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. Children of divorced parents may shift between the mother’s home and the father’s home on a monthly, weekly, or even a daily basis. Where do these people live? This is just one of the issues the U.S. Census Bureau will have to deal with in the upcoming 2010 Census.

The importance of the census cannot be overstated. It is the most comprehensive source of demographic data in the United States and tells us much of what we know about our nation’s population and how it is changing over time. This paper describes a bit of the history of census-taking in the United States, provides an overview of how the census is conducted, and discusses some of the hotbutton issues surrounding the decennial 2010 census of population and housing.

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. In this article, we develop and test prediction intervals based on empirical analyses of past forecast errors for counties in the United States. Using decennial census data from 1900 to 2000, we apply trend extrapolation techniques to develop a set of county population forecasts; calculate forecast errors by comparing forecasts to subsequent census counts; and use the distribution of errors to construct empirical prediction intervals.

The 2004 hurricane season was the worst in Florida’s history, with four hurricanes causing at least 47 deaths and some $45 billion in damages. In order to collect information on the demographic impact of those hurricanes, we surveyed households throughout the state and in the local areas sustaining the greatest damage. We estimate that one-quarter of Florida’s population evacuated prior to at least one hurricane; in some areas, well over half the residents evacuated at least once and many evacuated several times. Most evacuees stayed with family or friends and were away from home for only a few days. With continued population growth in coastal areas and the apparent increase in hurricane activity caused by global warming, the threats posed by hurricanes are rising in the United States and throughout the world. We believe the present study will help government officials plan more effectively for future hurricanes evacuations.

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. We also evaluate the effects of differences in population size, growth rate, length of base period, and length of forecast horizon on forecast errors, and investigate the impact of adjusting forecasts to account for the effects of annexations and changes in institutional populations. We believe the findings presented in this report will help practitioners make informed decisions when they construct population forecasts for subcounty areas.

(Accompanying tables begin on page 34 of this report.)

The elderly population of the United States is large and growing rapidly. In 2000, there were 35 million persons aged 65 and older, making up 12% of the total population. This population is projected to exceed 86 million by 2050, making up 21% of the total (U.S. Census Bureau, 2004). The oldest segment of the elderly population is growing particularly rapidly, with the population aged 85 and over projected to grow more than five-fold between 2000 and 2050, from 4 million to 21 million. Since disability rates rise with age, there is a strong likelihood that population aging will bring large increases in the number of disabled persons. This will have important implications for the housing industry and housing policy in the United States and will require the attention of federal, state, and local planners.

The effects of population size and growth rate on population forecast accuracy have been well documented. For example, we know that small places generally have larger errors than large places; that errors are generally higher for places with high growth rates than places with low growth rates; and that size of error generally remains more stable over time than does the direction of error. In this paper, we delve more deeply into these relationships using data for 2,482 counties in the United States and expand the analysis to include a third explanatory variable, prior forecast error.

The elderly population of the United States is large and growing rapidly. In 2000 there were 35 million persons age 65+, comprising 12% of the total population. By 2050 this population is projected to exceed 86 million, almost 21% of the total. Since disability rates increase with age, the aging of the population will bring substantial increases in the number of disabled persons and have a significant impact on the demand for housing. In this paper, we collect information on physical disabilities, particularly as they relate to mobility limitations. We analyze trends in disability rates over time and apply projected rates by age and sex to projections of the U.S. population to produce projections of the number of disabled persons. We follow a similar procedure to produce projections of the number of households with at least one disabled resident and develop an estimate of the probability that a newly built single-family detached unit will house at least one disabled resident during its lifetime. We extend the analysis to include the impact of “visitability,” or the ability of a disabled person to visit the homes of friends and relatives without difficulty. We close with a discussion of the implications of the rapidly rising number of disabled persons for the housing industry and for public policy in the United States.

Most migration statistics in the United States focus on changes in permanent residence, thereby missing temporary moves such as the daily commute to work, business trips, vacations, and seasonal migration. In this paper, we analyze temporary migration streams in Florida, focusing on moves that include an extended stay. Using several types of survey data, we examine the characteristics of non-Floridians who spend part of the year in Florida and Floridians who spend part of the year elsewhere. We develop estimates of the number, timing, and duration of temporary moves and the origins, destinations, characteristics, and motivations of temporary migrants. This study presents the most comprehensive analysis yet of temporary migration in Florida and provides a model that can be used in other places.

Many researchers have used time series models to construct population forecasts and prediction intervals at the national level, but few have evaluated the accuracy of their forecasts or the out-of-sample validity of their prediction intervals. Fewer still have developed models for subnational areas. In this study, we develop and evaluate six ARIMA time series models for states in the United States.

