US Consumer Expenditure Survey Research Articles

Regression with an imputed dependent variable

SummaryResearchers are often interested in the relationship between two variables, with no single data set containing both. A common strategy is to use proxies for the dependent variable that are common to two surveys to impute the dependent variable into the data set containing the independent variable. We show that commonly employed regression or matching‐based imputation procedures lead to inconsistent estimates. We offer a consistent and easily implemented two‐step estimator, “rescaled regression prediction.” We derive the correct asymptotic standard errors for this estimator and demonstrate its relationship to alternative approaches. We illustrate with empirical examples using data from the US Consumer Expenditure Survey (CE) and the Panel Study of Income Dynamics (PSID).

Building a Consumption Poverty Measure: Initial Results Following Recommendations of a Federal Interagency Working Group

Consumption is a well-being measure that is determined by a combination of resources (e.g., income, in-kind benefits, assets, debt, time) available to households, their circumstances, and their preferences. In this study, we derive consumption poverty statistics using a consumption measure that includes the flow of services from owner-occupied housing and vehicles and in-kind transfers. The base data are from the US Consumer Expenditure Survey Interview from 2015 through 2020. The consumption poverty rate (using an absolute threshold anchored to the 2015 relative consumption poverty rate) declines from 16.8 percent in 2015 to 11.5 percent in 2020.

Underreporting of Purchases in the US Consumer Expenditure Survey

Abstract Motivated misreporting occurs when respondents give incorrect responses to survey questions to shorten the interview; studies have detected this behavior across many modes, topics, and countries. This paper tests whether motivated misreporting affects responses in a large survey of household purchases, the US Consumer Expenditure Interview Survey. The data from this survey inform the calculation of the official measure of inflation, among other uses. Using a parallel web survey and multiple imputation, this article estimates the size of the misreporting effect without experimentally manipulating questions in the survey itself. Results suggest that household purchases are underreported by approximately five percentage points in three sections of the first wave of the survey. The approach used here, involving a web survey built to mimic the expenditure survey, could be applied in other large surveys where budget or logistical constraints prevent experimentation.

Household carbon inequality in the U.S.

Household carbon emissions are mainly affected by income and other key demographic factors. Understanding the contribution of these factors can inform climate responsibilities and potential demand-side climate mitigation strategies. By linking US consumer expenditure survey data with a nested national within a global multi-regional input-output model, this study estimates consumption-based GHG emissions for 9 income groups and assesses the carbon inequality in the US for 2015. Our results show that the per capita carbon footprint (CF) of the highest income group (>200 thousand USD per year) with 32.3 tons is about 2.6 times the per capita CF of the lowest income group (<15 thousand USD) with 12.3 tons. This is due to large gap in consumption volume and associated carbon emissions along the entire global production chain. Consumption pattern tends to narrow the gap in household per capita CF between income groups due to the lower carbon intensity per dollar spent by higher income groups. Another important factor influencing carbon footprints is household size and thus sharing of household equipment and other consumption items. The US average per capita CF is 18.1 tons compared to the global average of approximately 5 tons. The high carbon footprint across income groups in the US is largely due to the large contribution of emissions from heating and cooling and private transport, which reflects the settlement structure and lifestyles in the US, relying heavily on cars and living in larger houses.

Does the "missing" high-income matter? -Income distribution and inequality revisited with truncated distribution

The issue of missing high-income data in household surveys has been a constant concern among researchers and practitioners when drawing inferences on inequality measures, discussing the relationship between poverty and growth, and examining the relationship between expenditure and income. We introduce a truncated distribution technique to correct the potential bias caused by the missing high-income data. Using 2002/2007/2013 Chinese Household Income Project Survey data and the 2002/2007/2014 US Consumer Expenditure Survey data, we test and estimate three commonly used income distributions: lognormal, Singh Maddala, and Beta II distribution with/without the truncation assumption. We find that the truncated Beta II distribution best describes income distribution in China, while the truncated Singh Maddala best fits the income in the US. The missing high-income in China has a significant but small effect on the Gini and Theil coefficients for 2007, whereas the missing high-income in the US has significant effects for 2007 and 2014. The Gini coefficient increases from the sample mean 0.44 to the simulation mean of truncated Beta II distribution as 0.47 for China in 2007 and increases from the sample mean 0.4422/0.4485 to the simulated mean of truncated Singh Maddala distribution 0.4506/0.4588 for 2007 and 2014 respectively. We also check the impact of missing low-income individuals on inequality assessment and find that the missing low-income data does not appear to underestimate inequality.

