Higher local employment numbers lead to higher payrolls, especially in finance

Andrey Kamenov

Andrey Kamenov, Ph.D. Probability and Statistics

As we saw in our post about high-paid finance jobs some time ago, there are some counties where the average payroll is significantly higher. The highest numbers are registered in the large cities, but there has been a significant increase is counties that neighbor them (such as Suffolk and Westchester).

If we are to find a relationship between the payroll and employment numbers, it would be logical to assume that the payroll is higher in counties where more people are employed. Actually, it is likely that the relationship is reciprocal — more people are willing to get a job in a city where paychecks are larger.

If we take a look at the data provided by the U.S. Census Bureau County Business Patterns, it appears that such a relationship indeed exists; it is best described with a linear regression relationship between the average annual payroll and logarithm of the corresponding county employment number. This means that there should be roughly the same difference between counties with 5,000 and 10,000 people working in an industry as there is between counties with 50,000 and 100,000 people.

Let’s look at the chart representing this model for some of the more popular industries. We take finance and insurance, construction and “professional, scientific, and technical services” (which we will refer to as “professional services” for short):

new_lmplot

As we see, the relationship is somewhat less pronounced for the construction industry. What is more interesting is that most, if not all, of the outliers in the right part of the chart belong to the finance set. Among these outliers, there are three counties in New York State, two in California and one in each of the following states: Massachusetts, New Jersey, Connecticut and Washington, D.C.

Here are the residuals of our model on the U.S. map. As you can see, the fit is rather good in most counties, with the green zones, indicating higher-than-expected annual payrolls, concentrated near the large cities.

Discuss this article on our forum with over 1,900,000 registered members.

About Andrey Kamenov

Andrey Kamenov

Andrey Kamenov, Ph.D. Probability and Statistics

Andrey Kamenov is a data scientist working for Advameg Inc. His background includes teaching statistics, stochastic processes and financial mathematics in Moscow State University and working for a hedge fund. His academic interests range from statistical data analysis to optimal stopping theory. Andrey also enjoys his hobbies of photography, reading and powerlifting.

Other posts by Andrey Kamenov:

Leave a Reply

Your email address will not be published. Required fields are marked *