Showing papers by "National Bureau of Economic Research published in 1973"

Wage Comparisons -A Selectivity Bias

Abstract: The economics of information have been established by now as an integral part of economic analysis. However, surprisingly little has been written on the implications of search (and in particular, job search) for the estimation of the wage function and its ramifications in such cases as the estimation of the determinants of labor force participation, age-earning profiles, rates of return and rates of depreciation of human capital, degree of discrimination, etc. Given a wage offer distribution, the parameters of the observed wage distribution depend on the intensity of search. The lower a personâ€TMs wage demands the greater the chance of his finding an acceptable job, but the lower the wage he expects to receive and the wider the dispersion of acceptable wages around their mean. On the other hand, the job seeker may opt for a more ambitious search strategy, raising his minimum wage demand and consequently increasing the risk of remaining unemployed, but also increasing the expected wage and decreasing the dispersion of available offers. Models of wage offer distribution have traditionally been based on empirical observation of observed wage distribution. This approach may involve certain biases when applied to secondary labor groups â€" married women, teenagers and the aged. This paper attempts to point out some of these biases and suggests a method for their correction.

The Correlation between Health and Schooling

Abstract: This paper has two purposes. The first is to develop a methodological framework that can be used to introduce and discuss alternative explanations of the correlation between health and schooling. The second is to test these explanations empirically in order to select the most relevant ones and obtain quantitative estimates of different effects. The empirical work is limited to one rather unique body of data and uses two measures of health that are far from ideal. The methodological framework can, however, serve as a point of departure for future research when longitudinal samples with more refined measures of current and past health and background characteristics become available.

Contraception and Fertility: Household Production under Uncertainty

Abstract: Over the past century fertility behavior in the United Stated has undergone profound changes Measured by cohort fertility the average number of children per married woman had declined from about 5.5 children at the time of the Civil War to 2.4 children at the time of the Great Depression. It is seldom emphasized however that an even greater relative change took place in the dispersion of fertility among these women: the percentage of women with, say, seven or more children declined from 36% to under 6%. While students of population have offered reasonably convincing explanations for the decline in fertility over time, they have not succeeded in explaining the fluctuations in the trend and have made surprisingly little effort to explain the large and systematic decline in the dispersion of fertility over time. In this paper we attempt to study contraception behavior and its effects on fertility. One of the effects on which we focus considerable attention is the dispersion or variance in fertility. Our analysis is applied to cross-sectional data but it also provides an explanation for the decline in the variance in fertility over time.

The Definition and Impact of College Quality

Abstract: In this paper we are concerned with the characteristics of colleges which serve to increase subsequent monetary incomes of those who attend. Usually, lifetime earnings are explained by variables such as innate ability, experience in the labor force and years of education, although other socio-economic, demographic and occupational data can be inserted to increase the explanatory power of the model. This paper attempts to add a new dimension to the earnings function analysis by hypothesizing the features of colleges which might yield financial payoffs later in life, and then testing to see which of these traits actually do add most to the explanatory power of the traditional earnings function.

Weighted Ridge Regression: Combining Ridge and Robust Regression Methods

Abstract: This paper gives the formulas for and derivation of ridge regression methods when there are weights associated with each observation. A Bayesian motivation is used and various choices of k are discussed. A suggestion is made as to how to combine ridge regression with robust regression methods.

The Covariance Structure of Earnings and the on the Job Training Hypothesis

Abstract: The fine structure of earnings is defined by a theoretically meaningful decomposition of the covariance matrix of earnings (or log earnings) time series. A three-element variance components model is proposed for analyzing earnings of young workers. These components are interpreted as the effects of differential on-the-job training (OJT) and differential economic ability. Several properties of these components and relationships between them are deduced from the OJT model. Background noise generated by a nonstationary first-order autoregressive process, with heteroscedastic innovations and time-varying AR parameters is also assumed present in observed earnings. ML estimates are obtained for all parameters of the model for a sample of Swedish males. The results are consistent with the view that the OJT mechanism is an empirically significant phenomenon in determining individual earnings profiles.

