Use the mtcars R dataset. Let's say that you wanted to find the best fit model to explain mpg. H

Step 1:** Load the mtcars dataset and scale it using the scale() function to prepare it for PCA

Question

Use the mtcars R dataset. Let's say that you wanted to find the best fit model to explain mpg. However, many of the variables we used in the model are likely correlated (you can actually see this if you plot(mtcars)). So perhaps it might be more beneficial to find principal components that aggregate some of the measures, because these principal components will be uncorrelated. 1. (2pts) Prepare the mtcars dataset for a PCA by scaling it (hint: check to see if the output is a data frame. If not, use as.data.frame() to make it one.). 2. (2pts) Plot one of the scaled variables vs the unscaled version of the same variable (you can choose any variable for this plot). Don't forget to label your axes!

          Use the mtcars R dataset. Let's say that you wanted to find the best fit model to explain mpg. However, many of the variables we used in the model are likely correlated (you can actually see this if you plot(mtcars)). So perhaps it might be more beneficial to find principal components that aggregate some of the measures, because these principal components will be uncorrelated.

1. (2pts) Prepare the mtcars dataset for a PCA by scaling it (hint: check to see if the output is a data frame. If not, use as.data.frame() to make it one.).

2. (2pts) Plot one of the scaled variables vs the unscaled version of the same variable (you can choose any variable for this plot). Don't forget to label your axes!

Use the mtcars R dataset. Let's say that you wanted to find the best fit model to explain mpg. However, many of the variables we used in the model are likely correlated (you can actually see this if you plot(mtcars)). So perhaps it might be more beneficial to find principal components that aggregate some of the measures, because these principal components will be uncorrelated.

1. (2pts) Prepare the mtcars dataset for a PCA by scaling it (hint: check to see if the output is a data frame. If not, use as.data.frame() to make it one.).

2. (2pts) Plot one of the scaled variables vs the unscaled version of the same variable (you can choose any variable for this plot). Don't forget to label your axes!

Added by Heather M.

Question

Please give Ace some feedback