The 2004 hurricane season was the worst in Florida’s history, with four hurricanes causing at least 47 deaths and some $45 billion in damages. In order to collect information on the demographic impact of those hurricanes, we surveyed households throughout the state and in the local areas sustaining the greatest damage. Using these data, we estimated that one-quarter of Florida’s population evacuated prior to at least one of the hurricanes; in some areas, well over half the residents evacuated at least once and many evacuated several times. Most evacuees stayed with family or friends and were away from home for only a few days. In this study, we summarize the results regarding the number of evacuees, types of lodging, and number of days spent away from home for the state and the regions hit hardest by the hurricanes. Using logistic regression analysis, we analyze the factors affecting evacuation decisions. With continued population growth in coastal areas and the apparent increase in hurricane intensity (and perhaps frequency) caused by global warming, the threat posed by hurricanes is increasing as well. We believe the results of the present study will help federal, state, and local officials deal more effectively with this threat.

The temporary migration of elderly adults has a major impact on the resident populations of both sending and receiving communities. This article presents a methodology for estimating temporary migration and provides insights into migratory patterns that cannot be achieved by focusing solely on changes in place of usual residence.

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 based on models that incorporate the stochastic nature of the forecasting process or on empirical analyses of past forecast errors. In this paper, we develop and test empirical prediction intervals for county population forecasts in the United States. We find that prediction intervals based on the distribution of past forecast errors provide reasonably accurate predictions of the distribution of future forecast errors. We believe the construction of empirical prediction intervals to accompany population forecasts will help data users plan more effectively for an uncertain future.

In this study, we describe an approach that can be used to estimate the demographic impact of hurricanes and other natural disasters, provide a detailed assessment of the 2004 hurricane season in Florida, compare the 2004 hurricanes with Hurricanes Andrew (1992) and Katrina (2005), and draw several conclusions regarding the likely impact of hurricanes and other natural disasters on future population growth. This study provides the most comprehensive assessment yet of the 2004 hurricane season in Florida and adds to the small but growing literature on the demographic effects of natural disasters.

There are many "Floridas." There are the farms and small towns of north Florida, with families that have lived there for generations; the booming commercial and industrial areas of central Florida, creating new jobs and attracting young workers and their families from all over the United States; the retirement villages of southwest Florida, bringing thousands of snowbirds and retirees from northern states each year; and the enclaves of foreign-born residents in southeast Florida, bringing cultural diversity and a melting-pot ambiance to the region. Florida is not a single entity but rather a composite of many diverse parts, each with its own unique identity.

These parts are tied together by a common thread: rapid population growth. Florida has been one of the most rapidly growing states in the nation for many years and is expected to continue growing rapidly in the future. Although some parts of the state have grown more rapidly than others, no part has completely escaped the effects of rapid population growth. Population growth and demographic change have had an impact on virtually every aspect of life in Florida, and no social, political, environmental, or economic issue can be understood without a firm grasp of the state's population dynamics.

By most measures, the 2004 hurricane season was the worst in Florida’s history. Four hurricanes blasted through the state between August 13 and September 25, with Charley making landfall on the southwest coast near Punta Gorda, Frances on the southeast coast near Stuart, Ivan in the panhandle near Pensacola, and Jeanne nearly retracing the route followed by Frances. This was the first time in recorded history that four hurricanes had struck Florida in a single year. Most parts of the state were hit by at least one of the hurricanes and some were hit by two or even three. Overall, the storms were blamed for at least 80 deaths in Florida and caused more than $20 billion in damages.

In this issue of Florida Focus, we discuss some of the major findings of surveys conducted by BEBR of permanent residents living in Florida when the first of the hurricanes struck.

Florida was struck by four devastating hurricanes in 2004. In a previous issue of Florida Focus, we presented the results of a survey designed to assess the impact of those hurricanes at the state level. Those results provided a useful statewide overview, but provided no information on the impact of the hurricanes on local areas in Florida. Since some of the most populous parts of the state were largely unaffected by the hurricanes, state-level results understate the impact of the hurricanes on many local areas. In this report, we describe the results of surveys conducted in the areas most strongly affected by the hurricanes. These surveys, funded by the Florida Legislature, provide a wealth of information on evacuations, housing damage, population displacement, and reconstruction. The results of these surveys deepen our understanding of the full impact of Florida’s 2004 hurricane season.

