[R] Non-linear Weibull model for aggregated parasite data

[Dan E.]

Hi,

I am trying to fit a non-linear model for a parasite dataset.  Initially, I
tried log-transforming the data and conducting a 2-way ANCOVA, and found
that the equal variance of populations and normality assumptions were
violated.  Gaba et al. (2005) suggests that the Weibull Distribution is best
for highly aggregated parasite distributions, and performs better (lower
type 1 and 2 error rates) than models using normal (with log-transformed
data) and negative binomial error structure.  I have looked at the R help
site and had no success in conducting the analysis, so I had no choice but
to turn to the R masters.  The dependent variable is coccidiaopg (a fecal
egg count) and the independent variables are age (continuous), year
(continous), sex (2 level factor), and season (2 level factor).  The
variable sex is a nested factor in season due to the fact that different
individuals were sampled during the different seasons.  I may need to talk
with a local statistician, but if it is simple for someone to help with the
code to execute this analysis in R, I would be very greatful.  Also, I am
unsure how to estimate the starting parameters for shape and scale.

Thank you.

Best,
Daniel Eacker
-- 
View this message in context: http://n4.nabble.com/Non-linear-Weibull-model-for-aggregated-parasite-data-tp962780p962780.html
Sent from the R help mailing list archive at Nabble.com.