The signaling effect of gasoline taxes and its distributional implications

This paper proposes and tests a better-defined interpretation of the different responses of gasoline demand to tax changes and to market-related price changes. Namely, the signaling effect of gasoline taxes is one that impacts on long-run consumer decisions in addition to the incentives provided by tax-inclusive gasoline prices. Our hypothesis is tested using a complete demand system augmented with information on gasoline taxes and fitted to household-level data from the 2006 to 2013 rounds of the US Consumer Expenditure survey. Information on gasoline taxes is found to be a significant determinant of household demand additional to tax-inclusive gasoline prices. The equity implications are examined by contrasting the incidence across income distribution of a simulated $0.22/gallon tax increase to that of a market-related price increase equal in size. The tax increase is clearly regressive, slightly more than the market-related price increase. However, regressivity is by no means a reason to give up gasoline taxes as an instrument for reducing gasoline consumption externalities. Their high effectiveness in reducing gasoline demand implies that small tax increases can substantially improve the environment while minimizing the related distributional effects. Also, gasoline taxes generate revenue that can be used to offset their regressivity.

Bubble Treemaps for Uncertainty Visualization.

We present a novel type of circular treemap, where we intentionally allocate extra space for additional visual variables. With this extended visual design space, we encode hierarchically structured data along with their uncertainties in a combined diagram. We introduce a hierarchical and force-based circle-packing algorithm to compute Bubble Treemaps, where each node is visualized using nested contour arcs. Bubble Treemaps do not require any color or shading, which offers additional design choices. We explore uncertainty visualization as an application of our treemaps using standard error and Monte Carlo-based statistical models. To this end, we discuss how uncertainty propagates within hierarchies. Furthermore, we show the effectiveness of our visualization using three different examples: the package structure of Flare, the S&P 500 index, and the US consumer expenditure survey.

The Signaling Effect of Gasoline Taxes and Its Distributional Implications

This paper proposes and tests a better defined interpretation of the different responses of gasoline demand to tax changes and to market-related price changes. Namely, the signaling effect of gasoline taxes is one that impacts on long-run consumer decisions in addition to the incentives provided by tax-inclusive gasoline prices. Our hypothesis is tested using a complete demand system augmented with information on gasoline taxes and fitted to household-level data from the 2006 to 2013 rounds of the US Consumer Expenditure survey. Information on gasoline taxes is found to be a significant determinant of household demand additional to tax-inclusive gasoline prices. The equity implications are examined by contrasting the incidence across income distribution of a simulated $0.22/gallon tax increase to that of a market-related price increase equal in size. The tax increase is clearly regressive, slightly more than the market-related price increase. However, regressivity is by no means a reason to give up gasoline taxes as an instrument for reducing gasoline consumption externalities. Their high effectiveness in reducing gasoline demand implies that small tax increases can substantially improve the environment while minimizing the related distributional effects. Also, gasoline taxes generate revenue that can be used to offset their regressivity.

Are Unobservables Separable?

It is common to assume in empirical research that observables and unobservables are additively separable, especially, when the former are endogenous. This is done because it is widely recognized that identification and estimation challenges arise when interactions between the two are allowed for. Starting from a nonseparable IV model, where the instrumental variable is independent of unobservables, we develop a novel nonparametric test of separability of unobservables. The large-sample distribution of the test statistics is nonstandard and relies on a novel Donsker-type central limit theorem for the empirical distribution of nonparametric IV residuals. Using a dataset drawn from the 2015 US Consumer Expenditure Survey, we find that the test rejects the separability in Engel curves for most of the commodities.

Is consumption risk priced in the stock market?

Abstract The paper examines whether the risk in the consumption of stockholders caused by incomplete consumption insurance is priced in the cross-section of average stock returns. Using Taylor series expansion of the average marginal utility of consumption, we show that the risk in the consumption of stock market participants can be decomposed into two components, insurable (hedgeable using financial assets) and uninsurable (caused by incomplete consumption insurance) consumption risks. We argue that the growth rate of average consumption may be viewed as a proxy for the insurable component of consumption risk, while the growth rates of the rescaled higher-order cross-sectional consumption distribution moments may be regarded as a multivariate proxy for uninsurable risk in consumption. Exploiting microlevel household quarterly consumption data from the US Consumer Expenditure Survey, we find that both components of consumption risk are significantly priced when the limited stock market participation is taken into account. Neither the insurable and uninsurable components of consumption risk nor the Fama–French risk factors are rejected as capturing important components of systematic risk when tested against each other in an integrated multifactor asset pricing model.

