concept regression analysis in category R

appears as: regression alysis, regression alyses, regression analysis
R in Action, Second Edition: Data analysis and graphics with R

This is an excerpt from Manning's book R in Action, Second Edition: Data analysis and graphics with R.

In many ways, regression analysis lives at the heart of statistics. It’s a broad term for a set of methodologies used to predict a response variable (also called a dependent, criterion, or outcome variable) from one or more predictor variables (also called independent or explanatory variables). In general, regression analysis can be used to identify the explanatory variables that are related to a response variable, to describe the form of the relationships involved, and to provide an equation for predicting the response variable from the explanatory variables.

For example, an exercise physiologist might use regression analysis to develop an equation for predicting the expected number of calories a person will burn while exercising on a treadmill. The response variable is the number of calories burned (calculated from the amount of oxygen consumed), and the predictor variables might include duration of exercise (minutes), percentage of time spent at their target heart rate, average speed (mph), age (years), gender, and body mass index (BMI).

Regression analysis is a term that covers a broad range of methodologies in statistics. You’ve seen that it’s a highly interactive approach that involves fitting models, assessing their fit to statistical assumptions, modifying both the data and the models, and refitting to arrive at a final result. In many ways, this final result is based on art and skill as much as science.

This has been a long chapter, because regression analysis is a process with many parts. We’ve discussed fitting OLS regression models, using regression diagnostics to assess the data’s fit to statistical assumptions, and methods for modifying the data to meet these assumptions more closely. We looked at ways of selecting a final regression model from many possible models, and you learned how to evaluate its likely performance on new samples of data. Finally, we tackled the thorny problem of variable importance: identifying which variables are the most important for predicting an outcome.

Figure 22.1. Regression analysis saved to a web page