107
10 0 Bio chemistry Chloride (MMOL/L) 103 98 107
10 1 Bio chemistry Chloride (MMOL/L) 102 98 107
11 0 Bio chemistry Chloride (MMOL/L) 100 98 107
11 1 Bio chemistry Chloride (MMOL/L) 102 98 107
12 0 Bio chemistry Chloride (MMOL/L) 109 98 107
12 1 Bio chemistry Chloride (MMOL/L) 104 98 107
13 0 Bio chemistry Chloride (MMOL/L) 99 98 107
13 1 Bio chemistry Chloride (MMOL/L) 101 98 107
14 0 Bio chemistry Chloride (MMOL/L) 101 98 107
14 1 Bio chemistry Chloride (MMOL/L) 100 98 107
15 0 Bio chemistry Chloride (MMOL/L) 110 98 107
15 1 Bio chemistry Chloride (MMOL/L) 96 98 107
1 2 Bio chemistry Chloride (MMOL/L) 108 98 107
2 2 Bio chemistry Chloride (MMOL/L) 99 98 107
3 2 Bio chemistry Chloride (MMOL/L) 100 98 107
4 2 Bio chemistry Chloride (MMOL/L) 106 98 107
5 2 Bio chemistry Chloride (MMOL/L) 96 98 107
6 2 Bio chemistry Chloride (MMOL/L) 103 98 107
7 2 Bio chemistry Chloride (MMOL/L) 108 98 107
8 2 Bio chemistry Chloride (MMOL/L) 103 98 107
9 2 Bio chemistry Chloride (MMOL/L) 100 98 107
10 2 Bio chemistry Chloride (MMOL/L) 96 98 107
11 2 Bio chemistry Chloride (MMOL/L) 102 98 107
12 2 Bio chemistry Chloride (MMOL/L) 104 98 107
13 2 Bio chemistry Chloride (MMOL/L) 101 98 107
14 2 Bio chemistry Chloride (MMOL/L) 100 98 107
15 2 Bio chemistry Chloride (MMOL/L) 99 98 107
;

*Create datasets for each of the visits and rename the flag variable;

data scr (where=(visit=0)rename=(flag=flg0))
vis1(where=(visit=1)rename=(flag=flg1))
vis2(where=(visit=2)rename=(flag=flg2));
set lab;
run;

*Merge the datasets so that the flags for the three visits lie adjacent to each other;

data comon;
merge scr vis1 vis2;
run;

*Find number of subjects for all combinations of laboratory flags

from baseline (screening) to visit 1;
proc means data=comon completetypes noprint missing;
class labgrp labparam flg0 flg1 /preloadfmt ;
output out=shif01 N=num;
run;

*Transposing data into presentable format;

proc transpose data= shif01(where=(flg1 ne . and flg0 ne .)) out=trn1;
by flg0 notsorted;
id flg1;
var num;
copy labgrp labparam;
run;

*Find number of subjects for all combinations of laboratory flags from baseline (screening) to visit 2;

proc means data=comon completetypes noprint missing;
class labgrp labparam flg0 flg2 /preloadfmt ;
output out=shif02 N=num;
run;

*Transposing data into presentable format;

proc transpose data= shif02(where=(flg2 ne . and flg0 ne .)) out=trn2;
by flg0 notsorted;
id flg2;
var num;
copy labgrp labparam;
run;

*Combine two transposed datasets to create report;

data final(where=(_NAME_ ne '' and labgrp ne '' and labparam ne ''));
merge trn1
trn2(rename=(low=low2 normal=normal2 high=high2));
run;

*Determining number of subjects under each flag at baseline;

data base;
set shif01;
keep flg0 num;
where labgrp eq '' and labparam eq '' and flg1 eq . and flg0 ne .;
rename num=basenum;
run;

data final1;
merge final base;
by flg0;
run;

*rtf output of shift table;

option nodate nonumber;

ods rtf file=".\shifteg.rtf";
proc report data= final1 nowd style(header)=[background=white font_size=8 pt] split='*';
column labgrp labparam flg0 ('Screening vs. Visit 1' Low Normal High ) ('Screening vs. Visit 2' Low2 Normal2 High2 ) basenum;
define labgrp/order 'Lab Group'left;
define labparam/order 'Lab Parameter' left;
define flg0/display 'Baseline *Status'left;
define Low/display 'Low' center;
define Normal/display 'Normal' center;
define High/display 'High'center;
define Low2/display 'Low'center;
define Normal2/display 'Normal'center;
define High2/display 'High'center;
define basenum/display 'Baseline*Count' center;
run;
ods rtf close;

The output is obtained as shown below

In the table the column named ‘Baseline Count’ represents the number of low, normal and high flags at baseline visit(or screening) i.e. there is 1 subject with low flag, 11 with normal flag and 3 subjects with high flag.

The ‘Screening vs Visit 1’ section is a 3x3 contingency table. The value in first cell (first row, first column) presents the number of subjects for whom the flag was low both at Screening and Visit1. The second cell (first row, second column) further presents the number of subjects with low flag at screening and normal flag at visit1 and so on.

2009-03-06T01:09:00.000-08:00

The Bootstrap Method

Prepared by Meena R S

Bootstrap method is a way of simulating results for a larger number of samples based on the given sample. The bootstrap method is used to quantify the uncertainty in any parameter estimate (e.g., mean, variance, percentile value, etc.). All bootstrap methods involve generating hypothetical samples from the original sample. Each hypothetical sample is called a Bootstrap Sample.

Bootstrap method has the following assumptions

1. The sample taken should be a valid representative of the population

2. Bootstrap method takes sampling with replacement from the sample. Each sub sampling is independent and identical distribution (i.i.d.). In other words, it assumes that the sub samples come from the same distribution of the population, but each sample is drawn independently from the other samples.

The bootstrap works by computing the desired statistic for a sub sample of the data set. The sub sampling is done with replacement and the size of the sample is equal to the size of the original sample. The desired statistic is calculated for each sub sample. The collection of these statistics is used as an estimate of the sampling distribution.

Example 1: The following example represents the length of 3 different petals 10 trees of the same type. This program estimates the uncertainty parameters mean and standard deviation

data petals;
input petal1 petal2 petal3;
cards;
1.21 1.31 1.53
2.13 2.21 3.17
1.59 1.70 1.56
1.45 1.23 1.21
1.41 1.96 1.24
1.04 1.8 1.58
1.03 1.05 2.1
1.4 1.25 1.26
1.56 1.26 1.34
1.82 1.24 1.56
;
run;

* This macro is used to generate 10 bootstrap samples of the above data;

%macro bootsamp(data,boot, b);
data &boot;
do isample=1 to &b;
do i = 1 to nobs;
pt = round(ranuni(0) * nobs) ;
set &data nobs = nobs point=pt; *point options is used to create samples in any order;
output;
end;
end;
stop;
run;
%mend;

%bootsamp(petals, boot, 10); *Generating 10 bootstrap samples;

*Calculating the parameters mean and standard deviation for each subsample and appending them to obtain the final sample dataset;

%macro sample(j=, n=);
%do i=&j %to &n;
data petals1;
set boot;
where isample=&i;
run;

proc means data=petals1 ;
var petal1 petal2 petal3 ;
output out = petals_&i mean = mean std = std n =n;
run;

proc append base=final data=petals_&i force;
run;
%end;
%mend;

%sample (j=1, n=10);

proc means data=final mean std ;
var mean std;
output out = means_ mean = mean std = std n =n;
run;

Output is shown below

2009-03-06T00:59:00.000-08:00

Use of ampersands and semicolons in SAS macros

Prepared by Jose Abraham

Single, double and triple ampersands

Multiple ampersands can be used to allow the value of a macro variable to become another macro variable reference. The macro variable reference will be rescanned until the macro variable is resolved.

