Econ 4621: Urban Economics (Holmes)

Minneapolis/St. Paul Density Gradient

The Excel Worksheet, MSP_density_gradient.xls contains data for cities in the MSP metro area as well as the regressions run in class. (The regression results are on separate worksheets labeled 1990 and 2000.) The data is from the 2000 and 1990 Census. The data was constructed as follows.

For each Minnesota city (apologies to Hudson, WI), the distances between the city and downtowns of Minneapolis and St. Paul were determined. The variable DISTANCE in the data is the minimum of these two distances. Cities with DISTANCE less than or equal to 20 miles were selected. The longitude and latitude coordinates of each city are from the Census and are defined to be some point, usually the geographic center, in the city. The coordinates for downtown Minneapolis lat=44.975653, long=-93.272287;the coordinates of the IDS building and for downtown St. Paul are lat=44.9559, long=-93.1022, the coordinates of the state capital.

The data includes the land area (in square miles) of each city from the 2000 Census. This does not include water area, a relevant issue for the Twin Cities. The data includes the 1990 population and the 2000 population.

We calculated the density gradient by running a regression with the natural log of the population density as the Y variable and the distance from downtown as the X variable. Note to calculate the natural log with Excel, we used the ln(x) function.

To run a regression in Excel, we used the Data Analysis option of the Tools menu. If the option is missing from your copy of Excel, you can add it by provides what's necessary. If that option is not available in the Excel you are running, you can add it by selecting the Add-Ins option from the Tools menu. For tips on using Excel to run a regression, click here for a helpful web site.