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 Similar articles in PubMed Alert me to new issues of the journal Download to citation manager Citing Articles Citing Articles via Google Scholar Google Scholar Articles by Morrison, D. G. Articles by Godke, R. A. Search for Related Content PubMed PubMed Citation Articles by Morrison, D. G. Articles by Godke, R. A.

Discriminant Analysis for Predicting Dystocia in Beef Cattle. I. Comparison with Regression Analysis¹

Louisiana Agricultural Experiment Station, Louisiana State University Agricultural Center, Baton Rouge 70803

Abstract

Data from 131 calvings of Chianina crossbred cows (2 to 5 yr old) bred to Chianina bulls were used to compare stepwise multiple regression analysis (RA) and stepwise, two-group discriminant analysis (DA) for predicting dystocia. Variables (21) studied in relation to dystocia included both prebreeding and precalving cow and calf effects. Calving was categorized as either unassisted or assisted without regard to the severity of dystocia. During this study, 30 (22.9%) assisted births occurred. All variables were standardized to a mean of zero and a variance of one before statistical analyses. Models were developed based on precalving variables and with both precalving and post-calving variables with both RA and DA. Average discriminant scores (centroids) were different (P<.01) between assisted and unassisted cows. Significant precalving DA variables were cow age and precalving pelvic height. This model correctly predicted 26 of 30 (86.7%) of the occurrences of dystocia. Significant precalving RA variables were prebreeding pelvic width and precalving pelvic height. The amount of variation accounted for by these two factors was 31.5%. Calf birth weight, calf chest depth, calf height, precalving pelvic area, cow age and precalving cow weight were selected by DA for use in the combined precalving and postcalving prediction model. Calf birth weight was 58% more important than either pelvic size or cow age. Percentage correctly classified with this model was 87.4. Significant postcalving variables selected by RA in order of importance were prebreeding pelvic width, calf birth weight and calf shoulder width (R² = .399). Because the same data used to identify the important variables in relation to dystocia were also used to test their prediction accuracy by DA, the predictive value of the models has not been tested using a hold-out sample of these data. Thus, results are likely biased upward. However, use of DA was a more appropriate statistical procedure than RA for predicting dystocia because distinct group classification of the dependent variable was accomplished.

¹ Published with the approval of the Director of the Louisiana Agr. Exp. Sta.

² Present address: Rosepine Research Station, Rosepine, LA 70659.

³ Dept. of Anim. Sci.

⁴ Former Associate Professor, Dept. of Exp. Statist.; present address: Dept. of Comp. Info. Sys., Southwestern Missouri State Univ., Springfield, MO 65804.