Has Income Segregation Really Increased? Bias and Bias Correction in Sample-Based Segregation Estimates

Several recent studies have concluded that residential segregation by income in the United States has increased in the decades since 1970, including a significant increase after 2000. Income segregation measures, however, are biased upward when based on sample data. This is a potential concern because the sampling rate of the American Community Survey (ACS)—from which post-2000 income segregation estimates are constructed—was lower than that of the earlier decennial censuses. Thus, the apparent increase in income segregation post-2000 may simply reflect larger upward bias in the estimates from the ACS, and the estimated trend may therefore be inaccurate. In this study, we first derive formulas describing the approximate sampling bias in two measures of segregation. Next, using Monte Carlo simulations, we show that the bias-corrected estimators eliminate virtually all of the bias in segregation estimates in most cases of practical interest, although the correction fails to eliminate bias in some cases when the population is unevenly distributed among geographic units and the average within-unit samples are very small. We then use the bias-corrected estimators to produce unbiased estimates of the trends in income segregation over the last four decades in large U.S. metropolitan areas. Using these corrected estimates, we replicate the central analyses in four prior studies on income segregation. We find that the primary conclusions from these studies remain unchanged, although the true increase in income segregation among families after 2000 was only half as large as that reported in earlier work. Despite this revision, our replications confirm that income segregation has increased sharply in recent decades among families with children and that income inequality is a strong and consistent predictor of income segregation.     

An Evaluation of Persons per Household (PPH) Estimates Generated by the American Community Survey: A Demographic Perspective

The American Community Survey (ACS) is a U.S. Census Bureau product designed to provide accurate and timely demographic and economic indicators on an annual basis for both large and small geographic areas within the United States. Operational plans call for ACS to serve not only as a substitute for the decennial census long-form, but as a means of providing annual data at the national, state, county, and subcounty levels. In addition to being highly ambitious, this approach represents a major change in how data are collected and interpreted. Two of the major questions facing the ACS are its functionality and usability. This paper explores the latter of these two questions by examining “persons per household (PPH),” a variable of high interest to demographers and others preparing regular post-censal population estimates. The data used in this exploration are taken from 18 of the counties that formed the set of 1999 ACS test sites. The examination proceeds by first comparing 1-year ACS PPH estimates to Census 2010 PPH values along with extrapolated estimates generated using a geometric model based on PPH change between the 1990 and 2000 census counts. Both sets of estimates are then compared to annual 2001–2009 PPH interpolated estimates generated by a geometric model based on PPH from the 2000 census to the 2010 census. The ACS PPH estimates represent what could be called the “statistical perspective” because variations in the estimates of specific variables over time and space are viewed largely by statisticians with an eye toward sample error. The model-based PPH estimates represent a “demographic perspective” because PPH estimates are largely viewed by demographers as varying systematically and changing relatively slowly over time, an orientation stemming from theory and empirical evidence that PPH estimates respond to demographic and related determinants. The comparisons suggest that the ACS PPH estimates exhibit too much “noisy” variation for a given area over time to be usable by demographers and others preparing post-censal population estimates. These findings should be confirmed through further analysis and suggestions are provided for the directions this research could take. We conclude by noting that the statistical and demographic perspectives are not incompatible and that one of the aims of our paper is to encourage the U.S. Census Bureau to consider ways to improve the usability of the 1-year ACS PPH estimates.     

Sun Belt Rising: Regional Population Change and the Decline in Black Residential Segregation, 1970–2009

The goal of this study is to examine the extent to which population shifts over the post–Great Migration period and divergent trends in segregation across regions contributed to the overall decline in black segregation in the United States in recent decades. Using data from the 1970 to 2000 decennial censuses and the 2005–2009 American Community Survey (ACS), our analysis indicates that black dissimilarity and isolation declined more in the South and West than in the Northeast and Midwest. Nevertheless, regional population shifts account for only a modest amount (8 % to 12 %) of the decline in black-white segregation over the period and for an even smaller proportion of the decline in black-nonblack segregation, in part because the largest declines in segregation occurred in the West while the region with the largest relative increase in the black population was the South. Using more refined census divisions rather than census regions provided some additional explanatory power (shifts across divisions explained 15 %–16 % of the decline in black-white segregation): divisions with larger gains in their share of the black population tended to have larger declines in black segregation. Overall, although the effect of the regional redistribution of the black population on declines in segregation was significant, of even greater importance were other causes of substantial declines in segregation in a wide array of metropolitan areas across the country, and especially in the West, over the past 40 years.     

