Multivariate dynamic linear models for estimating the effect of experimental interventions in an evolutionary...

Area of Science:

• Dairy Science
• Agricultural Engineering
• Statistical Modeling

Background:

• Evolutionary operations optimize production by analyzing small changes in process variables.
• Assessing intervention effects on milk production requires robust analytical tools.
• Dynamic linear models (DLMs) offer a flexible framework for analyzing time-series data in animal agriculture.

Purpose of the Study:

• To construct a tool for assessing intervention effects on milk production within an evolutionary operations framework.
• To apply a dynamic linear model (DLM) with Kalman filtering for this assessment.
• To evaluate the model's utility in commercial dairy herds with different experimental designs.

Main Methods:

• Developed a dynamic linear model (DLM) incorporating parameters for milk yield, individual cows, and intervention effects.
• Utilized Kalman filtering for parameter estimation and intervention effect assessment.
• Applied the model to data from two commercial Danish dairy herds with distinct experimental setups (control/treatment and pretest/posttest).

Main Results:

• The DLM successfully estimated intervention effects in both herds.
• Reducing concentrate in Herd 1 (AMS) showed no negative impact on milk yield.
• Increasing energy in Herd 2 (total mixed ration) positively affected milk yield, but only for the first intervention.

Conclusions:

• The developed DLM is a flexible and dynamic tool for systematic experimentation in dairy herds.
• The model can serve as a decision support system for on-farm process optimization.
• Evolutionary operations, when analyzed with appropriate models, can identify efficient production strategies.