quantitating bimodality

From: Calman Prussin (CPRUSSIN@niaid.nih.gov)
Date: Thu Sep 06 2001 - 10:44:01 EST


Has anyone come up with a good means to quantitate bimodality? We are
examining expression of a protein by basophils and certain donors
demonstrate bimodal expression whereas most are clearly unimodal or very
questionably bimodal. The distribution (unimodal or bimodal) has important
implications for our conclusions.

The only scheme I have come up with is to have several investigators score
blinded samples (unimodal, questionably bimodal, clearly bimodal). A CV may
yield more objective data but seems lacking.

Any ideas would be appreciated.

Calman



This archive was generated by hypermail 2b29 : Sun Jan 05 2003 - 19:01:30 EST