A Test of the Conditional Independence Assumption in Sample Selection Models

Identification in most sample selection models depends on the independence of the regressors and the error terms conditional on the selection probability. All quantile and mean functions are parallel in these models; this implies that quantile estimators cannot reveal any—per assumption non‐existing—heterogeneity. Quantile estimators are nevertheless useful for testing the conditional independence assumption because they are consistent under the null hypothesis. We propose tests of the Kolmogorov–Smirnov type based on the conditional quantile regression process. Monte Carlo simulations show that their size is satisfactory and their power sufficient to detect deviations under plausible data‐generating processes. We apply our procedures to female wage data from the 2011 Current Population Survey and show that homogeneity is clearly rejected. Copyright © 2015 John Wiley & Sons, Ltd.     

Estimating panel data models in the presence of endogeneity and selection

We consider estimation of panel data models with sample selection when the equation of interest contains endogenous explanatory variables as well as unobserved heterogeneity. Assuming that appropriate instruments are available, we propose several tests for selection bias and two estimation procedures that correct for selection in the presence of endogenous regressors. The tests are based on the fixed effects two-stage least squares estimator, thereby permitting arbitrary correlation between unobserved heterogeneity and explanatory variables. The first correction procedure is parametric and is valid under the assumption that the errors in the selection equation are normally distributed. The second procedure estimates the model parameters semiparametrically using series estimators. In the proposed testing and correction procedures, the error terms may be heterogeneously distributed and serially dependent in both selection and primary equations. Because these methods allow for a rather flexible structure of the error variance and do not impose any nonstandard assumptions on the conditional distributions of explanatory variables, they provide a useful alternative to the existing approaches presented in the literature.     

Wage determination in the union and nonunion sectors.

This study contains estimates of wage equations for white male union and nonunion employees. The authors find that nonunion wages are generally more responsive than union wages to individuals' education and experience and to regional price-level variation. Despite those differences, however, estimates of union-nonunion wage differentials based on these separate equations do not differ greatly from a differential obtained from a union dummy variable in an equation based on combined union and nonunion observations. Union-nonunion differentials vary widely across occupational groups and are generally larger in the lower skilled and more highly unionized occupations. The results for manufacturing, for which additional industry data are available, indicate a negative impact of high concentration ratios on the wages of all workers and a greater impact of establishment size on nonunion than on union wages. Data were drawn from the May 1973 Current Population Survey.     

Least squares model averaging by Mallows criterion

This paper is in response to a recent paper by Hansen (2007) who proposed an optimal model average estimator with weights selected by minimizing a Mallows criterion. The main contribution of Hansen’s paper is a demonstration that the Mallows criterion is asymptotically equivalent to the squared error, so the model average estimator that minimizes the Mallows criterion also minimizes the squared error in large samples. We are concerned with two assumptions that accompany Hansen’s approach. The first is the assumption that the approximating models are strictly nested in a way that depends on the ordering of regressors. Often there is no clear basis for the ordering and the approach does not permit non-nested models which are more realistic from a practical viewpoint. Second, for the optimality result to hold the model weights are required to lie within a special discrete set. In fact, Hansen noted both difficulties and called for extensions of the proof techniques. We provide an alternative proof which shows that the result on the optimality of the Mallows criterion in fact holds for continuous model weights and under a non-nested set-up that allows any linear combination of regressors in the approximating models that make up the model average estimator. These results provide a stronger theoretical basis for the use of the Mallows criterion in model averaging by strengthening existing findings.     

The impact of minimum wages on wages,work and poverty in Nicaragua

In this paper we use an individual- and household-level panel data set to study the impact of changes in legal minimum wages on a host of labor market outcomes including: a) wages and employment, b) transitions of workers across jobs (in the covered and uncovered sectors) and employment status (unemployment and out of the labor force), and c) transitions into and out of poverty. We find that changes in the legal minimum wage affect only those workers whose initial wage (before the change in minimum wages) is close to the minimum. For example, increases in the legal minimum wage lead to significant increases in the wages and decreases in employment of private covered sector workers who have wages within 20% of the minimum wage before the change, but have no significant impact on wages in other parts of the distribution. The estimates from the employment transition equations suggest that the decrease in covered private sector employment is due to a combination of layoffs and reductions in hiring. Most workers who lose their jobs in the covered private sector as a result of higher legal minimum wages leave the labor force or go into unpaid family work; a smaller proportion find work in the public sector. We find no evidence that these workers become unemployed.Our analysis of the relationship between the minimum wage and household income finds: a) increases in legal minimum wages increase the probability that a poor worker's family will move out of poverty, and b) increases in legal minimum wages are more likely to reduce the incidence of poverty and improve the transition from poor to non-poor if they impact the head of the household rather than the non-head; this is because the head of the household is less likely than a non-head to lose his/her covered sector employment due to a minimum wage increase and because those heads that do lose covered sector employment are more likely to go to another paying job than are non-heads (who are more likely to go into unpaid family work or leave the labor force).     

The effects of multiple minimum wages throughout the labor market: The case of Costa Rica

This paper investigates the effects of legal minimum wages on employment and hours worked among workers covered by minimum wage legislation as well as those for whom it does not apply (the uncovered sector) in Costa Rica. This country's large uncovered sector and complex minimum wage policy, which has for decades set numerous wages throughout the wage distribution, provide a stimulating counterpoint to the U.S. framework for the analysis of the impact of minimum wages. Using 1988–2000 micro data, we find that a 10% increase in minimum wages lowers employment in the covered sector by 1.09% and decreases the average number of hours worked of those who remain in the covered sector by about 0.6%. We do not find a significant impact on hours worked in the uncovered sector. Finally, we show that despite the wide range of minimum wages, the largest impact on the employment of covered sector workers is in the lower half of the skill distribution.     

Stereotypes, Asian Americans, and Wages: An Empirical Strategy Applied to Computer Use at Work

This article examines the effect on wages of the Asian-American stereotype as mathematically and technically adept, and the role this stereotype may play in explaining racial wage differences. We propose an empirical strategy to examine the influence of stereotypes on labor market outcomes, with a specific application to the wage premium associated with computer use at work. Using Current Population Survey data, ordinary least squares estimates do not provide compelling evidence that a positive stereotype affects wages for Asian Americans.     

An efficiency wage approach to reconciling the wage curve and the Phillips curve

This study develops an efficiency wage model that generates a wage curve at the regional level and a Phillips curve at the national level, under the assumption that workers' efficiency depends on both regional and aggregate labor market conditions. An equation relating wages to unemployment and lagged wages is derived from the profit-maximizing behavior of firms, and it is demonstrated that the coefficient on lagged wages is less than 1 with regional data but equals 1 with aggregate data. In addition, there is an equilibrium relationship between unemployment and wages at the regional level, but not at the aggregate level.     

On-the-job search equilibrium with endogenous unemployment benefits

This paper develops an on-the-job search model with wage posting where unemployment benefits are proportional to past wages. We emphasize that this contributes to increasing the reservation wages of unemployed workers and introduces a feedback effect of the distribution of wages on the distribution of unemployment benefits. We show that the model predictions are consistent with some stylized French facts and quantify the impact of inefficient rejections of low-wage offers by the unemployed. We find that, by reducing the indexing of unemployment benefits to previous earnings and increasing lump-sum transfers, it is possible to increase both employment and welfare.     

Minimum wages,wages and employment in various sectors in Honduras

This paper contributes to our understanding of the impact of minimum wages on labor markets of developing countries, where there are often multiple minimum wages and compliance is weak. We examine how changes in more than 22 minimum wages over 1990–2004 affect employment, unemployment and average wages of workers in different sectors, defined by coverage under the legislation. The evidence suggests that minimum wages are effectively enforced only in medium and large-scale firms, where a 1% increase in the minimum wage leads to an increase of 0.29% in the average wage and a relatively large reduction in employment of ? 0.46%. We find that public sector wages emulate minimum wage trends but the higher cost of labor does not reduce employment there. There are no discernable effects of minimum wages on the wages of workers in small-firms or the self-employed; yet, higher minimum wages may create more unemployment. We conclude that (even under our upper bound estimate of the effect on the wages of workers) the total earnings of workers in the large-firm covered sector fall with higher minimum wages in Honduras, which warrants a policy dialogue on the structure and level of minimum wages.     

The distribution of changes in manufacturing employment and the impact of the minimum wage

That employment for workers in durable goods industries is more sensitive to the pace of economic activity than for non-durable goods employees is not a surprising result. What is noteworthy about the conclusions of this study, however, is the manner in which increases in the minimum wage have altered the distribution of employment and sensitivity to short-run changes in employment of production workers in manufacturing industries. By focusing on the distribution of employment and how that distribution changes over the cycle, estimates of some aspects of the impact of the minimum wage that have not previously been analyzed have been developed.The evidence indicates that increases in the minimum wage over the period 1947–1975 have had a significant impact on employment patterns. Minimum wage legislation has had the effect of decreasing the share of projected employment and increasing vulnerability to cyclical changes in employment for the group of workers most ‘marginal’ to the work force low-wage industry employees. Hence, as a result of increased minimum wages, low-wage industry employees are able to obtain fewer jobs during periods of normal employment growth and their jobs are less secure in the face of short-run employment variations.Minimum wage legislation has undoubtedly resulted in higher wages for some of the relatively-low-productivity workers who were able to obtain employment than these workers would have received in its absence. The cost in terms of lost employment opportunities and cyclical vulnerability of jobs, however, has apparently been borne most heavily by low-wage industry employees. The primary beneficiaries of the shifts in the pattern of employment shares occasioned by minimum wage increases were high-wage industry workers, particularly in the ordnance, food, tobacco, and petroleum industries.     

Politics in wage setting: does government colour matter?