Computational experience with a group theoretic integer programming algorithm

Abstract: This paper gives specific computational details and experience with a group theoretic integer programming algorithm. Included among the subroutines are a matrix reduction scheme for obtaining group representations, network algorithms for solving group optimization problems, and a branch and bound search for finding optimal integer programming solutions. The innovative subroutines are shown to be efficient to compute and effective in finding good integer programming solutions and providing strong lower bounds for the branch and bound search.

Error Components Regression Models and Their Applications

Abstract: In this paper, we have developed an operational method for estimating error components regression models when the variance- covariance matrix of the disturbance terms is unkown. Monte Carlo Studies were conducted to compare the relative efficiency of the pooled estimator obtained by this procedure to (a) an ordinary least sources estimator based on data aggregated over time, (b) the covariance estimator, and (d) a generalized least squares estimator based on a known variance-covariance matrix. For T small and large p, this estimator definitely performs better than the other estimators which are also based on an estimated value of the variance-covariance matrix of the disturbances. For p small and large T it compares equally well with other estimators.

The Effects on Income of Type of College Attended

Abstract: The effects of particular attributes of colleges on the subsequent earnings of individuals who attend are much discussed but rarely studied systematically. Here we seek to compare the earnings patterns of people attending different types of colleges. The classification of colleges used in this study is the scheme developed by the Carnegie Commission on Higher Education based on the sense of commitments to research, types of programs offered and selectivity of admission of students. We find that at the college level, differences in type of institution attended have highly significant effects on differences in lifetime earning patterns of students.

Schooling, Ability, Non Pecuniary Rewards, Socioeconomic Background and the Lifetime Distribution of Earnings

Abstract: Inequality in income or earnings is the most indisputable fact about the distribution of income. Inequality in income distribution occurs in most political and economic models and has from ancient times to the modern era. Society and government have expressed a desire to establish a minimum floor for members of society -- though the level of the floor and the means of achieving it are matters of debate. Besides a direct interest in the questions of the sources of inequality, how to achieve income redistribution, and the efficacy of various policy tools, economists are also concerned with establishing how various labor markets operate, how rational individuals are, and how important are individual effort , chance, and predestination. Economists have constructed various theories that purport to explain income distribution. Some aspects of these theories have been tested against empirical observations. This study will extend the range of such tests. In addition, we will generate some new facts that a complete theory should be able to explain.

Monte Carlo for Robust Regression: The Swindle Unmasked

Abstract: This paper gives an alternative derivation of a Monte Carlo method that has been used to study robust estimators. Extensions of the technique to the regression case are also considered and some computational points are briefly mentioned.

Multinational Firms and the Factor Intensity of Trade

Abstract: In studying the impact of direct investment on the amount, direction, and composition of international trade we have found that the multinational firm fits uncomfortably into the usual theory of trade and capital movements. We attempt here to introduce the fact of the existence of multinational firms into the explanation of trade flows and particularly into the long-running debate over the relations among factor abundance, factor prices and trade.

Optimal Adaptive Control Methods for Structurally Varying Systems

Abstract: The problem of simultaneously identifying and controlling a time-varying, perfectly-observed linear system is posed. The parameters are assumed to obey a Markov structure and are estimated with a Kalman filter. The problem can be solved conceptually by dynamic programming, but even with a quadratic loss function the analytical computations cannot be carried out for more than one step because of the dual nature of the optimal control law. All approximations to the solution that have been proposed in the literature, and two approximations that are presented here for the first time are analyzed. They are classified into dual and non-dual methods. Analytical comparison is untractable; hence Monte Carlo simulations are used. A set of experiments is presented in which five non-dual methods are compared. The numerical results indicate a possible ordering among these approximations.

A Review of Cyclical Indicators for the United States: Preliminary Results

Abstract: This paper represents a very early progress report on a new study of business cycle indicators for the United States. Our host organization, CIRET, is concerned with research on surveys of economic tendencies that cover broad areas of business, investment, and consumer behavior. These inquiries yield mainly qualitative data on plans and expectations of economic decision-making units. Such data are aggregated and also in a sense quantified in form of diffusion indexes (the Ifo Business Test and its components may serve as examples), but they are basically limited to showing only the direction and not the size of changes in the economic variables covered. A major purpose of compiling and analyzing these diffusion measures is to improve prediction of cyclical movements in business activity. This objective is the same as that pursued in the National Bureau studies of quantitative business cycle indicators -- the latest of which is the project to be discussed in this paper. Appraisals of the predictive records and potentials of these two time series data sets (the cyclical indicators and the expectational diffusion indexes) are therefore definitely an appropriate subject for consideration in this conference.