White Residential Segregation in U.S. Metropolitan Areas: Conceptual Issues, Patterns, and Trends from the U.S. Census, 1980 to 2010

Racial and ethnic diversity continues to spread to communities across the United States. Rather than focus on the residential patterns of specific minority or immigrant groups, this study examines changing patterns of White residential segregation in metropolitan America. Using data from the 1980 to 2010 decennial censuses, we calculate levels of White segregation using two common measures, analyze the effect of defining the White population in different ways, and, drawing upon the group threat theoretical perspective, we examine the metropolitan correlates of White segregation. We find that White segregation from others declined significantly from 1980 to 2010, regardless of the measure of segregation or the White population used. However, we find some evidence consistent with the group threat perspective, as White dissimilarity is higher in metro areas that are more diverse, and especially those with larger Black populations. Nevertheless, our findings indicate that Whites having been living in increasingly integrated neighborhoods over the last few decades, suggesting some easing of the historical color line.     

An Application of Bayesian Methods to Small Area Poverty Rate Estimates

Efforts to estimate various sociodemographic variables in small geographic areas are proving difficult with the replacement of the Census long-form with the American Community Survey (ACS). Researchers interested in subnational demographic processes have previously relied on Census 2000 long-form data products in order to answer research questions. ACS data products promise to begin providing up-to-date profiles of the nation’s population and economy; however, unit- and item-level nonresponse in the ACS have left researchers with gaps in subnational coverage resulting in unstable and unreliable estimates for basic demographic measures. Borrowing information from neighboring areas and across time with a spatiotemporal smoothing process based on Bayesian statistical methods, it is possible to generate more stable and accurate estimates of rates for geographic areas not represented in the ACS. This research evaluates this spatiotemporal smoothing process in its ability to derive estimates of poverty rates at the county level for the contiguous United States. These estimates are then compared to more traditional estimates produced by the US Census Bureau, and comparisons between the two methods of estimation are carried out to evaluate the practical application of this smoothing method. Our findings suggest that by using available data from the ACS only, we are able to recreate temporal and spatial patterns of poverty in US counties even in years where data are sparse. Results show that the Bayesian methodology strongly agrees with the estimates produced by the SAIPE program, even in years with little data. This methodology can be expanded to other demographic and socioeconomic data with ease.     

New midyear age-sex-color-specific estimates of the U.S. population for the 1940s and 1950s: including a revision of coverage estimates for the 1940 and 1950 censuses

This paper describes new midyear (July 1) estimates of the "true" population of the United States by age, sex, and color (white, nonwhite) for the 1940s and 1950s. It also presents the corresponding implied coverage estimates for the 1940 and 1950 censuses. The new population estimates are calculated by combining the most recent figures on the 1960 population with estimates of the demographic components of change for the 1950s and 1940s in an iterative reverse cohort-component projection algorithm. Among the principal findings of the new estimates are: (a) existing midyear estimates of the "true" population in the 1950s are 450,000 to 500,000 too high; (b) existing age-specific estimates for the 1950s tend to underestimate the population at the older ages (55 years and over) and overestimate the population in the young and middle adult years (15 to 54 years); (c) estimates of the "true" population in the 1940s were too low except for nonwhites at ages 65 and over; (d) existing estimates of percentage net undercount and underenumeration for the 1950 and 1940 censuses tend to be too high, substantially so for nonwhites in the 1940 Census; and (e) nonwhites were more completely enumerated in 1940 than in 1950. Thus, in addition to being methodologically and temporally consistent with post-1960 estimates, the new population estimates described here imply some substantial revisions in demographic, social, and economic statistics for the two decades prior to 1960.     

Development of birth registration and birth statistics in the United States

The registration of vital events in the United States has always been under the authority of State and local areas. The preparation of national birth statistics has been made possible through a co-operative working arrangement between the Federal Government and the States. This paper traces the development of registration systems in the United States from colonial days to the present period. The absence of adequate registration systems throughout the country, during the nineteenth century, led to the use of data collected in the decennial population censuses of 1850–1900 for estimating birth rates. This procedure was abandoned because of the unreliability of the results. Steps leading to the formation of the national birth-registration area in 1915, when it included ten States and the District of Columbia, and. activities resulting in its completion in 1933 are discussed.

A major portion of the paper outlines the nation-wide test of birth-registration completeness conducted in 1940 in conjunction with the decennial census of population. Important results of the test are presented, and the methodology is explained. A similar test is being carried out in 1950. Data derived will be used to focus attention on local areas requiring registration promotion. Correction factors for statistical series based on registered events will also be obtained. The final section of the paper indicates the steps States are taking to improve quality of reporting on the birth record. Changes in the content of the standard certificate of live birth since 1915 are summarized and the statistics tabulated from birth certificates detailed.     

