Without seeing the model I'm not clear on the cause. In general it is not
very useful to compute 1 d.f. tests for parameters that represent only part
of a meaningful hypothesis.
Note that anova.lrm computes Wald statistics, which are subject to the
Hauck-Donner effect (which may not be the cause
Greg Snow imail.org> writes:
> The individual tests on coefficients in logistic regression
> are generally based on a Wald test statistic.
> Unfortunately there is a bit of a paradox possible in this
> case where the coefficient is highly
> significant, but due to a flattening of the likelihoo
The individual tests on coefficients in logistic regression are generally based
on a Wald test statistic. Unfortunately there is a bit of a paradox possible
in this case where the coefficient is highly significant, but due to a
flattening of the likelihood the standard error is overestimated an
3 matches
Mail list logo
