[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index][Subject Index][Author Index]

Re: dinodimorphism

At 5:56 PM +0930 12/21/01, Adam Britton wrote: 
<SNIP>based upon discriminant analyses of large, known datasets
from wild animals. When you're dealing with a few scant fossil remains, the
problem is trying to determine which characteristics - if any - are
dimorphic, and which range belongs to which sex.<SNIP>

Adam Britton 

Indeed.

It requires 300 specimens for a statistically meaningful analysis. Beyond that, you generally increase the number of rare or teratological species.

Ask any foraminifera researcher - of which, I started as - And to which I was married for 9 years (a foraminferal Cenozoic micropaleontologist).

Less than 300 - well that's nice. You deal with the data set that you have and infer what you can, and do it (the inference) knowing that you didn't have 300 or more to mathematically begin with. You just don't always have 300 specimens from any stratigraphic horizon and sample - especially as you get "larger."

More specimens than that (300) - what you get is an increase in information about the unusual. It's all about data in the long run.

Ciao, Happy Holidays, and Cheerio,
Marilyn W.