Data Analytics for Poultry and Swine Industries

How should we solve problems and make data-driven decisions?

The new edition of this course starts in July 19th. If you want to review the program, visit this link.

About this course

The swine and poultry industries generate enormous amount of information. This could be used to register historical series or as a data base to generate information to improve the results and plan future developments.

Analytical thinking sets the foundation for proper decision making. This process should consider the identification of the problem, the appropriate data collection, the statistical or analytical analysis, the interpretation and communication of the results, and the proper decision making.

The course uses practical examples from the industry and real data shared by some of the main integrations of the world. Utilizes JMP, R and Tableau software with poultry and swine examples. Opens the opportunity for customized data analytic projects. It is a blended course, with self-paced interactive modules and virtual sessions with NC State professors and experts invited from different companies. After completion and evaluation, the Course offers an Extension Certificate in Data Analytics for Poultry and Swine Industries.

The 7 chapters include:

Overview of analytics and potential benefits

A. Statistical thinking and problem solving I

- Identifying potential root causes
- Software for data visualization and analytics
- Practice, Data visualization and graphics I

B. Statistical thinking and problem solving II

- Compiling and Collecting Data
- Data preparation for analysis
- Exploratory data analysis

C. Decision making with data

- Estimation
- Hypothesis Testing for Continuous Data
- Sample Size and Power

D. Statistical process control and quality control

E. Correlation and regression to predict responses

- Statistical process, correlation and regression.

F. Experimentation for problem solving and innovation

- Design of experiments
- Designing experiments to test factors
- Screening experiment
- Response Surface Experiments (RSE)

G. Predictive Modeling

- Introduction of Predicting Modeling
- Multiple Linear Regression Model
- Non-Linear Models
- Logistic Regression
- Decision Trees
- Neural Networks
- Generalized Regression
- Model Comparison and Selection
- Text Mining
- Introduction to Machine Learning