The following demonstrates how macro variables with multiple ampersands are resolved. There are 4 macro variables

Macro variable :Value
A : CATCH
B : STUMP
C : RUN
HIT : A

Resolving a macro variable:

&VARNAME references a macro variable. The rule is that the scanner reads from left to right.

1. If we put one ampersand i.e., ‘&HIT’ then the macro variable hit resolves to ‘A’.

2. If we put two ampersands then the two ampersands resolve to one and scanner continues. i.e., ‘&&HIT’
On the first scan - ‘&&’ resolves to ‘&’ and ‘HIT’ held as token.
On the second scan – ‘&HIT’ resolves to ‘A’.

3. If we put three ampersands i.e., ‘&&&HIT’
On the first scan -‘&&’ resolves to & and the remaining &HIT resolves to ‘A’ and the it results ‘&A’
On the second scan –‘&A’ resolves to ‘CATCH’

Single and double semi colons
When creating macros for programming, sometimes we would like to generate a dynamic SAS statement within a macro %DO loop. For example if we want to run a print procedure inside a macro and refer to a set of macro variables within the VAR statement.

proc print;
var
%do i = 1 %to &max;
&&var&i
%end;;
run;

Consider a simple program containing this %DO loop in a macro

data one;
input A $ B C D E;
datalines;
a 12 16 18 20
;
run;

%let var1=A;
%let var2=B;
%let var3=C;
%let var4=D;
%let var5=E;
%let max=4;
%let indt=one;

%macro prnt;
proc print data=&indt.;
var
%do i = 1 %to &max.;
&&var&i
%end;;
run;
%mend;

%prnt;

In this program, there are two consecutive semicolons used after the %end statement which is not common in a simple SAS program. Here the first semicolon closes the %END and the second semicolon closes the VAR statement. And if we run this macro it will generate the following SAS statements

proc print data=one;
var a b c d;
run;

and it produces the result

2009-03-05T22:20:00.000-08:00

Alignment of decimal points

Prepared by Sreeja E V

As per quality standards when presenting descriptive statistics for parameters in clinical trial reporting, the data should be aligned with respect to the decimal point. This dynamic decimal alignment and numeric precision should be maintained between varying parameters in the same dataset.

The following example contains 4 parameters A, B, C and D and their values. We have to present the descriptive statistics namely n, mean, standard deviation, minimum, median and maximum. The mean, standard deviation and median will be presented to one more decimal place than the observed value while minimum and maximum will be presented to the same number of decimal places as observed value. The value for n will be presented as integer.

As a first step the descriptive statistics needs to be computed for the parameters and then it is required to determine the number of decimal places needed for the descriptive statistics for each parameter. The observed value with the most number of decimal places is then found out and the maximum number of decimal places used to present the data is determined for each parameter.

Once the maximum number of decimal places per parameter is obtained, one simply needs to pass this information into a character variable containing a representation of the appropriate numeric format as described.

Further the maximum integer length for each parameter is determined and white space is inserted using repeat function for values whose integer length is less than maximum integer length.

data lab;
input parameter $ value;
datalines;
A 12.3654
A 13.1
B 456.1
B 456
C 41.236
C 41.04
D 1.76
D 1.241
;
run;

proc means data=lab noprint;
by parameter;
var value;
output out=desc_data N=N Mean=Mean Std=std Min=Min Median=Median Max=Max;
run;

*Determining the number of decimal points;
*For that the values of all the parameters have been converted to character values so that the digits after the decimal places can be extracted to the variable de_part and its length can be stored in the variable dec_no. If the values of a particular parameter are whole numbers then dec_no will be assigned to zero;

data deci_point;
set lab;
value_n=put(value,best.);
de_part=scan(value_n,2,'.');
if de_part ne ' ' then dec_no=length(de_part);
else dec_no=0;
run;

*Determining maximum number of decimal points for each parameter; *Here the maximum of the variable dec_no for each parameter is determined and stored in the variable decimal;

proc sql noprint;
create table decimal as select
distinct parameter,
max(dec_no) as decimal
from deci_point
group by parameter;
select * from decimal;
quit;

*Creating the formats;

*The variables zerornd, onernd, zerofmt and onefmt are determined for each parameter for rounding and formatting purpose;

proc sql noprint;
create table decimal_1 as select
distinct
parameter,
decimal,
10**(-decimal -0) format best. as zerornd,
10**(-decimal -1) format best. as onernd,
"8." put(decimal +0,1.) as zerofmt,
"8." put(decimal +1,1.) as onefmt
from decimal
;
select * from decimal_1;
quit;

*Applying decimal formats;

data desc_stats(keep=parameter fn fmean fmedian fstd fmin fmax );
merge desc_data decimal_1;
by parameter;
fn=compress(put(n,3.));
if mean ne . then fmean=compress(putn(round(mean,onernd),onefmt));
if median ne . then fmedian=compress(putn(round(median,onernd),onefmt));
if std ne . then fstd=compress(putn(round(std,onernd), onefmt));
if min ne . then fmin=compress(putn(round(min,zerornd),zerofmt));
if max ne . then fmax=compress(putn(round(max,zerornd), zerofmt));
run;

proc sort data=desc_stats;
by parameter;
run;

proc transpose data=desc_stats out=stat;
var fn fmean fstd fmin fmedian fmax;
by parameter;
run;

*To align decimal points;

*Length of integer part of each value is determined and stored in the variable lenint. Further maximum integer length is obtained by determining maximum over lenint and maxint where initial value of the variable maxint is set to zero. While attaining end of the file the value of maxint is assigned to the macro variable max;

data outdata;
set stat(rename=(col1=value)) end=eof;
retain maxint 0;
lenint=length(compress(scan(value,1,'.')));
maxint = max(maxint, lenint);
if eof then call symput("max", put(maxint, best.));
run;

*The difference between the variable max and lenint is determined by the variable diffint. For observations whose diffint>0 (i.e.the observations whose integer length is diffint times less than max) white space is inserted diffint-1 times using repeat function (repeat function gives repetitions after the original string) and concatenates that with the value after removing trailing blanks of value using trim function. For observations whose diffint=0 (i.e.the observations whose integer length same as max) no white space is inserted;

data aligned(drop=maxint lenint diffint value);
retain parameter _name_ value value_aligned;
length value_aligned $15;
set outdata;
if parameter ne '' and value ne '' then do;
diffint = &max - lenint - 1;
if diffint >= 0 then do;
value_aligned = repeat(" ", diffint)trim(left(value));
end;
else do;
value_aligned = trim(left(value));
end;
end;
run;

proc format ;
value $stat
"fn"="n"
"fmean"="Mean"
"fstd"="SD"
"fmin"="Minimum"
"fmedian"="Median"
"fmax"="Maximum"
;
run;

proc print data=aligned;
format _name_ $stat.;
run;

The output is obtained as

2008-10-10T06:42:00.000-07:00

SURVIVAL ANALYSIS
Prepared by Jose Abraham

Survival analysis (also called time to event analysis) is concerned with studying the time between entry to a study and a subsequent event. These methods are most often applied to the study of deaths. In fact, they were originally designed for that purpose, which explains the name survival analysis. Survival analysis is an important medical concern and is extremely useful for studying events like onset of disease and recurrence of disease.