This paper studies the relationship between wage formation and the political colour of the government in an economy with a centralized wage bargaining system. Ideological, organizational and personal ties between the central trade union and the social democratic political party suggest that the trade union may behave significantly different in wage negotiations under a social democratic than under a conservative government. Using time series data for Norway, we estimate that changing from a conservative to a social democratic central government significantly reduces manufacturing wages and makes wages more responsive to unemployment. This result is consistent with a wage bargaining model augmented by political preferences of the union leaders and suggests that the effect of bargaining coordination depends on the political colour of the government. The estimated effects are both robust with respect to model specification and stable over time. We are grateful to Fredrik Wulfsberg, participants at seminars in Trondheim and Oslo, and an anonymous referee for valuable comments.     

Wages,non-wage characteristics,and predominantly male jobs

This paper estimates the wage premium associated with working in predominantly male jobs. It also examines whether this wage premium is greater than the compensation workers demand for the less desirable non-wage characteristics of such jobs. The coefficients of the change in the proportion of men in an occupation on the change in wages for quits and layoffs provide opposing biased estimates of the wage premium; because workers who voluntarily quit move to better matches, but those that are laid off accept jobs from the representative distribution of job offers. Specifically, when the premium paid over- (under-)compensates for undesirable work characteristics, the quit estimate is a downward (upward) biased estimate of the wage premium, while the layoff estimate is biased upward (downward). Results from the U.S. National Longitudinal Survey of Youth (NLSY) and the U.S. Panel Study of Income Dynamics (PSID) indicate that: (1) the estimated bounds of the wage premium are large; and (2) the wage premium overcompensates for the non-wage characteristics of male jobs.     

Wage determination in urban Russia: Underpayment and the gender differential

A stochastic frontier wage equation is employed to examine labor-market efficiency and estimate workers’ potential wages in Russia after a decade of economic reforms using a nationally representative household survey. Dynamic monopsony underpayment, defined as the differences between the highest wage a worker with given characteristics could earn and the worker's actual wage, is a significant factor lowering real wages. The estimated degree of underpayment differs significantly depending on gender and substantially exceeds the estimates for Western economies. Workers’ potential wages are elastic with respect to the local cost of living. Women's mean potential wage is only 58% of men's.     

Payroll taxes,wages and employment: Identification through policy changes

This paper investigates the effect of changes in payroll taxes on wages and employment in Argentina. The analysis, based on administrative data, focuses on the impact of a series of major changes in payroll taxes which varied across geographical areas. This setup offers two main advantages over previous studies. First, using longitudinal data, the variation in tax rates across space and time provides a plausible source of identification of their effects on employment and wages. Second, the use of legal tax rates for each area at each point in time provides a remedy for the measurement error bias raised by the use of empirical rates constructed from observed tax and wage bills. Once this bias is accounted for, the results indicate that changes in payroll tax rates are only partially shifted onto wages, and they point to the absence of any significant effect on employment.     

Better protected,better paid: Evidence on how employment protection affects wages

This paper empirically establishes the effect of the employer's term of notice on the wage level of employees. The term of notice is defined as the period an employer has to notify workers in advance of their upcoming dismissal. The wages paid during this period are an important element of firing costs and hence employment protection. To find a causal effect, I exploit the exogenous change in the term of notice that resulted from the introduction of a new Dutch law in 1999. Strong evidence is found that a longer ‘dormant’ term of notice leads to higher wages. In my sample, an additional month of notice increases wages by three percent, ceteris paribus.     

An empirical analysis of state labor markets: has worker insecurity shifted wages in the 1990s?

Labor markets in the 1990s have tightened considerably but with a surprising lack of wage inflation. There are several explanations for this behavior, where one of the more prominent explanations is that worker insecurities have depressed wage growth. This study develops an augmented Phillips curve model to test whether there are any structural shifts in wage dynamics in the 1990s. Using state data from 1980 to 1996, the empirical results are consistent with wages becoming more cyclically responsive in the 1990s. Increased long-term unemployment and permanent job losses are associated with the depressed wages in the 1990s, supporting claims that worker insecurity has dampened wage growth.     

The Variation in Wage Rigidity by Occupation and Union Status in the Us

This study estimates wage equations with data disaggregated by occupation and union status, and it derives two measures of wage rigidity for each group of workers: the sensitivity of wages to unemployment and the speed with which wages respond to price inflation. The sensitivity of wages to an aggregate measure of unemployment was found to depend negatively on an occupation's skill level. In addition, union wages were more sensitive to unemployment than non-union wages and responded less rapidly to price inflation.     

Fixed and Random Effects in Classical and Bayesian Regression*

This paper proposes a common and tractable framework for analyzing fixed and random effects models, in particular constant‐slope variable‐intercept designs. It is shown that, regardless of whether effects (i) are treated as parameters or as an error term, (ii) are estimated in different stages of a hierarchical model, or whether (iii) correlation between effects and regressors is allowed, when the same prior information on idiosyncratic parameters is introduced into all estimation methods, the resulting common slope estimator is also the same across methods. These results are illustrated using the Grünfeld investment data with different prior distributions. Random effects estimates are shown to be more efficient than fixed effects estimates. This efficiency gain, however, comes at the cost of neglecting information obtained in the computation of the prior unknown variance of idiosyncratic parameters.