Fertility of the american negro in 1830 and 1850

Abstract A comparison of the proportionate age distributions for negroes enumerated in the decennial censuses of the United States in the first half of the rorh century indicates that by 1850, negro fertility apparently had been declining for at least 20 years. This paper develops the relationship of the age distribution of a declining fertility population, where the decline has persisted for less than 25 years, to the stable population with the same current schedules of fertility and mortality. This relationship is used to estimate the negro birth rate and total fertility as of 1850. In turn, these estimates and the relationship of the age distributions of two stable populations with different fertility are used to estimate the negro birth rate and total fertility as of 1830.     

Mexico–US Migration: Views from Both Sides of the Border

Migration to the United States increased sharply in the 1980s and 1990s, raising political concerns. The immigrant flow from Mexico, both authorized and unauthorized, was particularly large. Good data would con‐tribute to rational discussion of this politically charged issue, but data on immigration, particularly of the unauthorized, are notoriously poor. This article applies residual estimation techniques to data from the 1990 and 2000 population censuses of Mexico and the United States (Mexico‐born population) to quantify the intercensal migration flow, arguing that the reasons why unauthorized migrants might avoid enumeration in the United States would not adversely affect data from Mexico. Results suggest that the annual net flow of migrants aged 10 to 80 years from Mexico to the United States averaged between 324,000 and 440,000 between 1990 and 2000. A sensitivity analysis indicates that these results are quite robust (especially those using US data) to likely 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.     

The American Community Survey in counties with “seasonal” populations

The U.S. Census Bureau designed the American Community Survey (ACS) to provide annual estimates of social and economic characteristics for states, counties, municipalities, census tracts, and block groups. Because of its April 1 reference date, in northern nonmetropolitan counties with substantial seasonal population fluctuations the decennial census provides a statistical representation of the demographic and social characteristics of the population at a time when the population is close to its annual minimum. The year-round monthly ACS sample survey has the potential to provide local communities with an unprecedented understanding of the average population characteristics over the course of a year. In the future, the ACS even has the potential for providing social and economic characteristics of the population by season. This paper examines four ACS pilot data collection counties, Oneida and Vilas Counties in northern Wisconsin, and Lake and Flathead Counties in northwest Montana. We hypothesize that the ACS will reflect a resident population over the course of the year that is different from the traditional April 1 decennial census population. While the ACS holds much promise, our research uncovered some sampling problems that are not yet fully resolved. In addition, our analysis was not able to examine ACS estimates for minor civil divisions (MCDs), which are functioning governmental units in many states. The fact that these MCDs often have very small populations, together with the fact that estimated standard errors at the much larger census tract level in these counties are disconcertingly large, raises (currently unanswerable) questions concerning the eventual statistical quality of ACS estimates for small MCDs. Consequently, the adequacy of the ACS as a replacement for the census long form may depend on the ability of the Census Bureau to effectively address the concerns presented in this analysis.     

The role of population size in the determination and prediction of population forecast errors: An evaluation using conifidence intervals for subcounty areas

Producers of population forecasts acknowledge the uncertainty inherent in trying to predict the future and should warn about the likely error of their forecasts. Confidence intervals represent one way of quantifying population forecast error. Most of the work in this area relates to national forecasts; although, confidence intervals have been developed for state and county forecasts. A few studies have examined subcounty forecast error, however, they only measured point estimates of error. This paper describes a technique for making subcounty population forecasts and for generating confidence intervals around their forecast error. It also develops statistical equations for calculating point estimates and confidence intervals for areas with different population sizes. A non-linear, inverse relationship between population size and forecast accuracy was found and we demonstrate the ability to accurately predict average forecast error and confidence intervals based on this relationship.     

Estimating the approximate size of the illegal alien population in the united states by the comparative trend analysis of age-specific death rates

This paper presents the results of an attempt to determine, through the use of demographic analysis, the approximate magnitude of the resident illegal alien population in the United States. The method described is the comparative analysis of trends in age-specific death rates in the United States and selected States, 1950 to 1975. The procedure depends on two assumptions: (a) that few or no illegal aliens are included in decennial census counts or current population estimates; and (b) that the reported statistics on deaths include deaths to all or nearly all illegal aliens. If the illegal alien population has increased by several million since 1970, then death rates in geographic areas where illegal aliens are most concentrated should show substantial excesses over the rates for the remainder of the country. A roughly similar downward trend in the death rates of all age groups since 1970 in all areas of the United States is apparent and hence does not support the view that many millions of illegal residents (perhaps over 6 million) are living here. However, the finding of a persistent deviation in the death rate trend for 10 selected States since 1960 for whites males, ages 20 to 44, and for no other group, suggests that the deaths of illegal aliens are being recorded in our vital statistics system. A range of estimates of the illegal alien population based on this analysis is presented and compared with the results of other studies.     

