Alice Nakamura

A Comparison of the Labor Force Behavior of Married Women in the United States and Canada, with Special Attention to the Impact of Income Taxes

Estimation results are presented for the probability of working the hourly wage rate and the annual hours of work for wives in seven different age groups in both the U.S. and Canada. Federal and state or provincial taxes are incorporated into the analysis. An iterative estimation method is employed to circumvent the statistical problems resulting from the dependence of the hours of work on the tax rate and the dependence of the tax rate on the hours of work. (authors)

The econometrics of female labor supply and children

This is a survey of applied econometric research on the effects of children on female labor supply. Reasons for interest in the topic, and a basic model and terminology, are reviewed. Concerns are raised about the possible endogeneity of child status variables, and about the instrumental variables approach for dealing with this problem. Alternative ways of conceptualizing and estimating child status effects are considered, together with selected empirical evidence. Relevant developments from the household demand literature are summarized. Basic issues of model choice are also discussed.

Predicting Female Labor Supply: Effects of Children and Recent Work Experience

This study examines the empirical associations between female labor supply and child status and marital status using 1970 and 1980 U.S. census data and 1971 and 1981 Canadian census data. When the data are used in a purely cross-sectional manner, without controlling for previous labor supply, we find, as others have, that female labor supply is negatively related to the number of children a woman has had. However, this relationship changes when we condition on weeks of work in the previous year. This study makes use of longitudinal information in the Canadian and U.S. census data that has been largely ignored. The paper also explores certain econometric issues raised by the nature of the empirical results.

Index Number Concepts, Measures and Decompositions of Productivity Growth

This paper explores the definitions and properties of total factor productivity growth (TFPG) indexes, focusing especially on the Paasche, Laspeyres, Fisher, Törnqvist, and implicit Törnqvist ones. These indexes can be evaluated from observable price and quantity data, and certain of these are shown to be measures of TFPG concepts and theoretical indexes that have been proposed in the literature. The mathematical relationships between these and quantity aggregates, financial measures, and price and quantity indexes are explored. Decompositions of the productivity growth indexes are also given. The paper concludes with a brief overview of some limitations on our analysis.

Dynamic models of the labor force behavior of married women which can be estimated using limited amounts of past information

This paper examines the extent of the inadequacy of standard cross-sectional models of US labor force behavior and considers the abilities of alternative models to capture the observed continuity in the hours of work and earnings of individuals as well as in their employment histories. Both of the alternatives to the standard cross-sectional model considered in this study incorporate limited amounts of information about past work behavior that could easily be collected as part of a national population census. Using a population of 21 to 64 year old married working women taken from a 1969 through 1978 Michigan Panel Study of Income Dynamics, the variables included in the Z vector age: 1) age of the wife; 2) education of the wife; 3) state average hourly wage in manufacturing measured in 1967 dollars; and 4) unemployment rate for the state in which the wife lives. Results show that by using information about a womens hours of work and wage rate in the previous year, it may be feasible to improve on forecasts of a womans employment and earnings behavior. For each model a separate estimate is made for wives aged 21 through 46, and for those aged 47 through 64. The dummy and difference models perform much better than the standard model, with the dummy model having the higher pseudo-chi-square statistic. These models show that systematic errors made in determining which individuals work, what they earn per hour, or how many hours they work, should result in prediction errors of the same sort year after year in the computation of annual earnings. These findings with respect to years of work and nonwork, years of part time versus full time work, and cumulative earnings over a 10 year period, confirm and extend Heckmans findings; thus, forecasting models of the work behavior of individuals should not be estimated using pure cross-sectional data. It would be important if researchers could identify what observable factors, if any, increase the likelihood that wives will alter their work behavior from what it has been in the immediate past, even if they are not able to fully understand or explain this previous work behavior.

Model specification and endogeneity

This paper considers the treatment of endogenous explanatory variables in the work of the Cowles Commission and in Carl Christs classic 1966 textbook, and certain problems that arise when this approach is followed in areas such as the study of female labor supply where a prior knowledge is sparse or uncertain. The motivations for, and evidence against the use of, mixed estimation approaches involving exogeneity pretests are explored. The paper concludes with a consideration of complementary and alternative empirical approaches, including greater use of predictive evaluation as suggested by Christ.

Accounting for Housing in a CPI

Statistical agencies in different nations usually use the rental equivalence approach to the treatment of housing in their CPIs but a few countries use the user cost approach. The paper argues that an opportunity cost approach is the correct theoretical framework for accounting for OOH in a CPI. This approach, first mentioned in a 2006 OECD paper by Diewert, is developed more fully here. We explore the relationship of this new approach to the usual rental equivalency and user cost approaches. The new approach leads to an Owner Occupied Housing Opportunity Cost (OOHOC) index that is a weighted average of the rental and the financial opportunity costs.

On the performance of tests by Wu and by Hausman for detecting the ordinary least squares bias problem

We first consider the performance of the Wu (1973), Hausman (1978) (W-H) specification error test as a test for the existence of ordinary least squares (OLS) bias. We discuss power properties of the test under alternative null hypotheses, one of which has not previously been considered. We next consider how the W-H test performs as an indicator of the extent (rather than the existence) of an OLS bias problem, since this usage of the test seems common in applied studies. Finally Monte Carlo methods are used to evaluate Wus two-step estimation procedure involving the W-H test as a pretest.

Benchmarking and the measurement of the best practice efficiency: an electricity generation application

“While, for example, we look at the cost of power as a number of ‘analysed’ items such as coal, water-rate, ash removal, drivers’ and stokers’ wages, etc., it will probably be a long time before it dawns upon us that all this expenditure can be reduced to a horse-power-hour rate, and that such a factor, once known, may turn out to be a standing reproach. The burning of 200 tons of coal per week may mean anything or nothing, but the cost of a horse-power hour can be compared at once with standard data ... the publication of figures based on them would reveal amazing inefficiencies that under present conditions are unsuspected and unknown because no means of comparison exists.” A. Hamilton Church (1909, 190)

On the impact of the tests for serial correlation upon the test of significance for the regression coefficient

Monte Carlo methods are used to investigate the relationship between the power of different pretests for autocorrelation, and the Type I error and power of the significance test for a resulting two-stage estimate of the slope parameter in a simple regression. Our results suggest it may be preferable to always transform without pretesting. Moreover we find little room for improvement in the Type I errors and power of two-stage estimators using existing pretests for autocorrelation, compared with the results obtained given perfect knowledge about when to transform (i.e., given a perfect pretest). Rather, researchers should seek better estimators of the transformation parameter itself.