One of the principal objectives of analytics is to discover underlying factors that account for observed patterns in data. Identifying these intervening factors often leads to an understanding of what drives a process or outcome of interest. Partial correlation is a technique that makes it possible to examine the correlation between two variables while controlling a third variable. Control variables are selected based on a hypothesis (or, at least, a hunch) that they influence the correlation between the two variables of interest.
For this example, we will look at the relationship between the birth rate, the infant mortality rate, and the secondary school enrollment ratio for females across nations. The hypothesis is that the educational level influences both the number of children born and the likelihood of a child surviving infancy.
The partial procedure...