Are women more generous than men? Evidence from the US Consumer Expenditure Survey

This paper examines how gender, age, education, income, race, and ethnicity affect giving behaviors using the 2006 US Consumer Expenditure Survey. The testable hypotheses are based on theories of human capital and social capital. The research suggests that gender differences in philanthropic behavior are non-existent. Education, annual income, wealth, and being Hispanic increase the probability of giving, but they had no effect on the amount gifted. It is estimated that age and race interact with gender to affect differences in giving – older women are more likely than younger men to donate but give smaller shares of their income, while white women, black women, and Asian women are less likely to donate and give smaller amounts than men of ‘other’ races.

Accommodating multiple constraints in the multiple discrete–continuous extreme value (MDCEV) choice model

Multiple-discrete continuous choice models formulated and applied in recent years consider a single linear resource constraint, which, when combined with consumer preferences, determines the optimal consumption point. However, in reality, consumers face multiple resource constraints such as those associated with time, money, and capacity. Ignoring such multiple constraints and instead using a single constraint can, and in general will, lead to poor data fit and inconsistent preference estimation, which can then have a serious negative downstream effect on forecasting and welfare/policy analysis.In this paper, we extend the multiple-discrete continuous extreme value (MDCEV) model to accommodate multiple constraints. The formulation uses a flexible and general utility function form, and is applicable to the case of complete demand systems as well as incomplete demand systems. The proposed MC-MDCEV model is applied to time-use decisions, where individuals are assumed to maximize their utility from time-use in one or more activities subject to monetary and time availability constraints. The sample for the empirical exercise is generated by combining time-use information from the 2008 American Time Use Survey and expenditure records from the 2008 US Consumer Expenditure Survey. The estimation results show that preferences can get severely mis-estimated, and the data fit can degrade substantially, when only a subset of active resource constraints is used.

Abatement cost functions for incentive-based policies in the automobile market

This paper compares the outcomes of policies that target vehicle holdings with those that target vehicle usage using data from the US Consumer Expenditure Survey. Results show that a higher price of gasoline shifts vehicle holdings towards more fuel efficient vehicles and reduces the annual demand for miles, whereas imposing a fee on vehicles or a feebate program only shifts vehicle holdings towards more fuel efficient vehicles and has little to no impact on the demand for miles. While it is relatively expensive to reduce CO 2 emission through incentive-based policies, achieving any abatement level is more expensive through imposing fees on vehicles than gasoline taxes. In addition, the maximum amount of abatement attainable by a feebate program is relatively small and the same amount could be achieved by imposing a $0.73 gasoline tax per gallon.

Role of ethnicity in consumption of meat products

Previous studies on the demand for meat products have not received much attention on the role of ethnicity on consumption. Using data from the US Consumer Expenditure Survey (CES) and LinQuad demand systems, this study investigates the impact of ethnicity on the demand for meat products in the United States. Results indicate that ethnicity plays a significant role in the consumption of meat products. Specifically, results show that, compared to Hispanics, African American households consume significantly more bacon, pork chops and chicken meats. In general, White households consume lower quantities of meat products, compared to Hispanics, specifically chicken and seafood products.

Personal tradable carbon permits for road transport: Why, why not and who wins?

Personal road transport sector poses a significant challenge in reducing carbon emissions. This paper evaluates a policy approach known as personal tradable carbon permits to reduce carbon emissions from personal vehicles. The policy is a downstream tradable permit where individuals are allocated carbon emission caps. The policy is qualitatively evaluated in the context of carbon taxes and some upstream tradable permit options. The biggest disadvantage of such a policy is the initial set up costs. Personal tradable permits, however, are more effective than carbon taxes and are also capable of stabilizing the gasoline prices faced by the consumers when the underlying oil prices fluctuate. Since equity effects are often a concern to policy makers, the effect of such personal carbon permits on the distribution of burden is quantified in a partial equilibrium framework for the US population. Different permit allocation strategies are investigated in this regard. Using US consumer expenditure survey data, and incorporating a differentiated price response for different households, we find that all three allocation strategies considered are progressive: a per adult based allocation is the most progressive, a per vehicle allocation nearer to proportional, and a per capita allocation in between the two. Personal tradable permits therefore take care of equity concerns directly through the design of the policy.

