Displaying 1 result from an estimated 1 matches for "longhit".
2005 Feb 20
1
logistic regression and 3PL model
...ot;)
cat("\nConvergence message:", fit$message, "\n")
invisible(fit)
}
I have been using "lower=.25" in the call for logitreg:
options(contrasts = c("contr.treatment", "contr.poly"))
X <- model.matrix(longhit ~ age*gender, data=data)[,-1]
logitreg(X, data$longhit, lower =.25)
However, this is giving me .25 as the value for intercepts and all the
regression weights. Am I correcting for the guessing base rate correctly?
Any suggestions or pointers would be greatly appreciated. Thank you in
advance....