topic Re: Sas create table in SAS Enterprise Guide

Sas create table

PICKME — Mon, 15 Aug 2016 14:02:28 GMT

SAS Enterprise Guide 7.11

Hi, I have questions.

1. I want to create a table which I want to create. but i don't know how to do. PLZ let me know 😞

original dataset :

ID A1 A2 A3 ... A91 An : disease name

-------------------------------------

1 1 1 1 0 1:disease o

2 0 1 0 1 0:disease x

910000 1 0 1 0

TABLE which i want to create :

disease1 disease2 count phi coefficient

-----------------------------------------------------------

A1 A2 30 0.012

A1 A3 20 0.033

A1 A91 100 0.223

A2 A3 40 0.111

A2 A91 200 0.333

A90 A91 100 0.445

2. I've already tried these proc steps.

proc table;

table A1*(A2-A91);

output out=a / chisq;

run;

but i don't know next steps.

and i know i have to use 'proc tamplate step' but i don't know how to do. plz help me.

Re: Sas create table

RW9 — Mon, 15 Aug 2016 14:25:56 GMT

Hi,

I think in your code you meant to say:

proc freq data=<dataset>;
  tables A1*(A2-A91);
  output out=a / chisq;
run;

Or something similar to that. On a secondary note, proc template is used to create templates, be them style templates, graph templates or table templates. You do not *need* to use them at all, although they are helpful to get output to look a certain way.

Next up I would suggest you post test data as a datastep, follow this post:

https://communities.sas.com/t5/SAS-Communities-Library/How-to-create-a-data-step-version-of-your-data-AKA-generate/ta-p/258712

So we can run code against it.

Re: Sas create table

Ksharp — Tue, 16 Aug 2016 03:25:06 GMT

How do you get that COUNT variable. I also notice you want PI coefficient.


data have;
input ID     A1  A2  A3  A4;
cards;
1             1    1    1    0     
2             0    1    0   1  
3             1    1    1   1  
4             0    0    1   0  
5             1    1    0   0  
6             1    0    1   1  
7             1    0    1   1  
8             0    0    0   0  
9             0    1    1   1  
11            1    1    1   0  
12            1    1    1   1  
13            1    0    1   0  
14            0    1    1   1  
15            1    1    0   0  
16            1    1    1   0  
17            0    1    1   1  
18            1    1    1   0  
;
run;

data temp;
 set have(drop=id);
 array x{*} A:;
 length vname1 vname2 $ 40;
 do i=1 to dim(x);
  vname1=vname(x{i});
  value1=x{i};
  do j=i+1 to dim(x);
   vname2=vname(x{j});
   value2=x{j};
   output;
  end;
 end;
keep vname1 vname2 value1 value2;
run;
proc sort data=temp;
 by vname1 vname2 value1 value2;
run;
proc freq data=temp noprint;
 tables vname1*vname2/out=temp1 list;
run;
proc freq data=temp noprint;
 by vname1 vname2 ;
 table value1*value2/chisq;
 output out=temp2 phi;
run;
data want;
 merge temp1 temp2;
 by vname1 vname2;
run;