Attachment | Size |
---|---|

code.txt | 13.86 KB |

Hello, I want to run a G*E model (2 binary variables ) using the script from “JuanJMV”(https://openmx.ssri.psu.edu/node/4324). Unfortunately, there seems to be some errors in my model

I just met the following Warning message when I add one of the Constraint lines

Warning message:

In mxTryHard(model = model, greenOK = greenOK, checkHess = checkHess, :

The model does not satisfy the first-order optimality conditions to the required accuracy, and no improved point for the merit function could be found during the final linesearch (Mx status RED)

Constraint on variance of Binary variables

matUnv <- mxMatrix( type="Unit", nrow=nvo, ncol=1, name="Unv1" )

var_constraint <- mxConstraint( expression=diag2vec(V0)==Unv1, name="Var1" )

or

matUnv <- mxMatrix( type="Unit", nrow=nvo, ncol=1, name="Unv1" )

var_constraint <- mxConstraint(expression=rbind(V0[2,2],V0[1,1]) == Unv1, name="Var1")

Another errors occurred when I remove the Constraint lines and define covE as:

myVarE <- mxMatrix( type="Symm",nrow=nv, ncol=nv, free=c(F,T,F), values=c(1, 0.1, 1),

labels=c("e_1_1", "e_2_1", "e_2_2"), lbound=c(0.0001,rep(NA,2)),name="E0")

** Information matrix is not positive definite (not at a candidate optimum).

Be suspicious of these results. At minimum, do not trust the standard errors.

Any suggestions from you?

Thanks!