The point of survival analysis is to follow subjects over time and observe at which point in time they experience the event of interest. The data which is obtained from survival studies may contain censored observations. Censoring comes in many forms and occurs for many different reasons.

For example if we consider a cancer study in which the subjects after response from treatment were followed up for a specific period of time for the recurrence of cancer (event of interest). If a subject experiences recurrence at time t, which is not known exactly and all we know that the event occurred after a specific time T (i.e. t>T), then the last time at which the subject was observed is recorded and the survival time for that subject is considered as right censored. Also if the recurrence is experienced before a specific time, and the exact time is unknown, then the survival time recorded from that subject is considered as left censored. So the times obtained from subjects who are having no recurrence until the end of the study and those who were lost to follow up, before the end of the study period are censored.

In the aforesaid study, the basic structure of the data is that for each case there is one variable which contains either the time that recurrence happened or, for censored cases, the last time at which the case was observed, both measured from the chosen origin. Another variable that denotes the censoring status of each case is also present (uncensored =1 and censored=1). Also the data contain values of other variables such as markers, tissues etc…. A small part of data in this form is given below

data molecules;
input marker surv censor stage histo;
datalines;
0 75 1 2 1
1 115 0 3 2
1 96 1 1 1
0 110 0 2 3
0 178 0 3 2
1 149 1 2 3
1 163 1 4 4
0 211 1 1 2
1 167 1 2 1
0 195 0 2 1
1 140 1 3 4
0 202 0 4 4
0 153 0 2 2
1 147 0 1 3
0 132 0 4 1
0 178 1 3 2
;
run;

Analysis of censored data can be easily performed in SAS with the help of various procedures like PROC LIFETEST, PROC PHREG etc.The purpose of the analysis is to model the underlying distribution of the survival time variable and to assess the dependence of the survival time variable on the independent variables.

The Kaplan Meier curve is plotted by taking disease free survival time on the horizontal axis and survival probability on the vertical axis. This curve is useful to measure the proportion of patients surviving at a specific time. Also we can compare the survival experience of two groups by comparing their curves. This comparison of survival estimates can be done by making use of the strata statement in PROC LIFETEST. The significant differences of the Kaplan Meier curves can be tested by Logrank test. If the p-value in the log-rank test is large (>0.05) then we can say that there is no difference in survival. The piece of SAS code for doing this comparison of survival curves between those cases in which the marker is present (marker=1) and those in which it is not present (marker=0).

proc lifetest data= survdata method=km plots=(s,lls) outsurv=option;
time surv*censor (0);
strata marker;
run;

The strata statement provides the log rank test and Wilcoxon test statistics. The outsurv= option in the proc lifetest statement to create a SAS data set that has the KM survival estimates. Plots=(s, lls) produces log-log curves as well as survival curves. The log-log survival curves will be parallel or nearly parallel if the proportional hazard assumption is met.

We can make use of this lifetest procedure to compute the non parametric estimates of the survivor function by Kaplan Meier method. The option method=km in the PROC LIFETEST produces Kaplan-Meier survival estimates and the option Plots=(s) plots the estimated survival function. A part of SAS output showing the survival estimates and the Kaplan-Meier curve is given below

Kaplan – Meire Curves

Hazard ratio is a reasonable estimate for representing the effect of different factors in event occurrence. Cox regression model can be used and it models the time to event data. This can be done in SAS using the PROC PHREG. The following piece of code can be used to model the data

proc phreg data =molecules;
model surv*censor(0) =marker stage histo /rl ties=breslow selection=b;
baseline out=out1 survival=s logsurv=ls loglogs=lls;
run;

The backward selection procedure (with the option selection=b) in Cox’s regression removes the non-significant variables from the regression model and it includes only significant variables in the final model. The option ties= breslow is used to handle the ties. Proc phreg produces the regression coefficients and their standard errors for the variables which were included in the final model along with the p-values obtained from the Wald’s chi-square test. Hazard ratios and their 95% confidence intervals for those variables are also included in the output.

A part of the output is given below

Hazard ratios can be interpreted similarly as that of interpreting odds ratios, i.e. a hazard ratio of 1 for an explanatory variable can be interpreted as it has no effect on the hazard. While a hazard ratio less than 1 denotes that the variable effect results in a decreased hazard. And a hazard ratio greater than 1, denotes that the variable effect results in an increased hazard.

2008-10-10T05:28:00.000-07:00

Quality Control (QC): steps towards effective programs and outputs
Prepared by Mohanan K K

The term SAS QC refers to the maintenance of the quality of data and quality of programming. The quality of data refers to the Accuracy, Completeness, Consistency, Timeliness, Uniqueness and Validity of data. The quality of programming on the other hand means that the SAS program should produce correct and meaningful outputs and at the same time meet all standards like indentation of statements, optimization of code, use of drop and keep statements and error/warning free logs to name a few.

The QC personnel involved in the SAS QC process are SAS programmers who are independent of the actual programming that is being carried out for the study. At Kreara, the SAS QC process involves the following steps

a) Checking the quality of SAS code and outputs developed.
b) Entering the review comments into the issue tracker.
c) Tracking the resolution of the review comments.

The QC personnel review the code, log and output and raise issues in an issue tracker which is a web application accessible to the team members and which helps in tracking the resolution of issues. The issues raised by the QC are made available to the SAS Programmer who in turn corrects the code as per comments and flags the issue as resolved. The issues are closed by the QC personnel when the correction is satisfactory.

At Kreara intensive QC of codes and outputs is done in four stages as described below

1. Output QC
2. Log QC
3. Code QC
4. Parallel Programming

1. Output QC

The Output QC further includes

a. Sample or complete check against actual data
b. Check against the template

During the output QC, the QC personnel checks whether the outputs produced are as per template or requirements. In addition a sample check is performed against the database. The sample size for sample check varies depending on the study. In case of tables a complete check is done on the outputs produced.

2. Log QC

The SAS program always generate a log file. As part of the Log QC, the QC personnel is required to look for errors, warnings and critical notes in the log. Critical notes may include “Missing values were generated as a result of performing an operation on missing values”. The Log QC is aimed at making the log free of warnings, errors and notes.

3. Code QC

The code QC involves step by step review of the code. The following aspects of the code need to be reviewed

a. Adherence to the requirements
b. Logic
c. Syntax
d. Optimization
e. Presentation
f. Completeness of datasets

A peer review is carried out during which the SAS Programmer is required to explain the code to the QC personnel. Any discrepancies are discussed and corrected by the SAS Programmer.

4. Parallel Programming

Parallel programming is included in the QC process at Kreara. Parallel programming helps in both the output QC and optimization of code. During the parallel programming the QC personnel generates the outputs as per requirement without emphasis on the template and SAS programming standards/practices. The outputs generated by parallel program are compared to actual output for discrepancies. The parallel program may also be compared with actual program in order to improve the Quality of programming.

The following example explains the parallel programming in QC process.

If a SAS programmer calculates the confidence interval, using the ‘tinv’ function in the data step as shown below, a parallel programmer or QC personnel uses the simple proc means procedure and then the outputs are compared.

