Population Projections by Age for Florida and its Counties: Assessing Accuracy and the Impact of Adjustments

Projections of total population have been evaluated extensively, but few studies have investigated the performance of projections by age. Of those that did, most focused on projections for countries or other large areas. In this article, we evaluate projections by age for Florida and its counties, as produced and published between 1996 and 2010 by the Bureau of Economic and Business Research at the University of Florida. We first compare the precision and bias of projections of total population with the precision and bias of projections by age, at both the state and county levels. This is followed by a more detailed examination of county-level projection errors for individual age groups, first in the aggregate and then disaggregated by sex and population size. The second part of the analysis focuses on a number of adjustments that were implemented in projections published in 2006 and 2009. Intended to improve accuracy, these adjustments involved updates to the base population, fertility rates, and survival rates. We compare the accuracy of projections incorporating these adjustments with the accuracy of projections excluding them. We believe this study offers a unique opportunity to examine a variety of characteristics regarding the forecast accuracy of small-area population projections by age.     

Testing local level labor force and unemployment projections

The labor force projections perform well, even for small areas, which suggests that changes in local labor force participation rates can be approximated by national changes. In fact, the mean absolute percent errors are low even when the previously calculated population projections are used. The unemployment projections do not do as well, and using 1980 census labor force data instead of previously calculated labor force projections offers no improvement in the results. A two-step study is needed to determine why the errors are so large. First, the state level changes from 1970 to 1980 should be compared with national changes to determine the difference in unemployment rate changes by race and sex. Second, state level data on the occupational mix should be examined for the relationship between this and the changes in state level unemployment rates by race and sex. It is hypothesized that the first step will show that even state level changes in unemployment rates by race and sex cannot be well approximated by the national changes and the second step will show that some of the variation can be explained by state differences in occupational mix. Further studies should be made to determine how the calculation of national changes affects the results. Changes in labor force participation rates seem to follow trends, and therefore extrapolation may not have much effect on the results. Although using the actual changes in unemployment from 1970 to the latest year available as a proxy for the changes from 1970 to the target year may have a serious detrimental effect on the unemployment projections, if some of the variation in the national changes in race and sex can be explained and some adjustments made, the actual changes may be the best proxy to use.     

Aboriginal population prospects

Data from the 1991 Census largely confirm earlier projections of the size and structure of the Aboriginal population, although the data for Torres Strait Islanders are markedly inconsistent with previous counts. The 1986 and 1991 Censuses mark the first intercensal period for decades for which Aboriginal population counts have been consistent. This provides an opportunity, taken in this paper, to examine closely the discrepancies between projections and the 1991 Census and to comment on ways in which determinants of Aboriginal population change are diverging from the parameters used for previous projections. We pay particular attention to mortality prospects, because of the occurrence in the 1991 Census of a higher than expected sex ratio and differences between projections and counts for certain age groups. We note the evidence for under-enumeration of the Aboriginal population in particular age groups in the 1991 Census as in previous censuses, and estimate the size of adjustments necessary to correct for some, but not all, of these deficiencies. The analysis shows that Aboriginal fertility increased in the second half of the 1980s.     

The forecast accuracy of Australian Bureau of Statistics national population projections

This paper examines the forecast accuracy of Australian Bureau of Statistics national population projections produced from the 1960s to the early 2000s. As well as total populations, the accuracy of the following is assessed: age-sex-specific populations, the Total Fertility Rate, life expectancy at birth and net international migration. It is shown that forecasts of the 1960s and 70s were the most inaccurate; forecasts of the 1980s and later proved to be much more reliable. The paper goes on to take an alternative perspective on population forecast error through the use of an adapted percentage error measure which accounts for offsetting errors in births, deaths, net migration and the jump-off population. This measure also permits an assessment of the relative contributions of the components of demographic change to overall inaccuracy. It is shown that errors in forecasting net international migration have generally contributed most to inaccuracy followed by births and then deaths and jump-off error. ABS projections of total population are also compared to those produced using a simple naïve model. The paper concludes by arguing that the new error measure could prove valuable in other studies of population forecast accuracy.     

Precision,bias, and uncertainty for state population forecasts: an exploratory analysis of time series models

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. Using annual population estimates from 1900 to 2000 and a variety of launch years, base periods, and forecast horizons, we construct population forecasts for four states chosen to reflect a range of population size and growth rate characteristics. We compare these forecasts with population counts for the corresponding years and find precision, bias, and the width of prediction intervals to vary by state, launch year, model specification, base period, and forecast horizon. Furthermore, we find that prediction intervals based on some ARIMA models provide relatively accurate forecasts of the distribution of future population counts but prediction intervals based on other models do not. We conclude that there is some basis for optimism regarding the possibility that ARIMA models might be able to produce realistic prediction intervals to accompany population forecasts, but a great deal of work remains to be done before we can draw any firm conclusions.     

