Lesson 5: Linear Regression Analysis

Motivate...

In the previous lesson, we learned how to calculate the strength and sign of a linear relationship between two datasets. The correlation coefficient, itself, is not a directly useful metric. The correlation coefficient represents the linear dependence of the two datasets. If the correlation is strong, a linear model would be a good fit for the data, pending an inspection into the data and confirming whether a linear relationship is plausible.

Fitting a model to data is beneficial for many reasons. Modeling allows us to predict one variable based on another variable, which will be discussed in more detail later on. In this lesson, we are going to focus on fitting linear models to our data using the approach called linear regression. We will build off our previous findings in Lesson 4 on the relationship between drought, temperature, and precipitation. In addition, we will work through an example focused on climate - how the atmosphere behaves or changes on a long-term scale, whereas weather is used to describe short time periods  [Source: NASA - What's the Difference Between Weather and Climate?(link is external)]. As the world becomes more concerned with the effects of climate and as more companies prepare for the long-term impacts, climate analytic positions will only continue to grow. Being able to perform such an analysis will be beneficial to you and your current or future employers.