Durations in Panel Data Subject to Attrition: A Note on Estimation in the Case of a Stock Sample1

In the empirical analysis of unemployment durations or job durations, it is generally assumed that the stochastic processes underlying labour market behaviour and the behaviour concerning participation in a panel survey are independent. As a consequence, spells that are incomplete due to attrition can be treated as spells that are subjected to independent right censoring. However, if the assumption of independence is violated, i.e. if for example the probability of dropping out of the panel is related to the rate at which a job is found, then attrition may have to be modelled and estimated jointly with the unemployment duration distribution to avoid biased estimates of the rate at which individuals become employed. A way to model the joint dependence is by means of stochastically related unobserved determinants. We discuss some properties of these kinds of models and state conditions needed to estimate such models in the case of stock sampled duration data.     

Unemployment insurance and subsequent job duration: job matching versus unobserved heterogeneity

The relationship between Unemployment Insurance (UI) benefit duration, unemployment duration and subsequent job duration is investigated using a multi‐state duration model with state specific unobserved heterogeneity. I examine two potential explanations for the negative correlation between unemployment and job spell durations; UI benefits increase job matching quality (the ‘Matching’ effect) versus unobserved heterogeneity (‘Adverse Selection’). The Matching effect is found to be weak. Although new jobs accepted within 5 weeks of benefit termination seem to have a higher dissolution rate, the negative correlation between unemployment and job duration is mostly explained by unobserved heterogeneity. Various simulations indicate that increasing the maximum benefit duration by one week will raise expected unemployment duration by 1.0 to 1.5 days but will raise expected job duration by 0.5 to 0.8 day only. Copyright © 2001 John Wiley & Sons, Ltd.     

Transitions From School to Work and the Early Labour Market Experience

We consider transitions from school to work and the early market experience. The duration of post-school unemployment, wages, and job duration are estimated simultaneously. We find that individuals with higher levels ofschooling get jobs more quickly and have longer employment durations. Apprentices have shorter unemployment periods and stay longer in their jobs than others at the same educational level. Females have shorter unemployment periods and lower wages, and also stay in the first job longer. The unemployment duration and the accepted wage affect job duration positively, but the estimated covariance terms suggest unobserved factors working in the opposite direction.     

How low can U go?

• ? Although there is growing evidence that wage growth is building in response to low and falling unemployment in the advanced economies, there is scope for unemployment rates to fall further without triggering a pay surge.
• ? For a start, current unemployment rates in comparison to past cyclical troughs overstate the tightness of labour markets. Demographic trends associated with the ageing ‘baby boomer’ bulge have pushed down the headline unemployment rate – unemployment rates among older workers are lower than those of younger cohorts. And in a historical context, Europe still has a large pool of involuntary part‐timers.
• ? In addition, rising participation rates mean that demographics are less of a constraint on employment growth than widely assumed. In both 2017 and 2018, had it not been for increased activity rates (mainly for older cohorts), unemployment would have had to fall more sharply to accommodate the same employment increase. We expect rising participation rates to continue to act as a pressure valve for the labour market.
• ? Finally, unemployment rates were generally far lower during the 1950s and 1960s than now. If wages stay low relative to productivity, as was the case during that prior era, employment growth may remain strong, with unemployment falling further. In the post‐war era, low wages were partly a function of a grand bargain in which policy‐makers provided full employment in return for low wage growth.
• ? There is evidence to suggest that many post‐crisis workers have opted for the security of their existing full‐time job and its associated benefits despite lower wage growth, rather than change job and potentially earn more; the rise of the ‘gig economy’ has led some workers to value what they already have more. Put another way, the non‐accelerating inflation rate of unemployment (NAIRU) has fallen. So, the role of labour market tightness in pushing wage growth higher may continue to surprise to the downside.

     

Exits from unemployment: Recall or new job

This paper studies transitions out of unemployment in Spain distinguishing between recall to the same employer and reemployment in a new job. We use a large sample of newly unemployed workers obtained from Social Security records for Spain. These data contain information about each individual's employer identity before and after the unemployment spell. A discrete-time duration model with competing risks of exits serves us to investigate the factors that influence the probabilities of leaving unemployment to return to the same employer or to find a new job with a different employer. We find that taking into account the route to exit unemployment helps us to understand the influence of individual and job characteristics on the hazard rate. Moreover, the recall hazard rate exhibits no duration dependence, whereas the new-job hazard rate presents positive duration dependence.     

