Closed kmdesorcy closed 10 months ago
Hi @kmdesorcy -- can you show us the output of model.matrix(~rn, data = gut.r.week1)
? That should be able to tell us how the mean and dispersion models are being specified and if overparametrization is your problem.
Closing bc no follow-up received
Hello,
I'm trying to use corncob to test the differential abundance of all taxa in my samples across a categorical variable with 2 levels. I have ~70 samples. I'm getting an error message that the model is failing to converge. The error message states that the model is overspecified but I'm not sure I understand if I have only 1 categorical variable with 2 levels and a high # of samples. Any help would be very much appreciated.
cctest <- differentialTest(formula = ~ rn, phi.formula = ~ rn, formula_null = ~ 1, phi.formula_null = ~ rn, test = "Wald", boot = FALSE, data = gut.r.week1, fdr_cutoff = 0.05)
Error in differentialTest(formula = ~rn, phi.formula = ~rn, : All models failed to converge!