Abstract

An overview is given of the primary basis for the scientific inference that somidobove sustained release injection is safe for multiparous dairy cows. The process of analysis and interpretation of the voluminous data collected from a target animal safety study which started with 28 cows and lasted two lactations is described. This was a repeated measures study with most of 60 variables being measured or summarized every 28 days resulting in approximately 1500 measurements per cow. The statistical analysis was designed to screen the variables for biological change caused by treatment and consisted of a univariate analysis of variance for repeated measures data both within a lactation and across two lactations. Graphs of least squares means with error bounds and p-value plots of ANOVA p-values helped communicate statistical findings. A cross disciplinary approach interpreted analyses and arrived at inferences.

Keywords

repeated measures, p-value plots

Creative Commons License

Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.

Download

Share

COinS
 
Apr 30th, 9:30 AM

ANALYSIS OF A TWO LACTATION TARGET ANIMAL SAFETY STUDY OF SOMIDOBOVE SUSTAINED RELEASE INJECTION IN MULTIPAROUS DAIRY COWS

An overview is given of the primary basis for the scientific inference that somidobove sustained release injection is safe for multiparous dairy cows. The process of analysis and interpretation of the voluminous data collected from a target animal safety study which started with 28 cows and lasted two lactations is described. This was a repeated measures study with most of 60 variables being measured or summarized every 28 days resulting in approximately 1500 measurements per cow. The statistical analysis was designed to screen the variables for biological change caused by treatment and consisted of a univariate analysis of variance for repeated measures data both within a lactation and across two lactations. Graphs of least squares means with error bounds and p-value plots of ANOVA p-values helped communicate statistical findings. A cross disciplinary approach interpreted analyses and arrived at inferences.