Forecast accuracy of australian subnational population projections

Despite the considerable resources devoted to making demographic projections in Australia over the past two decades, there have been few attempts to evaluate the performance of these projections in terms of forecast accuracy. This paper first considers the role of accuracy amongst other objectives of projection activity. Accepting accuracy as a legitimate goal, we then assess the performance of 48 sets of population projections and forecasts for states and territories of Australia prepared since 1970. Projection accuracy is assessed by reference to length of forecast horizon, population size and rate of growth. We also examine the main sources of forecast error in selected projections for each state and compare the performance of past projections with alternatives based on simple extrapolation of contemporary population trends.     

The World's Changing Human Capital Stock: Multi‐State Population Projections by Educational Attainment

This research note presents the first global population projections by educational attainment using methods of multi‐state population projection. The educational composition of the population by age and sex and educational fertility differentials are estimated for 13 world regions, and alternative scenarios are presented to the year 2030. One of these scenarios assumes constant educational transition rates and the other assumes that all regions reach Northern American levels of enrollment rates by 2030. The strong momentum or, as the case may be, inertia in the transformation of the educational composition of a population, seen in the results, arises because education is mostly acquired at a young age. The sex bias in the educational composition, especially evident in some developing countries, is unlikely to disappear soon. China has made remarkable progress in improving educational enrollment and as a consequence by 2030 is expected to have more educated people of working age than Europe and Northern America together.     

Stability over time in the distribution of population forecast errors

A number of studies in recent years have investigated empirical approaches to the production of confidence intervals for population projections. The critical assumption underlying these approaches is that the distribution of forecast errors remains stable over time. In this article, we evaluate this assumption by making population projections for states for a number of time periods during the 20th century, comparing these projections with census enumerations to determine forecast errors, and analyzing the stability of the resulting error distributions over time. These data are then used to construct and test empirical confidence limits. We find that in this sample the distribution of absolute percentage errors remained relatively stable over time and data on past forecast errors provided very useful predictions of future forecast errors.     

Development and accuracy of projections of population and households in the united states

The history of the official U. S. projections of population and house-holds in recent decades is briefly reviewed, with particular attention to methodology and the relation of the methodology to the accuracy of the projections. The introduction of the cohort-component procedure in the 1930’s opened the way for separate analysis of the trend of the components of births, deaths, and net immigration in connection with making population projections. As a further development, the period-fertility method of projecting births gave way in the 1960’s to the cohort-fertility method. Consideration is now being given to various methods involving parity-progression procedures. Some alternative methods and problems of measuring the accuracy of population projections are then considered. The percent “error” in the projected population growth, by components and age, and the range from high to low expressed as a percent should also be examined in addition to the percent “error” in the total population. However accuracy is measured, the projections made in the 1930’s and 1940’s were often wide of the mark, and those made in the 1950’s and 1960’s failed to anticipate the sharp changes which occurred, even though the actual figures usually fell within the range projected. Elaboration of projection methodology has not resulted in any great increase in the precision of the projections, largely because birth rates have fluctuated widely, and the fluctuations have proven difficult, if not impossible, to predict. The projections of households have had a roughly similar history, and the methods and problems of evaluation are somewhat similar. Their development has been characterized by the introduction of alternative and changing “headship” rates and increasing disaggregation of the data and procedures. The paper concludes with some generalizations based on U. S. experience. Although refinement of methods may contribute little to accuracy, accuracy is only one aspect of the usefulness of projections. The need for conditional projections and their analytical usefulness are such that there is no question that we should confidently continue to make them.     

An Empirical Analysis of the Effect of Length of Forecast Horizon on Population Forecast Errors

Many studies have found that population forecast errors generally increase with the length of the forecast horizon, but none have examined this relationship in detail. Do errors grow linearly, exponentially, or in some other manner as the forecast horizon becomes longer? Does the error-horizon relationship differ by forecasting technique, launch year, size of place, or rate of growth? Do alternative measures of error make a difference? In this article we address these questions using two simple forecasting techniques and population data from 1900 to 1980 for states in the United States. We find that in most instances there is a linear or nearly linear relationship between forecast accuracy and the length of the forecast horizon, but no consistent relationship between bias and the length of the horizon. We believe that these results provide useful information regarding the nature of population forecast errors.     

