Summary
In this chapter, we learned what predictive biostatistics is and why we need it in different areas of life science. We also learned about the dependent and independent variables and their relation to confounders and latent variables. We performed linear regression for biostatistics in Python and used it to create the predictive model for predicting the HbA1c in different subjects based on their anthropometric and biochemical parameters.
We learned how to create logistic regression models used to predict whether subjects have T2DM based on their anthropometric and biochemical parameters related to obesity and biomarkers such as HbA1c.
We learned how to include multiple anthropometric and biochemical parameters in a single model and use them to predict HbA1c and T2DM presence using multivariate models. Using these models, we learned how predictive modeling works in biostatistics and how to apply it to a real-world diabetes dataset.
In the next chapter, we will learn...
