Data Matters with Fathom! Dynamic Statistics™ software

Activity 10.1

In 1972, Samuel Bowles found a correlation coefficient of .375 between years of education and income. What do you find in the Rep US Sample data?

To find the correlation, drag a new estimate onto the workspace. Select Empty Estimate, Linear Regression. Drag Education and Total Personal Income to Independent attribute and Dependent attribute.

Karl Pearson’s correlation test is based on an assumption that the data are normally distributed. For each numeric attribute in the data, get a histogram and make a judgment about whether the data look fairly normally distributed.

Drag a new graph onto the workspace. Drag a numeric variable onto the graph window. Select Dot Plot, Histogram. Drag the other numeric attributes to the x-axis of the histogram.

Are there correlations in that data that you could test with the significance test of the correlation coefficient?