Data Cart

Your data extract

0 variables
0 samples
View Cart
METPOP00
Average 2000 population of 2003 metro/micro areas in PUMA
Return to Geographic variables list

Description

METPOP00 reports the average 2000 population of metro/micro areas in each Public Use Microdata Area (PUMA). Where a PUMA lies entirely within a single metro area, this "average" is simply the metro area's population. Elsewhere, METPOP00 gives an approximation of the typical population size of the commuting systems where PUMA residents live.

Specifically, METPOP00 provides the population-weighted geometric mean of the 2000 populations of core-based (metropolitan/micropolitan) statistical areas (CBSAs), using the 2003 CBSA delineations of the Office and Management and Budget (OMB). For PUMA residents who live outside of any CBSA, METPOP00 uses county populations to approximate the commuting system population. (For Virginia "independent cities" that lie outside of CBSAs, we combine the populations of the independent cities with the populations of their neighboring counties.)

Using a geometric mean corresponds to measuring the average population on a logarithmic scale, which is suitable because CBSA and county populations generally have a log-normal distribution (highly concentrated at the lower end of the distribution with a long positive tail). For such distributions, the geometric mean is appropriately less sensitive to large outliers, more sensitive to variations among small values, and generally closer to the median than is the arithmetic mean. In practical terms, a logarithmic scaling makes sense because a difference between populations of 100,000 and 500,000 is about as significant for the character of a commuting system as any other factor-of-5 difference (e.g., 1 million and 5 million), and it is clearly more significant than an equal absolute difference of 400,000 in large commuting systems (e.g., 10.1 million and 10.5 million).

The specific steps to compute METPOP00 are 1) compute the populations of all spatial intersections (i.e., overlaps) between PUMAs and counties, 2) multiply each intersection's population by the logarithm of the population of the encompassing CBSA or noncore county, 3) sum these products for all intersections in each PUMA, 4) divide the sum for each PUMA by the total PUMA population, and 4) exponentiate the results to return to a linear scaling of populations.

For a detailed explanation and demonstration of the METPOP00 measure (as well as the DENSITY variable), see: