www.cmm.bristol.ac.uk/forum

I am at a new computer and it seems like I am unable to install R2MLwiN.

Tried it 3 ways:

install.packages("R2MLwiN")
Warning in install.packages :
package ‘R2MLwiN’ is not available (for R version 3.5.2)

> install.packages("R2MLwiN", repos = "http://cran.r-project.org")
Warning in install ...

thanks, worked like a charm!

Hi Chris,

Could you perhaps indicate how to do that?
Isn't there a problem in the output as well, given that the estimates for the constant are also odd?

Gerine

I did that, and it seems the problem may lie in the variance of the intercept at level 1?

> RL1$resmatrix
M N Nmin I
deviance 25 30105 3746 8.04
FP_Intercept 12 12718 3746 3.40
FP_predictor 18 19852 3746 5.30
RP3_var_Intercept 126 156618 3746 41.80
RP2_var_Intercept 120 111108 3746 29.70
RP1_var ...

I get the following error when I try to run the sixway function:


Error in if (RL1$resmatrix[1] == "Error") { :
missing value where TRUE/FALSE needed
In addition: Warning message:
In par(new = TRUE) : calling par(new=TRUE) with no plot

It doesn't occur when I run the analyses with 100 ...

thanks, that worked!

I don't need the information currently provided (Adapting for xxx iterations; burning in for x of y; actual update x of y) etc.
How do I turn this off? I don't see an option under ?runMLwiN

I noticed that in some formulas, there is an I before a new term, for instance:

(mymodel11 <- runMLwiN(logit(a_point, cons, 6) ~ 1 + gcseavnormal[1:5] + gender[1:5] + I(gcseavnormal^2)[1:5] + (1[1:5] | school),
D = "Ordered Multinomial", estoptions = list(nonlinear = c(N = 1, M = 2)), data ...

Thanks!! Thought the 5 was for "N categories", so good to know!

Could you indicate where in the function of 11.4 the reference category is specified?

I have tried replacing: With: But that doesn't work.