PROC UNIVARIATE DATA=old;
BY id ;
VAR anal;
OUTPUT out=new n = n1 n2
mean = mean1 mean2
std = std1 std2
;
RUN;

DATA new1;
SET new;
n1 = PUT(n1,4.0);
n2 = PUT(n2,4.0);
mn1 = PUT(mean1,6.1);
mn2 = PUT(mean2,6.1);
sd1 = PUT(std1,7.2);
sd2 = PUT(std2,7.2);

IF n1 NE 0 THEN DO;
clh1 = mean1 + tinv(0.975,n1-1) * std1 / sqrt(n1);
cll1 = mean1 - tinv(0.975,n1-1) * std1 / sqrt(n1);
ci1 = "("PUT(clh1,6.2)","PUT(cll1,6.2)")";
END;
IF n2 NE 0 THEN DO;
clh2 = mean2 + tinv(0.975,n2-1) * std2 / sqrt(n2);
cll2 = mean2 - tinv(0.975,n2-1) * std2 / sqrt(n2);
ci2 = "("PUT(clh2,6.2)","PUT(cll2,6.2)")";
END;
RUN;

The output can be simply obtained using proc means procedure as follows

proc means data=new ;
BY id;
VAR anal;
OUTPUT out=sum1
n = n1 n2
mean = mean1 mean2
std = std1 std2
lclm = ll1 ll2
uclm = ul1 ul2;
RUN;

The given parallel program suggests the reduction of steps and on the other hand the output produced by the parallel program is compared with actual output, as part of the output QC.

The Quality Control process is carried out until good quality outputs and code are obtained.

2008-10-10T05:24:00.000-07:00

Cochran-Armitage Trend Test
Prepared by Sreeja E V

In clinical trials, it is often of interest to investigate the relationship between the increasing dosage and the effect of the drug under study. Usually the dose levels tested are ordinal, and the effect of the drug is measured in binary. In such cases, Cochran-Armitage trend test is most frequently used to test for trend.

Here, the Null hypothesis (H0): There is no linear trend in effect of the drug under study across increasing levels of dosage. Alternative hypothesis (H1): There is linear trend in effect of the drug under study across increasing levels of dosage.

Consider an example. The data set effect contains hypothetical data for a clinical trial of a case control study. The clinical trial investigates whether the variable cascon relates with different genotype statuses. Subjects have one of either three genotype statuses 1, 2 or 3 where 1 represents abnormal, 2 represents partially abnormal and 3 represents normal status. The variable cascon has values 1=’Case’ and 2=’Control’. The number of subjects for each group is represented by the variable Count.

data effect;
input status cascon Count @@;
datalines;
1 1 15 1 2 26
2 1 19 2 2 10
3 1 20 3 2 3
;
run;

proc freq data=effect;
tables status*cascon / trend measures cl;
weight Count;
title 'Clinical Trial for case control study’;
run;

The output will appear as follows

Cochran-Armitage Trend Test
*************************

Statistic (Z) 4.0252
One-sided Pr > Z <.0001

Two-sided Pr > Z <.0001

Sample Size = 93

We consider the two-sided -value tests against either an increasing or decreasing alternative. Using trend test we get Pr > Z <.0001. Thus the null hypothesis is rejected and it is concluded that there exists a trend in binomial proportions of response across gene status.

2008-10-10T04:43:00.000-07:00

Execute a set of files in SAS.
Prepared by Rupesh R

There are situations where prior to running a SAS Editor(s) one may be required to run a list of files (SAS or non SAS). Our objective is how to call them in a single statement.

We need to run a set of SAS files prior to a SAS code. The usual scenario is to execute them one by one. But it is possible to access a set of files or members from this storage location by a single statement as follows.

Using filename statement we assign the fileref storage in an aggregate location.

filename storage “An- Aggregate –storage- location”;

Several files or members from this storage location can be accessed by listing them in parentheses after the fileref in a single %INCLUDE statement
%inc storage (Monthly, Quarterly); Non SAS files can also be accessed using quotation marks around the complete filename listed inside the parentheses. %inc storage ("file-1.txt","file-2.dat","file-3.cat"); Auto call SAS macros and Formats When the SAS editors contain user defined macros the above %inc statement does not work. In this situation we use sasautos option. Usually the formats and macros will be in separate folders. In those situations they can be called as follows. Libname project “project-path”;Libname formlib “format –path”;Libname mymacros “macro-path”; options fmtsearch=(formlib project) sasautos=( mymacros) mautosource ;
The fmtsearch option searches the formats in the files or libraries in the following order

1. Work.formats
2. formlib.formats
3. project.formats

Sasautos option invokes the macros in the file reference storage.

The auto call facility is usually used when all user-defined macros are stored in a standard location and they are not compiled until they are actually needed.
But when we get formats and macros in the same folder it is better to use the following statement.Options fmtsearch=( storage project) sasautos=( storage ) mautosource ; Here even though library work is not specified the fmtsearch option will search for the formats in the work library by default as mentioned earlier.The formats can also be called without using fmtsearch option if we know the name of SAS file which contains all the formats for the particular study. We can access the formats using a single %include statement.

%inc storage (formats);

Here the SAS editor formats contain all the formats for the study.

2008-10-10T04:29:00.000-07:00

WARNING: 25% of the cells have expected counts less than 5. Chi-Square may not be a valid test.
Prepared by Rajeev V

The chi-square test is a one of the tools in statistics to compare observed data with data we would expect to obtain according to a specific hypothesis. Procedure freq with option chisq help us to determine evidence for the association between two categorical variables in SAS.

While performing chi square test using proc freq in SAS one may sometimes encounter such a warning, WARNING: 25% of the cells have expected counts les than 5. Chi-Square may not be a valid test.

This type of warning arises in output window when the expected count in any of the cells is less than 5 when performing Pearson chi-square test; for example the expected counts for row2column1 in the below table is calculated as (16X235)/766 equal to 4.9086. If we see this type of warning just avoid p value corresponding to Pearson chi-square test and take into consideration p value of Fisher’s exact test. These are explained below using an example:-

Data _cat_;
Input grp $7. Cat1 $4;
Cards;
Case ABN
Control NRM
………………….
………………….
;
run;

ods output Chisq=chitb_1(where =(statistic in ("Chi-Square")))
FishersExact=fishexctb_1(where=(label1="Two-sided Pr<=P"));

proc freq data=_cat_;

table grp*cat1/chisq expected nocol norow nopercent ;

by _name_;

run;

ods output close;

The output will be,

The p-value obtained on performing the chi-square test above may not measure the association because (2, 1) th expected count is less than 5. SAS automatically performs Fisher's exact test for 2×2 tables but for tables larger than 2x2, exact tests are requested by using the exact option on the table statement or using exact fisher statement after table statement. SAS generate every possible table that is compatible with the given marginal totals, and calculates the exact probability p of each table, using Fisher’s formula (1934). By summing the probabilities of the extreme tables we obtain a P value that is used in the usual classical way as a test of the null hypothesis.From our example we will consider the two sided p value (1.00) from Fisher’s Exact Test.

2008-10-10T02:35:00.000-07:00

Calculation of adjusted odds ratio using Proc logistic

Prepared by Resmi Sukumar

Adjusted odds ratios are the odds of a dichotomous event adjusted for or controlling for other possible variables in the model. For example in a model where the response variable is the presence or absence of a disease, an odds ratio for a binomial exposure variable is an adjusted odds ratio for the levels of all other risk factor included in the model.

Adjusted odds ratio and corresponding 95% confidence interval is obtained by performing logistic regression analysis, this technique is implemented in the SAS® System using PROC LOGISTIC.