A chain of supermarkets decides to launch a new line of ethnic foods. Where should it concentrate its marketing efforts? A school district is plagued by increasingly crowded elementary schools. Is this a temporary phenomenon or a continuing long-run trend? A hospital considers adding an obstetrics unit. Will anticipated service demand cover the additional costs? A metropolitan transportation agency plans to expand its rapid transit system. Where should new routes and transit stops be added? A manufacturer needs to build a new plant. Where can it find enough skilled workers to staff that plant? Answering questions like these lies at the heart of small-area and business demography.

Estimates of the Hispanic population have traditionally been based on historical trends, ratios, or some variant of the cohort-component method. In this article, we describe and test a methodology in which estimates of the Hispanic population are based on symptomatic indicators of population change such as births, deaths, and school enrollments. Methods. Using a variety of techniques, we develop Hispanic population estimates for counties in Florida. We evaluate the accuracy of those estimates by comparing them with 2000 census counts.

Hispanic population estimates have larger errors than estimates of total population; errors vary considerably by population size and growth rate; some techniques perform better than others in places with particular population characteristics; and averages often perform better than individual techniques. In many circumstances, symptomatic data series can provide more accurate estimates of the Hispanic population than more commonly used techniques.

This book chapter starts by discussing the major producers of international, national, and subnational projections. Next, it provide a description of the methods and materials used in preparing three basic types of population projections: (1) trend extrapolation; (2) the cohort-component method; and (3) structural modeling. The authors briefly discuss methods for preparing related projections on such topics as school enrollment, employment, and households. They follow this with a review of issues that we believe should be considered when preparing or evaluating population projections, including a discussion of forecast accuracy. The authors close with several conclusions regarding the nature and utility of population projections.

The housing unit (HU) method is the most commonly used method for making small-area population estimates in the United States. These estimates are used for a wide variety of budgeting, planning, and analytical purposes. Given their importance, periodic evaluations of their accuracy are essential. In this article, we evaluate the accuracy of a set of HU population estimates for counties and subcounty areas in Florida, as of April 1, 2000. We investigate the influence of differences in population size and growth rate on estimation errors; compare the accuracy of several alternative techniques for estimating each of the major components of the HU method; compare the accuracy of 2000 estimates with that of estimates produced in 1980 and 1990; compare the accuracy of HU population estimates with that of estimates derived from other estimation methods; consider the role of professional judgment and the use of averaging in the construction of population estimates; and explore the impact of controlling one set of estimates to another.

A number of studies have dealt with the use of time series models to develop confidence intervals for population forecasts. Most have focused solely on national-level models and only a few have considered the accuracy of the resulting forecasts. In this study, we take this research in a new direction by constructing time series models for several states in the United States and evaluating the resulting population forecasts. Using annual population estimates from 1900 to 2000, we develop a variety of forecasts and investigate the impact of differences in model specification, state, launch year, length of base period, and length of forecast horizon on the accuracy of point forecasts and the width of confidence intervals. We also evaluate the extent to which predicted confidence intervals encompass future population counts. We conclude with several observations regarding the potential usefulness of time series models for forecasting state populations.

A number of studies have evaluated the accuracy ofprojections of the size of the total population, but few have considered the accuracy of projections by age group. For many purposes, however, the relevant variable is the population of a particular age group, rather than the population as a whole. We investigated the precision and bias of a variety of age-group projections at the national and state levels in the United States and for counties in Florida. We also compared the accuracy of state and county projections that were derived from full-blown applications of the cohort-component method with the accuracy of projections that were derived from a simpler, less data-intensive version of the method.

Business demography encompasses the application of demographic concepts, data, and techniques to the practical concerns of business decision makers. This loosely organized field includes—but is not limited to—site selection, sales forecasting, financial planning, market assessment, consumer profiles, target marketing, litigation support, and labor force analysis. Specific applications have evolved over time, reflecting changes in data sources, computer technology, statistical techniques, and the business environment itself. In this article, we survey the major features of this eclectic and rapidly changing field, focusing on the United States.

Spurred by new business applications and government programs, the demand for small-area demographic data and analysis has grown tremendously in recent decades. To meet that demand, analysts have drawn on an expanding set of data sources, statistical techniques, and computer applications. The result has been improved data quality across a broad spectrum of variables and geographic areas, enhancing both the usefulness and the importance of small-area analyses.

In the housing unit method, population is calculated as the number of households times the average number of persons per household (PPH), plus the population residing in group quarters facilities. Estimates of households and the group quarters population can be derived directly from concurrent data series, but estimates of PPH have traditionally been based on previous values or estimates for larger areas. In our study, we developed several regression models in which PPH estimates were based on symptomatic indicators of PPH change. We tested these estimates using county-level data in four states and found them to be more precise and less biased than estimates based on more commonly used methods.