Monte Carlo Techniques in Studying Robust Estimators

Abstract: Recent work on robust estimation has led to many procedures, which are easy to formulate and straightforward to program but difficult to study analytically. In such circumstances experimental sampling is quite attractive, but the variety and complexity of both estimators and sampling situations make effective Monte Carlo techniques essential. This discussion examines problems, techniques, and results and draws on examples in studies of robust location and robust regression.

An analysis of the loop optimization scores in knuth's ‘empirical study of FORTRAN programs’

Abstract: The optimization scores for Knuth's random sample of inner loops are analysed to provide a unified comparison of the five optimization levels. The techniques used are those of exploratory data analysis, and their role in the analysis is discussed. As a consequence of the analysis, five rough groups of programs with different optimization behaviour are identified and tentatively characterized. (Research supported in part by National Science Foundation Grant GJ-1154x to the National Bureau of Economic Research, Inc.)

What Happened During the Baby Boom? New Estimates of Age and Parity: Specific Birth Probabilities for American Women

Abstract: It is the main purpose of this paper to examine in detail the pattern of fertility fluctuations in the United States since the Second World War and to define, with some precision, the questions these patterns raise for students of fertility behavior.

The use of unit values to measure deviations of transaction prices from list prices

Abstract: The results reported in the Searle report have stimulated me to carry out an extensive study of unit value indices, based on a much more extensive body of data and much improved procedures as compared to the preliminary evidence contained in my “Measurement Bias in Price Indices for Capital Goods,” published in this journal in June, 1971. Once again, the new study confirms the hypothesis that transaction prices of capital goods exhibit procyclical fluctuations relative to list prices. Machinery prices appear to have been considerably more flexible downward during the period of weak investment demand between 1957 and 1963 than indicated by the Wholesale Price Index (WPI), and more flexible upward during the subsequent expansion during 1963–1969. This brief paper is a summary of the study. A complete and detailed report or results is contained in my forthcoming monograph, Measurement of Durable Goods Prices, to be published by the National Bureau of Economic Research.

Short-Run and Long-Run Prospects for Female Earnings

Abstract: This paper discussed the prospects for female earnings relative to male earnings. The determinants of the general level of earnings (female and male) are not considered. I concentrate on hourly earnings as being the best measure of the price of labor from both the demand and supply points of view. One can easily extend the discussion to annual earnings by taking account of annual hours. (In 1970 on average employed women worked about 3/4 as many hours per year as employed men.) The estimates of hourly earnings to be presented are calculated from the 1/1000 samples of the 1960 and the 1970 Census of Population. The Census samples provide much useful data on employed persons including such characteristics as sex, schooling, age, race, marital status, and class of worker. I have excluded agricultural and unpaid family members because of well-known difficulties in estimating their earnings and hours of work. All other persons who were at work during the Census week and who had their earnings in the year preceding the Census are included.

Citizen Rights and the Cost of Law Enforcement

Abstract: There is an inherent tension between the idea that individuals have certain inalienable (natural) rights and the economist's postulate that the rate if utilization of anything whose production requires scarce resources must be limited by considerations of opportunity cost. Remarks about rights to life, liberty, health, justice and the like are readily inserted into political pronouncements, legislative preambles and court decisions, but they (should) cause economists to raise questions about costs and quantities. Unfortunately, neither in ordinary language nor in the jargon of moral philosophy can such ultimate desiderata as liberty and justice be related to costs or quantities. Hence in the first section we sketch a model of social choice in which the necessary relationships can be defined. In section II, we give instances where, despite protestations to the contrary, the Law Enforcement System (LES) has made de facto reductions of citizen rights (liberties) in order to increase the efficiency if law enforcement. The final section considers some of the normative implications suggested by the positive arguments of section II.