Logistic regression analysis provides adjusted odds ratio if adjustors are used as additional predictors, otherwise it provides unadjusted odds ratio.

The general syntax of PROC LOGISTIC is:

PROC LOGISTIC DATA=dsn ;
MODEL depvar = indepvar(s)/options;
RUN;

Example:
Suppose we are interested in conducting a case control study to evaluate the relation among cases and controls between different genotypes. The different gene statuses are ‘abnormal’ and ‘normal’ where normal is considered as referent group. For this purpose we generate a dataset as follows

/*Random data generation*/

data genestat;
do i=1 to 50;
gene=round(1 + (3-1)*uniform(10));
age =round(1+(3-1)*uniform(15));
ethnic=round(1+(3-1)*uniform(14));
status=round(1+(2-1)*uniform(16));
cascon=round(1+(2-1)*uniform(17));
output;
end ;
drop i;
run;

/*formats */
proc format;
value gene 1= 'Gene1' 2= 'Gene2' 3= 'Gene3';
value cascon 1='Case' 2='Control';
value age 1='<18' 2="'18-35'" 3="'">35';
value ethnic 1='Asian' 2='Caucasian' 3='Other';
value status 1='Abnormal' 2='Normal ';

proc sort data=genestat ;
by gene;
format gene gene. cascon cascon. status status. age age. ethnic ethnic.;
run;

Let’s consider a model with variable status, age and ethnic are as predictors.

/*proc logistic for calculating adjusted odds ratio*/
ods trace on;
ods output CLoddsWald=gene_cancer(where=(Effect="status Abnormal vs Normal"));

proc logistic data=genestat;
class status/param=ref ref=last;/* reference parameter ref=last
i.e. ref='Normal'*/
model cascon=status age ethnic / clodds=both;/* clodds =gives WALD confidence Interval for odds ratio*/
by gene ;
run;

ods output close;
ods trace off;

The MODEL statement names the response variable and the explanatory effects, including covariates, main effects, interactions, and nested effects. The CLASS statement names the classification variables to be used in the analysis. The CLASS Statement permits specification of a reference level. By default, the lowest level of the variable placed in the CLASS Statement is treated as the reference category. The BY statement is used to obtain separate analyses on observations in groups defined by the BY variables.

The output table is obtained as

This shows that Gene1 and Gene2 are less likely to have the abnormal genotype status in case than control. Adjusted odds ratio for Gene3 shows that the odds of abnormal genotype occurring in the case group are higher than it occurring in control group.

Let's now consider the model where status is the only predictor.

/*proc logistic for calculating unadjusted odds ratio*/
ods trace on;
ods output CLoddsWald=gene_cancer(where=(Effect="status Abnormal vs Normal"));

proc logistic data=genestat;
class status/param=ref ref=last;/* reference parameter ref=last
i.e. ref='Normal'*/
model cascon=status / clodds=both;/* clodds =gives WALD confidence interval
for odds ratio*/
by gene ;
run;

ods output close;
ods trace off;

The output table is obtained as

This shows that the odds of abnormal genotype occurring in the case group are higher than it occurring in control group for gene 3 while it same for genes 1 and 2.

2008-10-10T00:31:00.001-07:00

Scrum - Agile project management

Scrum is a process skeleton that includes a set of practices and predefined roles. The main roles in Scrum are the ScrumMaster who maintains the processes and works similar to a project manager, the Product Owner who represents the stakeholders, and the Team which includes the developers.
During each sprint, a 15-30 day period (length decided by the team), the team creates an increment of potential shippable (usable) software. The set of features that go into each sprint come from the product backlog, which is a prioritized set of high level requirements of work to be done. Which backlog items go into the sprint is determined during the sprint planning meeting. During this meeting the Product Owner informs the team of the items in the product backlog that he wants completed. The team then determines how much of this they can commit to complete during the next sprint. During the sprint, no one is able to change the sprint backlog, which means that the requirements are frozen for a sprint.
There are several implementations of systems for managing the Scrum process which range from yellow stickers and white-boards to software packages. One of Scrum's biggest advantages is that it is very easy to learn and requires little effort to start using.

2008-10-06T05:18:00.000-07:00

Maintaining document standards at Kreara

Prepared by Sreedevi Menon

Documentation is an integral part of clinical trial studies and maintenance of standards while preparing various documents is of utmost importance. The documents related to clinical trial study may be anything from SOPs to documents related to project management, data management, statistics or SAS.

At Kreara, all or some of such documents are prepared as per requirement of the study. The emphasis is not only to make these documents as informative as possible but also to convey the information in a concise and effective manner. Further, effort is taken to maintain the quality of the information contained and the way of presentation.

An SOP for General Documentation Guidelines is maintained at Kreara and all personnel in the organization are trained on the same. This standard operating procedure describes the various guidelines to be followed during preparation and amendment of SOPs in general. It also presents guidelines for preparation of project related documents like the naming conventions to be followed.

In addition to this, individual SOPs are maintained for each and every document and to maintain standards, templates with instructions regarding the contents, layout and formatting of the contents are maintained in a central repository. The personnel responsible for writing the documents are required to follow the format in the templates while preparing the documents. The QC personnel check for any non-compliance to templates in the document in addition to the relevance of contents. Further the QA manager is responsible to ensure that the process is followed correctly.

The personnel at Kreara are trained in the SOPs related to document writing. A great deal of exposure in the related field is provided to them so that they are capable of preparing informative and effective documents.

2008-10-03T06:35:00.000-07:00

SAS COLON MODIFIER “ =: ”
Prepared by : Sujith K G.

Usually we use substr () function to select a string which starts with specific characters or for selecting a part of a string. We can also use Sas Colon Modifier “=:” for performing the same task. Both methods allow comparison of values based on the prefix of a text string. Both these methods have been explained using the following example

Here we have a dataset adverse which contains patient id and name of adverse event.

data adverse;
Input id ae $;
cards;
001 asthma
002 chesttightness
003 dizziness
004 cold
005 headache
006 dysphonia
007 commoncold
008 nausea
009 cough
;
run;

We are interested to flag the adverse events starting with “co” namely cough, cold and common cold as Yes and others as No.

This can be performed by using the SUBSTR() function as described below

data event;
set adverse;
if lowcase(substr(ae,1,2))='co' then res="Yes";
else res="No";
run;

The same purpose can be served by applying the Colon Modifier “=:” as described in the following steps

Now using, Colon Modifier the condition is,

data event;
set adverse;
if lowcase(ae) =: "co" then res="Yes";
else res="No";
run;

As can be seen from the above examples in the substring function we need to specify the position to extract the first two letters while in Colon modifier such a requirement is not needed.

