mean0 and mean1 in the ESTIMATE statements are functions of mu0 and mu1 which you have defined as functions of both parameters and data variables. Hence the error. ... View more

Yes, of course you are losing information by merging levels, but without doing so you get no model and no information. So, it's a tradeoff to merge some categories so that you can get a possibly useful model. There, of course, could be other approaches using different tradeoffs and you can decide which one is most useful. One attractive alternative is if you just want the test the association of each of the predictors with the response controlling for the other predictors. That can be done using the original data (no need to merge categories) by avoiding modeling altogether and instead use the CMH test in PROC FREQ. The General Association statistic tests the adjusted association of each predictor. proc freq; table harvest*weeks*variety*color/ noprint cmh; table harvest*variety*weeks*color/ noprint cmh; table variety*weeks*harvest*color/ noprint cmh; run; This is an example of using both EQUALSLOPES and UNEQUALSLOPES options to test the equal slopes assumption for Harvest in the submodel with Harvest and Variety on the data with merged categories. Since Harvest has two levels, it has one parameter on each of the two logits that are modeled. The EQUALSLOPES option with UNEQUALSLOPES=HARVEST estimates the parameter on one logit and the difference between that parameter and the parameter on the other logit (labeled with prefix U_). proc logistic data=one; class harvest variety / param=glm; model y=harvest variety / link=glogit equalslopes unequalslopes=harvest; run; If the test of that difference parameter is not significant, then you might conclude that the parameters are the same. By removing the UNEQUALSLOPES option, you then get just the estimated common slope for Harvest (and for Variety). That is the model with only the EQUALSLOPES option that I showed earlier. ... View more

Yes, you only need to include k-1 dummies for a categorical variable with k levels. In my example, FEM is a single dummy variable representing gender that equals 1 if female, 0 otherwise. The mu1 and mu0 expressions would need to include only parameter names and not any variable names from the data set like in my example. ... View more

Then you are not using the data that you attached in your first post. With those data, there are no warnings with the code you show. In the data you attached, there are 8 distinct response levels, and fitting the full model on all those levels with that small amount of data is not remotely feasible. So, you have to consider what you CAN do. If you combine the response levels down to three levels as done by the DATA step I gave, then you can fit the main effects model and you can even treat WEEK as categorical if you want. And the results show that WEEK is not significant, VARIETY is significant, and HARVEST is marginally significant. If you are willing to drop WEEK from the model, then you can fit the model with VARIETY and HARVEST and their interaction IF you assume that the multiple parameters on each of those model effects on the two logits are same... that is, that the two HARVEST parameters on the two logits are the same and similarly for VARIETY and the interaction. That can be done using the EQUALSLOPES option. (You can even test that equality assumption by also using the UNEQUALSLOPES= option in turn for each of the model effects which seems to show that the assumption is reasonable to the extent that the data can detect it). That model fits without error and shows that the HARVEST*VARIETY interaction is also not significant. So, if you again accept that it has no effect and drop it from the model, that leaves a model with just the HARVEST and VARIETY main effects. (You can play the same game of checking the equal parameters assumption for both effects in that model, and again the assumption seems reasonable). The equal slopes model on just HARVEST and VARIETY as done below again indicates that VARIETY is significant and HARVEST is marginally significant.  proc logistic data=one; class harvest variety / param=glm; model y=harvest variety / link=glogit equalslopes; run; ... View more

In the example I showed, you can see that the ESTIMATE statements depend only on the model parameters, b0, b1, b2, and k. The PREDICT statement allows the quantity specified in that statement to contain data values. So, the PREDICT statement that I showed uses the data values in each observation to estimate the "mean" expression which depends on the data values of MENT and FEM as well as the model parameters. ... View more

The data you show actually has 8 response levels and if you try to fit the 3 factor model with all factors categorical and include all the interactions, the number of parameters to be estimated is very large and is way, way more than can be supported by the data. That model makes the data far too sparse and PROC LOGISTIC will report "separation" in a log note indicating that the model cannot properly converge because some parameters are infinite. Yes, you can always treat a predictor as categorical, but for a variable that has a small number of meaningful numeric values, you could also treat it as continuous. Doing so results in only one parameter to be estimated (per logit) rather than several. But doing that alone is not nearly enough to avoid the sparseness and nonconvergence. If you reduce the response down to 3 levels and fit only the main effects model, then that model can be properly fit. For example,  data one; set one; y=int(peelcolor); if y=5 then y=4; run; proc logistic data=one; class harvest variety/param=glm; model y=harvest variety weeks / link=glogit; run; ... View more

PROC CATMOD is not the best procedure to use, and in any case, the Mean response is not the proper response function to model a nominal, multinomial response. Use a more modern procedure such as PROC LOGISTIC with the LINK=GLOGIT option in the MODEL statement. A WEIGHT statement is not needed. An example is the one titled "Nominal Response Data: Generalized Logits Model" in the Examples section of the LOGISTIC documentation. For your case, the following statements will attempt fit the appropriate generalized logit model and provide a table of Type3 tests of the model effects. The following code assumes that your WEEKS variable is actually a continuous variable while HARVEST and VARIETY are categorical. Note that with a six-level response, five independent generalized logits are modeled simultaneously so you will see five intercepts and five times the number of other parameters and degrees of freedom  as you might normally expect with a continuous or binary response. Because of the large number of parameters in this model, your data might be too sparse to avoid model fitting problems as a result of some parameters being infinite. proc logistic data=one; class harvest variety / param=glm; model PeelColor=harvest|variety|weeks / link=glogit; run; ... View more

Just add a PREDICT statement to get predicted values in the OUT= data set for each of the observations in the input data set.    predict mean out=preds; If you have one or more particular settings of the predictor(s) that you want a predicted value for, you can use one (or more) ESTIMATE statements. For example, to get the predicted mean for MENT=30 in the ZTNB example using the Long data in the second half of the note I referred to earlier: estimate 'pred for ment=30' exp(b0+b1*30);   ... View more

See this note that shows how to fit the zero truncated Poisson and negative binomial models using PROC FMM and PROC NLMIXED. As shown there, it's easiest to do with FMM. ... View more

As stated in the J-T test documentation, you will want to order the rows of your table (levels of RACE) to correspond with the way you  hypothesize the ordinal response (BMIGRP) to increase. For example, if you hypothesize that BMIGRP increases from white to black to other then you want the rows to be in that order. If it is a character variable, you might find it easiest to either recode it or create a new variable with  values 1, 2, 3 in the desired order. Of course, you should make sure that the response levels (BMIGRP) are arranged in increasing order across the columns (<30, 30-40, >40). Assuming that the data agree with that hypothesis, then the one-sided p-value tests the significance of that positive trend. ... View more

See the Details section on the JT test in the PROC FREQ documentation. As stated there, "The Jonckheere-Terpstra test is appropriate for a two-way table in which an ordinal column variable represents the response. The row variable, which can be nominal or ordinal". ... View more

It sounds like you probably want to use the Jonckeere-Terspstra test in PROC FREQ. Use the JT option in the TABLES statement for your two-way table. ... View more

See the documentation of the LSMESTIMATE statement. They are the values that correspond to the ordered list of LSMEANS values and which, in your case, select the LS-mean you want to estimate. It might be clearer if you add the E option in the LSMESTIMATE statements and look at the table it presents.   But if you have the numerators and denominators of the rates, as you indicated, then you would use the first analysis that I showed and not the one using LSMESTIMATE statements. ... View more