HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS		QUICK SEARCH:   [advanced] Author: Keyword(s): Year:  Vol:  Page:

This Article Full Text (PDF) Alert me when this article is cited Alert me if a correction is posted Services Similar articles in this journal Alert me to new issues of the journal Download to citation manager Citing Articles Citing Articles via Google Scholar Google Scholar Articles by Koch, G. G. Articles by Sen, P. K. Search for Related Content PubMed Articles by Koch, G. G. Articles by Sen, P. K.

Statistical Methods for Evaluation of Mastitis Treatment Data

Department of Biostatistics, University of North Carolina, Chapel Hill 27514

ABSTRACT

Categorical data on the response to treatment for mastitis are analyzed by several methods. The most important aspect of these analyses is the emphasis that the cow rather than a quarter of the udder is the basic experimental unit. Thus, the untenable assumption of independence among the quarters of an udder is not required. Given this framework, examples show that many questions can be investigated by weighted regression analysis. In particular, methodological strategies are outlined for 1) assessing the extent of interaction among experimental factors and its implications to model fitting for describing relationships, 2) accounting for pretreatment scores as a covariable, and 3) undertaking multivariate analyses with respect to the four quarters simultaneously.

The conclusion from these analyses is that the various active treatments under study are homogeneous and superior to no treatment. Cows on any of the active treatments completed the trial with approximately one less quarter being infected than when the study began. In particular, the decline in the average number of infected quarters was from 1.8 to .8.