2008-09-25T22:46:00.001-07:00

Kreara - Location

Technopark

View SlideShare presentation or Upload your own. (tags: kreara location)

2008-09-25T00:24:00.001-07:00

Ethical Guidelines for Clinical Research - India and the World

thical Guidelines for Clinical Research - India and the World

View SlideShare presentation or Upload your own. (tags: research clinical)

2008-09-24T00:33:00.001-07:00

Kreara - Clinical Data management and Biomterics

Kreara - Clinical Data management and Biomterics

View SlideShare presentation or Upload your own. (tags: biomterics sas)

2008-09-21T21:56:00.000-07:00

Odds ratio

Prepared by Prajitha Nair & Sreeja E V

In order to quantify the association between the exposure and the outcome of interest the incidence of disease in a group of individuals exposed to the supposed risk factor must be compared with the incidence in a group of persons not exposed. This comparison can be summarized by calculating either the ratio of the measures of disease occurrence for the two groups, which indicates the likelihood of developing the disease in the exposed individuals relative to those unexposed.In case-control studies, it is not possible to directly estimate disease incidence in those exposed and those unexposed, since people are selected on the basis of having or not having the condition of interest, not on the basis of their exposure status. It is however, possible to calculate the odds of exposure in the cases and in the controls.The odds ratio (OR) estimates the magnitude of association between the exposure and outcome. It is defined as the ratio of odds of an event occurring in one group to the odds of it occurring in another group, or to a sample-based estimate of that ratio. These groups might be an experimental group and control group.The 2x2 contingency table showing the relationship between the exposure and the disease is presented as follows:

Probability of being exposed among cases=a/(a+c)Probability of being non-exposed among cases=c/(a+c)Odds of being exposed among cases=a/cProbability of being exposed among controls=b/(b+d)Probability of being non-exposed among controls=d/(b+d)Odds of being exposed among controls=b/dOdds ratio = (odds of being exposed among cases)/ (odds of being exposed among controls)= (a/c)/ (b/d)= (a*d)/ (b*c)
In strict terms, the odds ratio obtained tells us how many more (or less, if the exposure is associated with a reduced risk) times likely the cases are to have been exposed to the factor under study compared with the controls.

If odds ratio is equal to 1 then this implies that the condition or event under study is equally likely in both groups. An odds ratio greater than 1 indicates that the condition or event is more likely in the first group. An odds ratio less than 1 indicate that the condition or event is less likely in the first group. The odds ratio can vary from zero to infinity.

2008-09-21T21:54:00.000-07:00

Odds Ratio using SAS

Prepared by Prajitha Nair

In the case-control study, the risk of cervical cancer was examined in relation to a gene XXXX. The status of the genes is abnormal and normal wherein normal is considered as the referent category.

Consider an example:data gene;input cat $7. genstatus $4. count;cards;case abn 119control abn 68case nor 317control nor 319;run;

ods output RelativeRisks=relrisk(where=(studytype="Case-Control (Odds Ratio)"));proc freq data=gene ;tables cat*genstatus/relrisk ;weight count;run;ods output close;

The table will be as follows:

Odds of exposure among cases=119/317Odds of exposure among controls=68/319Odds ratio= odds of exposure among cases/odds of exposure among controls =1.76

The odds ratio with respect to XXXX shows that the odds of abnormal genotype occurring in case group is 1.76 times higher than it occurring in control group. The 95% confidence interval for the odds ratio is obtained as (1.26, 2.46).The cervical cancer cases were 76% more likely to have abnormal genes than controls. In short, the odds ratio indicates that women who have abnormal genes were 76% more likely to develop cervical cancer than those with normal genes.

2008-09-19T03:06:00.002-07:00

Odds Ratio when cell count is zero

Prepared by Prajitha Nair

If frequency of the counts in any one of the cell is zero then the odds ratio cannot be computed?
Consider the example:

data gene;
input cat $7. genstatus $4. count;
cards;
case abn 119
control abn 0
case nor 317
control nor 319
;
run;

ods output RelativeRisks=relrisk(where=(studytype="Case-Control (Odds Ratio)"));

proc freq data=gene ;
tables cat*genstatus/relrisk ;
weight count;
run;

ods output close;

The output will look as follows:

This can be resolved as follows:
ods output CommonRelRisks=cmnrelrisk;
proc freq data=gene ;
tables cat*genstatus/relrisk cmh ;
weight count;
run;

ods output close;

The output will be produced as:

data cmnrelrisk_1(keep=Value LowerCL UpperCL);
set cmnrelrisk;
if studytype eq " (Odds Ratio)" then if method eq "Logit **" and value ne . then output;
else if studytype="Case-Control" then if method eq "Mantel-Haenszel" and value not in (.,0.0000) then output;
format LowerCL UpperCL ODDSR8.3 value ODDSR8.3;
run;

The cmh option will help to tackle the problem. The logit method will add 0.5 in all the cells of the 2 x 2 cross tabulation table where zero is in anyone of the cell and then odds ratio is evaluated.

Thus the odds ratio obtained is 240.506.

2008-09-04T05:18:00.000-07:00

Kreara - Preclinical research services

View SlideShare presentation or Upload your own.

2008-05-26T22:07:00.000-07:00

Understanding the %pageXof Y macro

Compiled by Rupesh R

The following macro needs to be applied for the purpose of presenting page numbers in Page X of Y format within the body of the document.

When calling the macro, the proc report code should be quoted by %nrstr as explained in step 1.a below. To avoid clutter of code, here the proc report code is created as a macro. This proc report code should contain a ‘compute before_page_’ block as described in the step 5 below.

%macro pageXofY (report= /* proc report code, quoted by %nrstr */ /*1.a*/
, dummy=dummy /* name of the dummy output file */
);
%global page pages len; /* 1.b*/

/-- first run --*/
%let page = 0;
%let len = 8; /* 1.c*/
filename _dummy &dummy.; /* 1.d*/
proc printto print = _dummy; run; /*1.e*/
%unquote (&report.) ;/* 1.f*/
proc printto; run;/*1.g*/
filename _dummy clear; /*1.h*/

%*-- second run --*;
%let pages = &page.; /*1.i*/
%let page = 0;/*1.j*/
%let len = %eval(%length(&pages.) * 2 + 4); /* 1.k*/
%unquote(&report.);/*1.l*/
%mend pageXofY;

Explanation of Macro
Step 1 (1.a): Using %nrstr function we mask the special characters and mnemonics .Here we mask & and % symbols in the proc report code.

Step 2 (1.b): Initialize three global macro variables
§ The variable ‘page’ returns the current page number
§ The variable ‘pages’ returns the total number of pages
§ The variable ‘len’ returns the expected length of the string ‘_XofY’ (2.c) .

Step 3 (1.c): The initial values of macro variables ‘page’ and ‘len’ are assigned as 0 and 8 respectively.

Step 4 (1.d): A dummy file path is defined for the output of proc printto

Step 5 (1.e): PRINTTO procedure is used for printing the output in the specified dummy file (_dummy).

Step 6 (1.f): The proc report code created for generating the output is executed using %unquote function in this step.

%UNQUOTE is to restore normal tokenization of a value whose tokenization was altered by a previous macro quoting function. %UNQUOTE takes effect during macro execution. If the value is not unmasked before it reaches the SAS compiler, the DATA step does not compile correctly and it produces error messages.

1) Execute the entire report procedure and generate an output to the specified file path “&dummy.”

2) In report procedure we should include the following set of statements.

compute before/after _page_;
call execute('%let page = %eval(&page. + 1);'); /* 2.a*/
length _XofY $&len.; /* 2.b. */
_XofY = symget('page') ' of ' symget('pages');/*2.c*/
line 'page ' _XofY $&len..; /* 2.d. */
endcomp;

3) Before/After each page of reporting the variable ‘page’ is calculated and so when we exit from this procedure the macro variable ‘page’ has the value of total number of pages. (i.e. The initial value of ‘page’ is ‘0’ when it comes to the first page of file then it becomes ‘1’ and so on, see step (2.a))

4) We get the total pages of report in variable ‘page’.Here the variable “pages” is not initialized. So symget (‘pages’) will return nothing

Step 7 (1.g): Exit the printto procedure and SAS reset the file path to the output window (by default).

