*Introduction*

I have been learning how to use Google Sheets analytical tools (including the Statistics and Merge Sheets plugin) and while practicing I thought it would be the perfect time to answer a question I have been wanting to know: does population dictate GDP per capita?

The steps were as follows:

- Find sources of data
- Munge the data together
- Plot the data
- Perform statistical analysis

*Find sources of data*

This was fairly easy. Wikipedia contains several recent sources of country population and GDP. This data was contained in two sources and was copy/paste into two blank tabs in a Google Sheet.

*Munge the data together*

I used the Merge Sheets plugin to munge the data together. It took probably 30-60m to cleanup after the munge but it was pretty effective.

*Plot the data*

To get an initial look at the data I plotted GDP per Capita over Population:

*Perform Statistical Analysis*

First task is to plot the distribution of GDP per Capita and Population. This was accomplished by using the Statistics plugin and choosing both variables (and no additional options):

It's pretty clear that a normal distribution of GDP is starting to appear but is extremely skewed towards low incomes.

It is all clear that population is all over the place. The plugin calculated N=233.

The final step was to calculate the correlation. This was accomplished by chossing GDP per Capita as the variable and Population as the "By" (and no additional options).

The result was an R-squared of 0.002.

*Conclusion*

With an R-squared of 0.002 we learn that there is basically no correlation whatsover.

Perhaps more interestingly is how easy the tools are to use. And except for the data cleanup it literally took about 10m to perform this analysis. Amazing.

## Add new comment