Accounting for migration in cohort-component projections of state and local populations

Abstract

Migration is the most difficult component of state and local population growth to forecast accurately because it is more volatile than either births or deaths, and subject to much larger fluctuations within a short period of time. In addition, migration rates can be based on several different measures of migration and the base population. The choice of the appropriate base population has received little attention from demographic researchers, but can have a tremendous impact on population projections. In this article, I develop three different models for projecting migration, each using a different denominator for migration rates. Population projections for ten states are made, using identical data and cohort component techniques, except for the different formulations of migration rates. Differences among the three sets of projections are noted, and conclusions are drawn regarding their usefulness as forecasts of population growth.

Tests of Forecast Accuracy and Bias for County Population Projections

“…This relationship became fairly weak for counties of 25,000 or more, however. This too is consistent with several earlier studies showing no consistent relationship between size of place and size of error among large places (e.g., Schmitt and Crosetti 1951;Smith 1984).…”

“…The results from these three measures are not shown here but led to the same conclusions as those reported in this article (Smith 1986a).…”

“…A negative relationship between size of place and size of error is a common empirical finding for population projections (e.g. , Irwin 1977;Isserman 1977;Smith 1984;White 1954). This relationship became fairly weak for counties of 25,000 or more, however.…”

“…For the entire sample, MAPE's were 25.9% for LINE, 30.8% for EXPO, and 35.4% for SHIFI'. A strong positive relationship between length of projection horizon and size of error is a common empirical finding (e.g., Irwin 1977;Isserman 1977;Schmitt andCrosetti 1951, 1953;Siege1 1953;Smith 1984;Stoto 1983;White 1954). …”

“…A number of studies have found that simple extrapolation techniques produce short-to medium-term forecasts of total population that are at least as accurate as those produced by more sophisticated techniques (e.g., Ascher 1978;Greenberg 1972;Hajnall955;Kale, Voss, Palit, and Krebs 1981;Siege1 1972;Smith 1984;Stoto 1983). I know of no study showing more sophisticated techniques to consistently produce more accurate population projections than these simple techniques.…”