An Evaluation of Population Estimates in Florida: April 1, 2000

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. Our results confirm a number of findings that have been reported before and provide empirical evidence on several issues that have received little attention in the literature. We conclude with several observations regarding future directions in population estimation research.     

Empirical Prediction Intervals for County Population Forecasts

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. We find that empirically-based prediction intervals provide reasonably accurate predictions of the precision of population forecasts, but provide little guidance regarding their tendency to be too high or too low. We believe the construction of empirically-based prediction intervals will help users of small-area population forecasts measure and evaluate the uncertainty inherent in population forecasts and plan more effectively for the future.     

State population and household estimates,with age,sex, and components of change: 1981-87

This report contains provisional US state estimates of 1) the resident and civilian populations and of households for July 1, 1987, 2) revised annual population and household estimates for July 1, 1981-1986, and 3) components of population change for the 1980-1987 period. Also shown are annual age estimates and median age of the resident population of states, 1981-1987, by sex for 10-year age groups and selected broad age groups. Florida passed Pennsylvania to become the 4th most populous state in 1987, ranking behind California, New York, and Texas. Alaska and Louisiana both registered population losses for the 1st time this decade, while West Virginia, Oklahoma, and Wyoming again had population declines. Several agriculture-based states--Iowa, North Dakota, and Nebraska--marked another year of population declines. California and Florida each gained more than 2 million persons through net immigration since 1980, and Texas over 1.2 million. The 25-44 year-olds are the most rapidly growing age group in the 1980s, increasing by 23.8%. This age group now constitutes almost 1/3 (31.9%) of the US population. US median age continues to climb upward, increasing from 30 years in 1980 to 32.1 years in 1987. The Northeast continues as the region with the highest median age (33.7) and the highest proportion of elderly (13.5% aged 65 and over). Largely because of changes in the age structure, households increased faster than the total population from 1980-1987 (12% versus 7.4%). The 4 states that lost population between 1980 and 1987--Ohio, Michigan, Iowa, and West Virginia--all had increases in households during the same period. While the Northeast and Midwest together accounted for only 10.8% of national population growth in the 1980-1987 period, they accounted for 26.9% of the national increase in households. California, Texas, and Florida accounted for 52.4% of national population growth from 1980 to 1987, but only for 36.5% of household growth.     

Ethnic population projections for the UK, 2001–2051

This paper reports on projections of the United Kingdom’s ethnic group populations for 2001–2051. For the years 2001–2007 we estimate fertility rates, survival probabilities, internal migration probabilities and international migration flows for 16 ethnic groups and 355 UK areas. We make assumptions about future component rates, probabilities and flows and feed these into our projection model. This model is a cohort-component model specified for single years of age to 100+. To handle this large state space, we employed a bi-regional model. We implement four projections: (1) a benchmark projection that uses the component inputs for 2001; (2) a trend projection where assumptions beyond 2007 are adjusted to those in the UK 2008-based National Population Projections (NPP); (3) a projection that modifies the NPP assumptions and (4) a projection that uses a different emigration assumption. The projected UK population ranges between a low of 63 millions in 2051 under the first projection to a high of 79 million in the third projection. Under all projections ethnic composition continues to change: the White British, White Irish and Black Caribbean groups experience the slowest growth and lose population share; the Other White and Mixed groups to experience relative increases in share; South Asian groups grow strongly as do the Chinese and Other Ethnic groups. The ethnic minority share of the population increases from 13% (2001) to 25% in the trend projection but to only 20% under our modified emigration projection. However, what is certain is that the UK can look forward to be becoming a more diverse nation by mid-century.     

Indigenous Australian population projections: problems and prospects

According to estimates from the 2006 Census, Aboriginal and Torres Strait Islander (Indigenous) Australians made up 2.5 % of the total Australian population. However, the focus of research and policy debate on Indigenous Australians far exceeds their population size for reasons of history, socio-economics, geography and demography. This has led to a need for accurate population projections of the population. In this paper, we outline a number of issues related to Indigenous population projections. These include the nature of self-identification; the impact of particular policy changes; significant differences in demographic parameters; and high rates of exogamy, especially in urban areas. We also document the relative accuracy of past and current population projections. In the final section of the paper we outline a research agenda that has the potential to lead to new and better Indigenous population projections.     

