Deriving the Predicted Residual Sum of Squares Statistic

Recently I was looking into measures to evaluate a regularized least squares model. One thing I would have liked was cross-validation to be able to compare different models. When researching possibilities, I discovered PRESS (Predicted Residual Sum of Squares Statistic). The main resources I used to study the subject are: [1] Adrien Bartoli: Maximizing the … Continue reading Deriving the Predicted Residual Sum of Squares Statistic

Statistical tests: One sample t-test in R

This is the second post about statistical testing. In the first one I explained the principal concept behind statistical tests. Parametric tests are, in contrast to non-parametric tests, statistical tests that make some kind of assumption about the data. In general parametric tests are used when we assume normality for the source population of our … Continue reading Statistical tests: One sample t-test in R

Statistical testing: An introduction

I am planning to write about parametric and non-parametric testing but since I know that many people have difficulties with the concept of hypothesis testing itself, I am going to give an introduction to the basic concepts first without immediately trying to frighten you. In general, a statistical test consists of four steps: Formulate the … Continue reading Statistical testing: An introduction