R language

Creating an informative chart or graph is easy if you know what comparison you want to make.

So we must first state our research question, detailing the comparison that we wish to make. Then we construct a dataset to perform the comparison. With our dataset in hand, we can explore the research question with charts and graphs, regressions and cross-tabulations.

Here, we have the freedom to choose our research question, so let's explore the following two questions:

  • Has New York City's Vision Zero initiative reduced traffic injuries and fatalities?
  • Does increasing the minimum wage increase the odds that an American adult will be employed?

In the case of Vision Zero, we will test the null hypothesis that there was no difference between the two time periods -- i.e. the hypothesis that the number of injuries and fatalities was statistically the same.

In the case of the minimum wage, we will test the null hypothesis that there is no correlation between state minimum wage rates and employment rates after controlling for other factors.

In both cases, the null hypothesis determines what inferences we might draw from the statistics that we calculate. That's why creating informative charts and graphs, estimating meaningful regressions and calculating insightful cross-tabulations start with formulation of a good null hypothesis.


To explore the Vision Zero question, we will analyze crash data from the NYC Dept. of Transportation.

To explore the minimum wage question, we will combine the minimum wage data from the Washington Center for Equitable Growth with the data on employment status, average annual pay and consumer prices from the US Bureau of Labor Statistics.

Finally, we must thank the R Foundation and the people who contributed to the development of the R language. Without their work, this analysis would not look so beautiful.

Copyright © 2002-2023 Eryk Wdowiak