[R-sig-ME] clogit error message

[NJ Robinson]

Dear all,

I am trying to perform conditional logistic regression using 'clogit'.
However when I run the model I get the following error message:

Warning message:
In fitter(X, Y, strats, offset, init, control, weights = weights,  :
  Ran out of iterations and did not converge

Could someone shed some light on what this message means?

The sample size of my data is 30 (comprising 15 pairs grouped by "site").
My sample data is composed of a binary response ("response") and 3
predictor variables all of which are factors ("x1","x2","x3").

The following command was used to construct the model;

>clogit(response~x1+x2+x3+strata(site))

based on the example of my data structure seen below,

site  response            x1              x2              x3
1        0                GroupA        GroupA        GroupA
1        1                GroupB        GroupB        GroupE
2        0                GroupA        GroupA        GroupB
2        1                GroupA        GroupA        GroupC
3        0                GroupB        GroupB        GroupD
3        1                GroupA        GroupA        GroupA

Have i used the correct syntax in order to run the model correctly for my
data structure?

Any help would be greatly appreciated.

Thanks

Nathan



--