Shifting racial hierarchies: An analysis of residential segregation among multi-racial and mono-racial groups in the United States

Multi-racial (mixed-race) people constitute a growing percentage of the United States (US) population. The study reported in this paper used residential segregation measures as a proxy for social distance, to examine whether segregation levels of multi-racial groups differ from those of mono-racial groups in the US in 2010. First, we find that all multi-racial groups considered in the study experience lower levels of segregation at county level than their mono-racial counterparts. However, black-whites and Hispanic-whites experience higher levels of segregation than other multi-racial groups. Second, we find region and minority composition of counties are associated significantly with segregation levels for multi-racial groups, but relative income is not.     

Residential segregation in urbanized areas of the United States in 1970: An analysis of social class and racial differences

Sociologists and urban commentators often portray metropolitan areas as highly segregated by social class and race. We measured the extent of socioeconomic residential segregation in urbanized areas of the United States in 1970, determined whether cities were as segregated as suburban rings, and compared levels of socioeconomic and racial residential segregation. We found moderate levels of residential segregation of socioeconomic groups. Levels of social class segregation varied little from one urbanized area to another and were about the same in central cities and suburban rings. Racial residential segregation was much greater than the segregation of social classes within either the black or white communities. The extent of racial residential segregation does not vary by educational attainment, occupation, or income.     

Segregation and diversity measures in population distribution

"The purposes of the present paper are to show the relationship between measures of population diversity and measures of segregation, to describe the salient properties of these indexes, and to demonstrate the empirical interrelationships among them." Some measures not frequently used in population studies are considered, and empirical illustrations are given of the significance of using one measure rather than another. In particular, the author stresses proportional reduction of error interpretations for an index and considers its ability to handle more than two groups. The primary geographic focus is on the United States. The "introductory section of the paper treats conceptual issues in more detail. The second section reviews selected measures and recent critical viewpoints, while the third section tests their empirical performance. The conclusion makes some recommendations about the selection of an index. A detailed bibliography follows."     

The number of Israeli immigrants in the United States in 1990

In this paper we estimate the size of several categories of “Israeli” immigrants in the United States. According to the 1990 U.S. census, there were about 95,000 Israeli-born immigrants in the United States in that year. Using the language and ancestry information available in the Public Use Microdata Sample (PUMS) of the 1990 census, we estimate that of this total, about 80,000 are Jews and 15,000 are Palestinian Arabs born in Israel. In addition to the Israeli-born, we present a range for the number of Jewish immigrants from Israel who are not Israeli-born (about 30,000-56,000). Thus our estimate for the total number of Jewish immigrants from Israel in the United States in 1990 is between 110,000 and 135,000. Fertility information available in the PUMS, also enable us to provide estimates for the number of second-generation Israelis in the United States in the 1990 (about 42,000). Finally, using both the 1980 and 1990 PUMS, we provide estimates for the rate of return migration among Israeli-born Jewish immigrants in the United States.     

Making the Housing Unit Method Work: An Evaluation of 2010 Population Estimates in Florida

The housing unit (HU) method—in which population estimates are derived from estimates of occupied HUs—is the most commonly used method for making small-area population estimates in the United States. It is widely used because it is conceptually simple, can utilize a wide variety of data sources, can be applied at virtually any level of geography, and often produces reliable estimates. Yet the HU method is more nearly a general approach to population estimation than it is a specific methodology. In this paper, we describe and evaluate several data sources and estimation techniques that can be used in applying the HU method. Using a set of county and subcounty estimates produced by the Bureau of Economic and Business Research (BEBR) at the University of Florida for April 1, 2010, we analyze errors by population size and growth rate, calculate errors for each of the three components of the HU method, and investigate the accuracy of estimates based on several different data sources and estimation techniques. We compare the accuracy of the 2010 estimates with previous BEBR estimates and estimates produced by the U.S. Census Bureau. We conclude that although some data sources and estimation techniques work better than others, the HU method can be tailored to produce reliable population estimates for a wide variety of geographic areas.     

Residential segregation of Spanish Americans in united states Urbanized Areas

Residential segregation among Spanish Americans, whites and blacks is measured in the 29 largest U.S. urbanized areas. Results show that Spanish Americans are much less segregated from whites than are blacks and are less concentrated within central cities. Spanish-white segregation also tends to be much lower in suburbs than in central cities, while back-white segregation is maintained at a high level in both areas. Segregation of Spanish Americans from whites is found to decline with generations spent in the United States. Finally, the relative proportion of Spanish who live in a central city and the relative number of Spanish who are foreign stock, are both highly related, across urbanized areas, to variations in the level of Spanish-white segregation.