Intertemporal consumption choices, transaction costs and limited participation in financial markets: reconciling data and theory

This paper builds a unifying framework that, within the theory of intertemporal consumption choices, brings together the limited participation -based explanation of the poor empirical performance of the C-CAPM and the transaction costs-based explanation of incomplete portfolios. Using the implications of the consumption model and observed household consumption and portfolio choices, we identify the preference parameters of interest and a lower bound for the costs rationalizing non-participation in financial markets, in the presence of unobserved heterogeneity in tastes for consumption and portfolio allocation. Using the US Consumer Expenditure Survey and assuming isoelastic preferences, we estimate the coefficient of relative risk aversion at 1.7 and a cost bound of 0.4 percent of non-durable consumption. Our estimate of the preference parameter is theoretically plausible and the bound sufficiently small to be likely to be exceeded by the actual total (observable and unobservable) costs of participating to financial markets.

Reconciling user costs and rental equivalence: Evidence from the US consumer expenditure survey

Previous research [Verbrugge, Randal, 2008a. The puzzling divergence of aggregate rents and user costs, 1980–2004. The Review of Income and Wealth 54(4), 671–699] demonstrated that housing rents and ex ante user costs diverge markedly for extended periods of time, a finding with profound implications for income and inflation measurement. But the primary data sources in that study were various indexes, based upon largely disjoint data sources, constructed using different aggregation techniques, and each subject to various criticisms. This raised doubts about the quality of the comparison. The relationship between user costs and rents might well be much tighter at the micro level; after all, house prices and rents (and their growth rates) can vary dramatically within cities, and rents are notoriously sticky. Furthermore, the use of indexes precludes both cross-sectional and dollar cost comparisons. In this study, we use Consumer Expenditure Interview Survey (CE) data to examine the relationship between user costs and rents at the individual unit-level, in dollars, using unit-level information on house value, rent, taxes, and the like. This allows us to accurately estimate unit-specific user costs and to control for unobservables like structure and neighborhood quality. We also make the point that in theory, after-tax user costs should equal net rent, i.e., expected rental income, rather than gross rent. Our findings are striking. In keeping with most previous research, we find tremendous divergence between conventional measures of user costs and net rents, thus ruling out index construction errors as a possible explanation. This divergence does not result from a faulty rent measure: we find that reported rents are sensible, in that they move similarly to official rent indexes, and are not simply out-of-pocket expenses. Instead, and most perplexing, we find a surprisingly close correspondence between net rents and a particular estimate of user costs, one implicitly assuming zero transactions costs and constructed using an appreciation measure that is both theoretically suspect and empirically a poor predictor of actual appreciation.

Equity analysis of personal tradable carbon permits for the road transport sector

The personal road transport sector is one of the largest and fastest growing sources of CO2 emissions. This paper investigates a tradable permit policy for mitigating carbon emissions from personal road transport and discusses various issues of permit allocation. As tradable permits will effectively raise the price of fuel, the policy has important distributional implications. The distribution of burden depends on permit allocation strategies and on the consumer response to an increase in price. The behavioural response varies among different segments of the population depending on their travel needs, which in turn are contingent upon their income, location of residence and other factors. A model previously estimated by [Wadud, Z., Graham, D.J., Noland, R.B., 2007. Modelling gasoline demand for different socio-economic groups. In: Proceedings of the 86th Annual Meeting of the Transportation Research Board, Washington, DC, USA, January 2007] with group-wise aggregated US consumer expenditure survey data for 20 years provides behavioural responses for different income groups. The resulting welfare distribution in the USA is evaluated in this paper. Different permit allocation schemes are also considered in the analysis.

Estimation of the consumption CAPM with imperfect sample separation information

AbstractWe propose a consumption‐based capital asset pricing model consumption (CAPM), in which the pricing kernel is calculated as the average of individuals' intertemporal marginal rates of substitution weighted by the probabilities of holding the asset in question. These probabilities are conditional on available imperfect sample separation information and are estimated simultaneously with the parameters of Euler equations. Using data from the US Consumer Expenditure Survey, we find that the consumption CAPM with probability‐weighted agents yields a more precise estimate of the agent's risk aversion compared with the model, in which the available imperfect information on asset‐holding status is erroneously regarded as a perfect sample separation indicator. Copyright © 2007 John Wiley &amp; Sons, Ltd.

An alternative semiparametric estimate of the base-independence equivalence scale: an application to US consumer expenditure survey data

This study proposes a semiparametric estimate and a test for base-independence equivalence scale. Our semiparametric approach is based on nondensity weighted loss function in contrast to Pendakur's (1999) density weighted loss function. Simulation results indicate that our specification tends to produce a smaller bias in estimating the equivalence scale and thus a more reliable test for base-independence hypothesis. We also provide an application using US Consumer Expenditure Survey data.