04-01-2018 02:12 PM
The purpose of our study is to compare our results for the dietary diversity for women during 2 seasons: spring and summer.
We want to check if our confounding variables for women’s dietary diversity interact during the 2 seasons.
We used the following proc logistic to answer our question (I’m using SAS Enterprise Guide 6.1):
proc logistic data=results2 ;
class region (param=ref ref='1-Sud')
v_urban_rural (param=ref ref='rural')
model Dietary_diversity (event='Yes')= season region v_urban_rural region*season v_urban_rural*season ;
format season saison.;
The code gave us the p-value for one group of the variable example: p-value for urban but it didn’t give us the p-value for rural !!! though we want to check the differences between the 2 seasons for all groups and not compare urban-rural between the 2 periods. So how can I ask for such information!!??
04-01-2018 02:23 PM
The way SAS parameterized categorical (also called CLASS) factors, you do not want to interpret the regression coefficients to answer the question you have asked.
You want to use the LSMEANS statement, along with the LINES options to determine which levels of the categorical variables are different. This will provide clear answers to the question you have asked.