2-Factor ANOVA using mean/std/n instead of lists?

Pandawaffle — Fri, 18 Dec 2015 21:23:13 GMT

I am trying to preform a 2-factor anova, IV's=pre & post treatment, patient1 & patient 2 DV=loudness. Some of the data I am using is archival from an excel file and does not contain the actual lists of data, only the mean, std, and n for each task. How do I enter these values and have SAS preform a 2-factor anova using them? I was able to find a method that allowed t-tests to be calculated in this way:

data Para;
input _stat_ $ value group $;
cards

;
n         93        a
mean      74.08      a
std       0.29     a
n         90         b
mean      73.53     b
std       0.71    b
;
proc ttest data=Para;
title 'Pre vs Post Para';
class group;
var value;
run;

I tried to replicate this input with proc glm, but it does not work. It instead reads the value column as one continuos set of data instead of the discrete mean, n, and std. Giving average values of e.g. (90+74.08+.29)/3 which it then compares.

data SASTest;
input _stat_ $ value group $ paitent $;
cards
;
n         93        pre    DS03
mean      74.08      pre    DS03
std       0.29     pre    DS03
n         90         post DS03
mean      73.53     post    DS03
std       0.71    post    DS03
n         93        pre    DS01
mean      68.58      pre    DS01
std       1.422     pre    DS01
n         90         post DS01
mean      70.80     post    DS01
std       0.8    post    DS01
;
proc glm data=SAStest;
      class group paitent;
      model value = group paitent group*paitent;
   run;

I know other Stats programs are capable of plugging and chugging the mean, std, and n for procedures like they are a TI-83 calculator formula, and I have to believe SAS is capable of it as well, but how do I code for this?

Re: 2-Factor ANOVA using mean/std/n instead of lists?

FreelanceReinh — Sat, 19 Dec 2015 14:13:40 GMT

Apparently, PROC GLM does not share PROC TTEST's feature to accept summary statistics as input data for certain analyses.

However, a bit of googling yields:

A thread from 2012 where a possible workaround -- disaggregating the data using a macro written by Michael Friendly -- and the caveats of doing so were discussed: https://communities.sas.com/t5/SAS-Statistical-Procedures/how-to-perform-t-test-or-anova-test/td-p/124831?start=0&tstart=0
A website providing a download link and explanations of the abovementioned macro: http://www.datavis.ca/sasmac/stat2dat.html
Conference papers on this topic with code and examples: from 1991, 2006 and 2014.

topic Re: 2-Factor ANOVA using mean/std/n instead of lists? in SAS Procedures

2-Factor ANOVA using mean/std/n instead of lists?

Re: 2-Factor ANOVA using mean/std/n instead of lists?