1. Let $$M_0$$ denote the null model, which contains no predictors. This model simply predicts the sample mean for each observation.
2. For k = 1,, 2, ..., p:
(a) Fit all $$\binom{p}{k}$$ models that contains exactly k predictors.
(b) Pick the best among these $$\binom{p}{k}$$ models, and call it $$M_k$$. Here best is defined as having the smallest RSS, or equivalently largest $$R^2$$.
3. Select a single best model from among $$M_0, ..., M_p$$ using cross-validated prediction error, $$C_p$$ (AIC), BIC, or adjusted $$R^2$$.

University of Michigan - Ann Arbor

Approach that includes testing all possible combinations of predictor variables and then selecting the best model.
Required packages for R:
1. tidyverse for easy data manipulation and visualization
2. caret for easy machine learning workflow
3. leaps, for computing best subsets regression

Best Subset Selection

James, G., Witten, D., Hastie, T., & Tibshirani, R. (2013). An introduction to statistical learning (Vol. 112, pp. 3-7). New York: springer.

An Introduction to Statistical Learning with Applications in R

Can also utilize the "install packages" feature in r 
library(tidyverse)
library(caret)
library(leaps)

How do I download packages in R?

Collection of R packages designed for data science - all packages have a shared design of tidy data
Several tools included - the connection s between them serve to make statisticians and data scientists more productive 

What is tidyverse?

Classification And REgression Training
Used to streamline making predictive models
Functions for training and plotting classification and
regression models.

What is caret?

Performs an exhaustive search for the best subsets of the variables in x
Used for regression subset selection

Learn Before

Related