Hi i want to compare the proportion of males between two groups.
first, am I correct in thinking a chi-square is appropriate?
second, how would I compare group by only one level of gender and not by both levels?
thanks for any help!
PROC FREQ DATA=_____;
TITLE3 'Chi-Square Test';
TABLES group*gender/CHISQ;
RUN;
A Chi-square test is appropriate if there are enough cases in every table bin. Otherwise, you might consider using an exact Fisher test.
What is there to compare statistically between males and females in a single group?
/* Extract a few observations at random from SASHELP.HEART dataset */
data heart;
call streaminit(78967896);
set sashelp.heart;
if rand("uniform") < 0.05;
run;
/* Compare the live/death status between males and females,
using two tests */
proc freq data=heart;
tables sex*status;
exact Fisher chisq / mc;
run;
PROC FREQ DATA=_____;
TITLE3 'Chi-Square Test';
TABLES group*gender/CHISQ relrisk riskdiff;
RUN;
PROC FREQ DATA=_____; TITLE3 'Chi-Square Test males'; where gender='Male'; TABLES group/CHISQ; RUN;
could be one way. Of course without data I do not know your exact values of gender...
Available on demand!
Missed SAS Innovate Las Vegas? Watch all the action for free! View the keynotes, general sessions and 22 breakouts on demand.
Learn how use the CAT functions in SAS to join values from multiple variables into a single value.
Find more tutorials on the SAS Users YouTube channel.