R help - Feb 2011 - Lmer binomial distribution x HLM Bernoulli distribution

Dear R-users,

I'm running a lmer model using the lme4 package. My dependent variable is
dichotomous and I'm using the "binomial" family. The results
are slightly different from the HLM results based on a Bernoulli
distribution. I read that a Bernoulli distribution is an extension of a
binomial distribution. Is that right? If so, how can I adapt my R model to a
Bernoulli distribution so that my R results are the same as my HLM results?

Thank you so much,

Luana Marotta

	[[alternative HTML version deleted]]

On Tue, Feb 1, 2011 at 10:51 AM, Luana Marotta <lucsmarotta at gmail.com>
wrote:
> Dear R-users,
> I'm running a lmer model using the lme4 package. My dependent variable
is
> dichotomous and I'm using the "binomial" family. The results
> are slightly different from the HLM results based on a Bernoulli
> distribution. I read that a Bernoulli distribution is an extension of a
> binomial distribution. Is that right? If so, how can I adapt my R model to
a
> Bernoulli distribution so that my R results are the same as my HLM results?
Actually it's the other way around.  A binomial(n, p) random variable
is the sum of n independent Bernoulli(p) random variables.
Alternatively, you could describe the Bernoulli(p) distribution as a
special case of the binomial, the binomial(1, p) distribution.

It is generally more productive to ask questions regarding lme4 and
lmer on the R-SIG-Mixed-Models at R-project.org mailing list.  It would
help if you could make the data and the output of your model fits
available so we can check on different systems.