One of the data science skills I want to play around with is deriving insights from data that publically available. Here, lets use some data on SF employee compensation and see what we can learn from the data.
First, per usual, load the dependencies.
I went to a talk a couple of weeks ago at Stanford on using machine learning to understand complex biological data. At one point in the talk the speaker made an offhand comment about data so simple "that a five year old could cluster it". Wow, were you that smart at five?
I want to get some intuition about regression models using multiple independent variables. More precisely, I am unsure if the relevant predictors would be better uncovered by multiple regression, or by pairwise analysis of all predictors against the response variable. So I'd like to use a dataset where I know the precise contribution of each predictor to the response variable.
Here, I want to look at using R to perform variable selection for a linear model. Let's consider forward and reverse selection, statistical techniques to keep only variables that maximize the variance explained. The dataset I'm using is the Boston housing price dataset from the MASS library.
Note, that there are some drawbacks/limitations to consider when using variable selection: http://www.stata.com/support/faqs/statistics/stepwise-regression-problems/