|
|
Bootstrap in twins GxE model |
|
Message/Author |
|
|
Hi, I use the "model contraint" command to model a GxE interaction in a AE model. I request bootstrap S.E. and confidence interval with 1000 replication. But all the S.E. are equal 0. What is the problem ? Thanks Alain Girard University of Montreal |
|
|
Please send your input, data, output, and license number to support@statmodel.com. I don't see a reason offhand that this would happen. |
|
|
Hello, I am running a GxE model with two dichotomous moderators, one is a grouping variable (m vs d), like this: new(ma mc me mt mu mv da dc de dt du dv); varm1=(ma+mt*sexodef)**2 + (mc+mu*sexodef)**2 + (me+mv*sexodef)**2 ; varm2=(ma+mt*sexjdef)**2 + (mc+mu*sexjdef)**2 + (me+mv*sexjdef)**2 ; mzmc=(ma+mt*sexodef)*(ma+mt*sexjdef) + (mc+mu*sexodef)*(mc+mu*sexjdef); dzmc=0.5*(ma+mt*sexodef)*(ma+mt*sexjdef) + (mc+mu*sexodef)*(mc+mu*sexjdef); (this syntax repeats for the second group with 'd' instead of 'm'). This model runs well. However, it appears that it is not possible to compare the ACE components between the groups (so: ma=da, mc=dc, me=de). Am I doing something wrong? Thanks. |
|
|
Please send the output and your license number to support@statmodel.com. |
|
Back to top |
|
|