• ## LR03: Residuals and RMSE

This is post #3 on the subject of linear regression, using R for computational demonstrations and examples. We cover here residuals (or prediction errors) and the RMSE of the prediction line. The first post in the series is LR01: Correlation.

• ## Workarounds to include R stat functions in data science pipelines

This post explores some of the possible workarounds that can be employed if you want to include non-pipe-aware functions to `magrittr` pipelines without using `intubate` and, at the end, the `intubate` alternative. See intubate <||> R stat functions in data science pipelines for an introduction.

• ## LR02: SD line, GoA, Regression

This posts continues the discussion of correlation started on LR01: Correlation. We will try to answer the following questions: Should correlation be used for any pair of data? Does association mean causation? What are ecological correlations? What happens with the scatter diagram when we change the standard deviations of x and y? What is the SD line? What is the Graph of averages? What is the Regression line. What is the Regression function?

• ## intubate <||> R stat functions in data science pipelines

The aim of `intubate` (logo `<||>`) is to offer a painless way to add R functions that are non-pipe-aware to data science pipelines implemented by `magrittr` with the operator `%>%`, without having to rely on workarounds of varying complexity.

• ## LR01: Correlation

This is the first of a series of posts on the subject of linear regression, using R for computational demonstrations and examples. I hope you find it useful, but I am aware it may contains typos and conceptual errors (mostly when I try to think instead of just repeating what others thought…). Help on correcting/improving these notes is appreciated. This first post deals with the subject of correlation.

Roberto Bertolusso