Step 8 (1.h): Clear the dummy file.

Step 9 (1.i): Assign the current value of variable ‘page’ to the macro variable ‘pages’. i.e. we assign the total number of pages to the variable ‘pages’

Step 10 (1.j): Reset the variable ‘page’ to ‘0’.

Step 11 (1.k): Calculate the approximate length of the variable ‘_XofY’ based on current value of ‘pages’.

Step 12 (1.l): Re-execute the report procedure for getting the output as per the requirement.

1) Execute the entire report procedure and generate output in the specified path given in the ods rtf file statement.

2) This time the compute block call the ‘page’ value as the current page and ‘pages’ as the total number of pages. So we will get the page number as Page X of Y form.

The following example illustrates the above macro.Here we get page X of Y on the top of each page.

data one;
do var = 1 to 100;
output;
end;
run;

%Macro Report;
proc report data=one nowd;
column var;
define var / display;
compute before _page_;/*2.a*/
call execute('%let page = %eval(&page. + 1);'); /* 2.b*/
length _XofY $&len.; /* 2.c. */
_XofY = symget('page') ' of ' symget('pages');/*2.d*/
line 'page ' _XofY $&len..; /* 2.e. */
endcomp;
run;
%Mend Report;

/* example usage */

options linesize=64 nonumber nodate;
%pageXofY(report=%nrstr(%Report));

2008-04-16T05:11:00.000-07:00

Different ODS Footers

If suppose we have ten observations and we are required to present the output such that the observation are distributed on different pages depending on the value of the variable “order”. Also the different pages need to have different footers , footers being presented in the body of the document.As a first step, a variable "page" is created which represents the page number corresponding to the observation in the dataset as described below.

data catval1;
set catval end=eof;
if order le 4 then page=1;
else if 5 le order le 7 then page=2;
else if order ge 8 then page=3;
run;

The footers can be presented in the body of the document using compute before /after statements in proc report as below.

proc report data= catval1 ;
column order var1 var2 ;
………………………………
………………………………
Other SAS statements;
…………………………………
………………………………..
compute before page;
If page=1 then footer= "\li75 @ Subjects who select more than one race” ;
If page=2 then footer=" ";
If page=3 then footer="\li75 + BMI = Weight (kg) / [Height (m)]^2";
endcomp;

/*here _page_ is the SAS generated variable */

compute after _page_ / style=[just=l protectspecialchars=off];
footer11= footer;
footer12="\li75 # Overall p-value for continuous variables “
footer13="\li for Categorical variables from CMH general association test";
line @1 footer11 $300.;
line @1 footer12 $300.;
line @1 footer13 $300.;
endcomp;

/* this will give different footers in each page*/
by page;
run;

The first page will contain the following footers

@ Subjects who select more than one race
# Overall p-value for continuous variables
for Categorical variables from CMH general association test

The second page will contain the following footers

# Overall p-value for continuous variables
for Categorical variables from CMH general association test

The third page will contain the following footers
+ BMI = Weight (kg) / [Height (m)]^2
# Overall p-value for continuous variables
for Categorical variables from CMH general association test

2008-04-16T03:27:00.000-07:00

NOTE: Groups are not created because the usage of parameter is DISPLAY.

A SAS dataset named subject is created. The SAS code for the creation of the dataset subject is as follows:
data subject;
input patid name$ sex$ visit $ parameter$ result $;
cards;
0101 lisha f Screening weight 65
0101 lisha f Screening height 150
0101 lisha f Visit1 weight 66
0101 lisha f Visit1 height 150
0102 manu m Screening weight 80
0102 manu m Screening height 165
0102 manu m Visit1 weight 80
0102 manu m Visit2 height 165
;
run;

The aim is to summarize the values across a single observation. The template is as follows:

When using the following code, the output is generated but a Note is also generated in the log as mentioned below:

proc report data=subject nowindows;
column patid name sex visit parameter result;
define patid/"Patient Number" group;
define name/"Subject Number" group;
define sex/"Sex" group;
define visit/"Visit" group;
define parameter/"Test" display;
define result/"Values" display;
run;

The SAS log will look like as follows::
1
2
3 data subject;
4 input patid name$ sex$ visit $ parameter$ result $;
5 cards;
NOTE: The data set WORK.SUBJECT has 8 observations and 6 variables.
NOTE: DATA statement used:
real time 0.01 seconds
cpu time 0.00 seconds
14 ;
15 run;
16
17 proc report data=subject nowindows;
18 column patid name sex visit parameter result;
19 define patid/"Patient Number" group;
20 define name/"Subject Number" group;
21 define sex/"Sex" group;
22 define visit/"Visit" group;
23 define parameter/"Test" display;
24 define result/"Values" display;
25 run;
NOTE: Groups are not created because the usage of parameter is DISPLAY.
NOTE: There were 8 observations read from the data set WORK.SUBJECT.
NOTE: PROCEDURE REPORT used:
real time 0.01 seconds
cpu time 0.01 seconds

A note is produced in the SAS log “NOTE: Groups are not created because the usage of parameter is DISPLAY.”
To remove this note from the log the following code should be used.

proc report data=subject nowindows;
column patid name sex visit parameter result;
define patid/"Patient Number" order;
define name/"Subject Number" order;
define sex/"Sex" order;
define visit/"Visit" order;
define parameter/"Test" display;
define result/"Values" display;
run;

The log is generated as
1
2
3 data subject;
4 input patid name$ sex$ visit $ parameter$ result $;
5 cards;
NOTE: The data set WORK.SUBJECT has 8 observations and 6 variables.
NOTE: DATA statement used:
real time 0.00 seconds
cpu time 0.00 seconds
14 ;
15 run;
16
17 proc report data=subject nowindows;
18 column patid name sex visit parameter result;
19 define patid/"Patient Number" order;
20 define name/"Subject Number" order;
21 define sex/"Sex" order;
22 define visit/"Visit" order;
23 define parameter/"Test" display;
24 define result/"Values" display;
25 run;
NOTE: There were 8 observations read from the data set WORK.SUBJECT.
NOTE: PROCEDURE REPORT used:
real time 0.00 seconds
cpu time 0.00 seconds

The SAS log is now free of the notes, errors and warnings. Instead of using the group variable, use order with display in the define statement.

2008-04-16T02:20:00.000-07:00

Applying Cochran-Mantel–Haenzel (CMH) general association test

Compiled by Rupesh R

Here the objective is to determine the general association between categorical variables subject and ranking for each emotion.

The CMH general association test is applied for this purpose. Proc freq is as described below to carry out the test. Proc freq generates p-values corresponding to each emotion and the results are outputted to the dataset hypnosis1.

The dataset is created as follows

data hypnosis;
input subject emotion $ ranking @@;
cards;
1 fear 4 1 joy 3 1 sadness 1 1 calmness 2
2 fear 4 2 joy 2 2 sadness 3 2 calmness 1
3 fear 3 3 joy 2 3 sadness 4 3 calmness 1
4 fear 4 4 joy 1 4 sadness 2 4 calmness 3
5 fear 1 5 joy 4 5 sadness 3 5 calmness 2
6 fear 4 6 joy 3 6 sadness 2 6 calmness 1
7 joy 4 7 joy 1 7 sadness 2 7 calmness 3
8 joy 3 8 joy 4 8 sadness 2 8 calmness 1
;
run;

The following code is used to carry out the analysis. The option ‘cmh’ in the ‘tables’ statement carries out the test. The option ‘cmhga’ presents the P-value for CMH General Association without a warning in the log.

proc sort;
by emotion;
run;

proc freq;
tables subject*ranking / cmh;
by emotion;
output out=hypnosis1 cmhga;
run;

The dataset hypnosis1 is obtained as follows

emotion	_CMHGA_	DF_CMHGA	P_CMHGA
calmness	14	14	0.449711056
fear	10	10	0.440493285
joy	20.25	21	0.505479124
sadness	21	21	0.458944209

In the dataset p_cmhga will be labeled as ’ P-value for CMH General Association’; df_cmhga as “DF for CMH General Association” and _cmhga_ as “CMH General Association” .

