Demography

Where do you live? For many people this seemingly simple question doesn’t have a simple answer. Some retirees spend winters in Florida or Arizona and summers in New York or Minnesota. Others buy an RV and move from place to place, with no fixed place of residence. College students spend part of the year in their college towns and part in their home towns. Migrant farm workers often move from place to place over the course of a year, spending no more than a few weeks or months at any given location.

Population forecasts entail a significant amount of uncertainty, especially for long-range horizons and for places with small or rapidly changing populations. This uncertainty can be dealt with by presenting a range of projections or by developing statistical prediction intervals. The latter can be based on models that incorporate the stochastic nature of the forecasting process, on empirical analyses of past forecast errors, or on a combination of the two.

Population projections are judged primarily by their accuracy. The most commonly used measure for the precision component of accuracy is the mean absolute percent error (MAPE). Recently, the MAPE has been criticized for overstating forecast error and other error measures have been proposed. This study compares the MAPE with two alternative measures of forecast error, the Median APE and an M-estimator. In addition, the paper also investigates forecast bias.

Population forecasts for subcounty areas are used for a wide variety of planning and budgeting purposes. Given the importance of many of these uses, it is essential to investigate which techniques and procedures produce the most accurate forecasts. In this report, we describe several simple trend extrapolation techniques and several averages and composite methods based on those techniques. We evaluate the precision and bias of forecasts derived from these techniques using data from 1970–2005 for subcounty areas in Florida.

As the elderly population of the United States grows in absolute number and as a proportion of total population, accurate projections of that population become increasingly important for sound policy decisions. Cohort component techniques are typically used for state and local projections of the elderly population, but are often outdated or even nonexistent for many local areas. This paper suggests an altemative approach, based on Medicare data and simple projection techniques.

Population projections are widely used in both the public and private sectors for planning, budgeting, and analysis. For these purposes, projections are often needed for small areas such as census tracts, zip code areas or traffic analysis zones. Population size, growth constraints, shifting boundaries, and data availability create special problems for small-area projections, however, and very little is known about their forecasting performance.

The base period of a population forecast is the time period from which historical data are collected for the purpose of forecasting future population values. The length of the base period is one of the fundamental decisions made in preparing population forecasts, yet very few studies have investigated the effects of this decision on population forecast errors. In this article the relationship between the length of the base period and population forecast errors is analyzed, using three simple forecasting techniques and data from 1900 to 1980 for states in the United States.

Most population statistics for states, counties, and cities refer to permanent residents, or persons who spend most of their time in an area. At certain times, however, many states and local areas have large numbers of temporary residents who exert a significant impact on the area's economy, physical environment, and quality of life. Typically, very little is known about the number, timing, and characteristics of these residents.

This article deals with the forecast accuracy and bias of population projections for 2,971 counties in the United States. It uses three different population projection techniques and data from 1950, 1960,1970, and 1980 to make two sets of 10-year projections and one set of 20-year projections. These projections are compared with census counts to determine forecast errors. The size, direction, and distribution of forecast errors are analyzed by size of place, rate of growth, and length of projection horizon.