How to get estimates for categorical variables in a Logistic regression - PROC Genmod

[sierranalani]

I'm computing a Logistic regression to get RRs. I have a combination of binary and categorical variables.  My output current gives me beta estimates for the binary variables accurately, however it gives me only one Beta estimate for the categorical variable and it seems as though it is treating them as binary variables. For my main categorical variable county designation it has three levels (Urban, Rural, Frontier). Here is my code:

PROC GENMOD DATA= Test DESCENDING;
	CLASS CntyDes (ref = 'Urban') / param = ref;
	MODEL UTD (event = 'Yes') = CntyDes / dist = bin link = log;
	ESTIMATE 'BetaFrontier' CntyDes 1 / exp;
	RUN;

Contrast Estimate ResultsLabel Mean Estimate Mean L'Beta Estimate StandardError Alpha L'Beta Chi-Square Pr > ChiSqConfidence Limits Confidence LimitsBetaFrontierExp(BetaFrontier)

0.6874	0.5099	0.9266	-0.3749	0.1524	0.05	-0.6735	-0.0762	6.05	0.0139
			0.6874	0.1047	0.05	0.5099	0.9266

The contrast estimate results give me the beta estimate of the Frontier designation but nothing for the Rural one. Is there a way to add the rural designation to the estimate statement or even just have the rural one come up in the Beta output instead of the Frontier one?

[PaigeMiller]

Your output is impossible to read as presented. Can you present the output in readable fashion? (screen capture is okay)

[sierranalani]

Updated with the output:

[PaigeMiller]

The MODEL statement should show that there are estimates for all levels of CNTYDES . Since you are getting a estimate for just Frontier, I am guessing that there is missing data in your data set for the other levels. Please check to make sure the other levels appear in your data set, and that UTD is not missing for each of the other levels. Also please check the log for ERRORs or WARNINGs about missing data.