2008-04-15T23:23:00.000-07:00

Using just=dec for alignment of decimals

Compiled by Prajitha Nair

We have a column in proc report with either 1 or 2 digits right of the decimal and an uncertain number of digits to the left. For enhanced output, the values have to be presented such that they are aligned with respect to the decimal point.

When the display value contains a decimal point, we can use just=dec to align the numbers directly. The JUST=DEC option can be used to align the decimal points in the values in a column

define colname / display "Column/header" style=[just=dec];

where colname is the name of the column name as specified in the SAS.

If we are using ods rtf tags then we can use the pretext option for the purpose

define colname /display “Column Header”

style(column)={pretext="\qj\tqdec\tx1200" protectspecialchars=off just=center};

2008-04-15T23:11:00.000-07:00

Extracting Engine and Path name of the code
Compiled by Prajitha Nair

The input parameter in the macro will be the name of the SAS file whose path is to be determined.

%macro PathbyName(progName);

%global fullPath fullPath1 engine;
%if %index(%upcase(&progName),.SAS) eq 0 %then
%let progName=&progName..sas;

proc sql noprint;
select xpath into :fullPath
from dictionary.extfiles where
index(upcase(xpath),"%upcase(&progName) " ) gt 0 ;
select setting into :engine from sashelp.voption
where optname="ENGINE";
quit;

%let engine = %trim(&engine);
%put engine = &engine;
%let fullpath = %trim(&fullPath);

%put fullpath = &fullPath;

%mend PathbyName;

2008-04-15T22:55:00.000-07:00

Accessing the current working directory where the file containing the SAS code is stored

Compiled by Prajitha Nair

Let the SAS editor containing the code be KR-PH-XXX-SAS-Init.sas and it is stored in a folder named SAS Programs_Final.

The following %let statements assigns the folder and editor names to macro variables pgmfld and pgm respectively.

%let pgmfld = SAS Programs_Final; /*Folder in which SAS code is stored*/
%let pgm= KR-PH-XXX-SAS-Init.sas; /*Name of the program editor*/

The following macro is then used to extract the path of the editor from sashelp.vextfl and determine the path of the folder as “dir1” and of the editor as “dir2”.

%macro filePath;
%global fpath maxRef;

proc sql noprint;
select xpath into :fPath
from sashelp.vextfl where xpath ? "&pgm";
quit;

%let fpath = %trim(&fpath);
%put &fpath;
%global dir1 dir2 pgm1 pgmfld1;
%let pgm1 =%trim(&pgm);
%let pgmfld1= %trim(&pgmfld);

data _null_;
x=length("&fpath")-length("&pgm1");
y=length("&fpath")-length("&pgm1")-length("&pgmfld1")-1;
call symput("dir2" ,trim(substr("&fpath",1,x)));
call symput("dir1" ,trim(substr("&fpath",1,y)));
run;

%mend filePath;

This macro helps in determining the path of the code and enables the code to be executed in any computer provided the SAS code is saved within a folder and the naming conventions are followed as above.

2008-03-14T04:10:00.000-07:00

Hiring

2008-02-15T05:27:00.000-08:00

New Abode

Finally after three years of exemplary hard work of all the present & past employees of KREARA, our dream of a beautiful new office came to frution on January 27th 2008. Thanks to all our clients and employees who have helped us make this dream come true

2007-11-23T03:41:00.000-08:00

Randomisation - Data sets

Compiled by Prajitha Nair
Here is a piece of code that will generate mock randomisation list that the programmers could use to generate the outputs before unblinding the data

/*Creating the dummy dataset for randomisation*/

Proc format;
value treat 1='Test'
2='Reference'
3='Placebo';
run;

/*Randomly assigning medical kit number to treatments*/
proc plan seed=111605;
factors medkit_no=220 random block=1 random/noprint;
output out=first;
treatments treat=3 cyclic (1 2 3 );
run;

proc sort data=first out=rand_trt;
by medkit_no;
run;

data rand_trt(keep=medkitno treat);
set rand_trt;
medkitno=put(medkit_no, z3.);
format treat treat.;
run;

/*merge to get the randomised patient included in the study*/
proc sort data=rand_trt;
by medkitno;
run;

proc sort data=medkit_alloc;/*sas dataset imported from mysql*/
by medkitno;
run;

data formo.randl;
merge rand_trt(in=a) medkit_alloc(in=b);
by medkitno;
run;

2007-10-11T04:05:00.001-07:00

Read only access to SAS Data sets
Compiled by Soumya Gopinath

Lock the entire SAS data library by using the option Access=Readonly.

Libname libref path access= Readonly;

2007-10-11T04:00:00.000-07:00

Silly Proc Report !
Compiled by Soumya Gopinath

An annoying period (.) appeared in the p-value column when the break statement was applied in proc REPORT. How can we eliminate this period (.) from the report (rtf file)?

Solution:
Firstly, the data type of p-value variable is numeric then the break option will replace the missing values with a period. To avoid this situation change the data type of p-value variable to character. Then the missing values will be replaced by blank space only.
Eg:
/* Create dataset with 5 variables and 8 observations*/
data test;
input usubjid $ parameter $ visit $ trtgrp result;
datalines;
001 FEV1 VISIT1 1 2.34
002 FEV1 VISIT1 3 0.98
001 FEV1 VISIT4 1 2.04
002 FEV1 VISIT4 3 1.98
001 FVC VISIT1 1 2.34
002 FVC VISIT1 3 2.98
001 FVC VISIT4 1 2.44
002 FVC VISIT4 3 1.99
;
run;
/* Carrying out ANOVA*/
ods output ModelAnova= test1;
proc glm data=test;
by parameter visit;
class trtgrp;
model result=trtgrp/ss3;
lsmeans trtgrp/adjust=t pdiff;
run;

data test2;
set test1;
test=' '; /* dummy variable*/
keep parameter visit probf Test;
run;

/* Specify the output location*/

ods rtf file="D:\soumya\test.rtf" style=styles.listingstyle;

proc report data = test2 nowd spacing = 2 headline headskip split = '*' missing;
column parameter visit test,(probf);
define parameter / group order=data left 'Parameter' ;
define visit / display left 'Timepoint' ;
define Test / across center "Test" ;
define probf/ display left "p-value";
break after parameter/summarize suppress;
run;

ods _all_ close; /* Closing all ODS outputs statements*/

In the above example probf is a numeric variable within the across variable ‘test’. So in the output a period occurred when the break statement active. Eliminate this we add one more statement in the dataset Test2.
probf1=put (probf, pvalue6.); /* for converting numeric type to character*/

Generally we can say that the numeric variables within the across variable in REPORT procedure should make a period in the blank space and to avoid this convert numeric variables to character by using PUT function.