Estimation of local demographic variation in a flexible framework for population projections

A cohort component projection of local populations based on sex and single year of age offers great value for planning local services, but demands data beyond the detail available. Local fertility, mortality and migration schedules by age and sex must be estimated sensitively to local variation if the results are to be of greater value than simpler methods of projection. Two approaches are compared, using data for the recent past: (a) direct estimation of local area age-specific schedules of fertility, mortality and migration based on data available to the national statistical agency; (b) graduation of national schedules using only local area population estimates by age, total numbers of births, and total numbers of deaths; age-specific migration is indirectly estimated from successive population estimates. These two approaches are compared with a projection using the same rates for each area. The three projections have been implemented for electoral wards in the Fife local government area of Scotland, using the flexible framework provided by POPGROUP software. Persuasive local population projections based on standard data for standard areas are feasible without the regular publication of migration flows.     

The abs population projections: Overview and evaluation

The paper provides a brief history of the ABS projection services in the context of its role as the central statistical agency in Australia. It also presents an overview of the methodology used for generating the projections and details the procedures used for compiling the various components of change incorporated in the projections. The accuracy of the ABS past projections is assessed by comparing their results, both at the national and state/territory levels, with corresponding estimated resident population figures. The paper also describes the range of projection services currently provided by the ABS, lists present unmet needs and indicates some of the developments likely to occur in the future in satisfying unmet demand, consolidation of existing services and dissemination of output.     

Developing strategies for deriving small population fertility rates

Many agencies require population estimates and projections by ethnic group. These projections need ethnic-specific, age-specific fertility rates (ASFRs) but their inclusion is challenging since ethnicity is not recorded at birth registration. In this paper maternity data are used in a case study of electoral wards in Bradford, West Yorkshire, to develop fertility rates for small populations for a 1991 based projection. The challenge is to capture local variations in fertility by ethnic group when data are sparse. Small areas were grouped together using cluster analysis to define combinations with similar sociodemographic and fertility experiences so that sparse data could be aggregated to estimate reliable ethnic-specific fertility rates. For comparison, the data were aggregated into the 1991 Office for National Statistics area type classification. Fertility rates by single year of age for all area types were smoothed using the Hadwiger function. For the White ethnic group there were sufficient births to create ethnic-specific, ward-level ASFRs. For other ethnicities grouping of areas was necessary. The accuracy of the ASFRs in predicting births was assessed using mean absolute percentage error. Results show that for some minority groups district-level ethnic-specific fertility rates produced the most accurate birth estimates even though they were based on a larger area. This implies that rates created may be informative about the local area for White ethnic type but not in the same way for smaller ethnic groups. In terms of grouping strategies we recommend that existing classifications are assessed to determine how well variations in rates are stratified before embarking on a custom scheme. Where population sub-groups are small in some areas, it may be more reliable to use rates derived for larger areas and apply these to local populations. Inevitably, the rates used in a projection are a compromise but hopefully will still capture important dimensions of population change.     

Population Projections and Demographic Knowledge in France and Great Britain in the Postwar Period

This study examines how official national population projections—a key mechanism for the production and dissemination of demographic knowledge—contributed to differing interpretations of population and fertility trends in France and Great Britain in the decades following World War II, despite these countries' similar fertility rates during most of this period. Projections presented different visions of the demographic future in the two countries. In France, publication of multiple variants emphasized future contingency, with low variants illustrating future population decline due to prolonged below‐replacement fertility. In Britain, publication of a single variant, assuming near‐replacement‐level fertility rates, projected moderate growth. National population projections thus created divergent representations of the two countries' demographic futures: an ever‐present threat of population decline in France, and a reassuring image of stability in Britain. Two principal mechanisms that contributed to cross‐national differences in population projections—national demographic history and institutional configurations—are discussed.     

Evaluating Population Forecast Accuracy: A Regression Approach Using County Data

Many studies have evaluated the impact of differences in population size and growth rate on population forecast accuracy. Virtually all these studies have been based on aggregate data; that is, they focused on average errors for places with particular size or growth rate characteristics. In this study, we take a different approach by investigating forecast accuracy using regression models based on data for individual places. Using decennial census data from 1900 to 2000 for 2,482 counties in the US, we construct a large number of county population forecasts and calculate forecast errors for 10- and 20-year horizons. Then, we develop and evaluate several alternative functional forms of regression models relating population size and growth rate to forecast accuracy; investigate the impact of adding several other explanatory variables; and estimate the relative contributions of each variable to the discriminatory power of the models. Our results confirm several findings reported in previous studies but uncover several new findings as well. We believe regression models based on data for individual places provide powerful but under-utilized tools for investigating the determinants of population forecast accuracy.