Using a Structural‐Form Model to Analyze the Impact of Home Ownership on Unemployment Duration

It is often found that the impact of home ownership on the hazard rate for leaving unemployment is positive, indicating that home ownership helps workers to leave unemployment for a paid job. However, little emphasis has been given to how such a relationship can be explained. This paper estimates a structural‐form model that allows for self‐selection into home ownership and the risk of home owners losing their property during a spell of unemployment. We find a substantial amount of self‐selection using indirect inference based on a mixed proportional hazards‐rate model and find virtually no impact of home ownership on individual labor market performance. Copyright © 2016 John Wiley & Sons, Ltd.     

Are Short‐lived Jobs Stepping Stones to Long‐Lasting Jobs?*

This article assesses whether short‐lived jobs (lasting one quarter or less and involuntarily ending in unemployment) are stepping stones to long‐lasting jobs (enduring 1 year or more) for Belgian long‐term unemployed school‐leavers. We proceed in two steps. First, we estimate labour market trajectories in a multi‐spell duration model that incorporates lagged duration and lagged occurrence dependence. Second, in a simulation we find that (fe)male school‐leavers accepting a short‐lived job are, within 2 years, 13.4 (9.5) percentage points more likely to find a long‐lasting job than in the counterfactual in which they reject short‐lived jobs.     

The search for success: do the unemployed find stable employment?

We use discrete time proportional hazards regressions to model the impact of previous unemployment incidence and duration on job tenure. We find that jobs that follow an unemployment spell have shorter mean duration than other jobs. Only one half of jobs that follow unemployment last for 12 months. Multivariate results suggest that an unemployment spell has a severe penalty on subsequent job tenure, and that it is unemployment incidence rather than duration which has the major impact.     

Nonlinearities and Fractional Integration in the US Unemployment Rate*

This paper proposes a model of the US unemployment rate which accounts for both its asymmetry and its long memory. Our approach introduces fractional integration and nonlinearities simultaneously into the same framework, using a Lagrange multiplier procedure with a standard null‐limit distribution. The empirical results suggest that the US unemployment rate can be specified in terms of a fractionally integrated process, which interacts with some nonlinear functions of labour‐demand variables such as real oil prices and real interest rates. We also find evidence of a long‐memory component. Our results are consistent with a hysteresis model with path dependency rather than a non‐accelerating inflation rate of unemployment (NAIRU) model with an underlying unemployment equilibrium rate, thereby giving support to more activist stabilization policies. However, any suitable model should also include business cycle asymmetries, with implications for both forecasting and policy‐making.     

New Insights into Unemployment Duration and Post Unemployment Earnings in Germany*

Building on non‐stationary search theory ( Mortensen, 1977 ; Van den Berg, 1990 ), this article estimates the effects of UB on unemployment durations and future earnings using unique administrative data in Germany. We apply censored Box–Cox quantile regression. Our results imply that the length of entitlement shows only a weak effect on unemployment duration for entitlement lengths up to 12 months and no effect on post unemployment earnings. There are noticeable effects on exits from unemployment for entitlement lengths above 12 months. A high wage replacement rate for low‐wage earners is associated with a longer duration of unemployment and higher post unemployment earnings.     

The cyclical pattern of regional unemployment flows in Poland

Using male unemployment benefit data across Polish regions during 1994–1996, we find that unemployment flows are pro-cyclical and increase with job reallocation, controlling for other factors. At the national level we observe that job reallocation and output are associated with stagnant unemployment flows, low inflows and long duration. This has heretofore been attributed to workers by-passing the unemployment benefit system as they move job to job. We show this to be a fallacy of aggregation. The cyclical behaviour of regional unemployment flows and their response to job reallocation suggests that workers use unemployment benefit system to facilitate transition.     

A Note on US Worker Turnover

The length of new employment relationships is of first‐order importance for a number of questions in recent macro‐labour research. We investigate it using data from the Survey of Income and Program Participation for the US from 1996 onwards, and document that above two‐fifths of newly employed workers fall into non‐employment within a year. We also find that the transition rate from employment to non‐employment within the first year varies significantly for different groups of the population, increases with the duration of the previous non‐employment spell, exhibits an acyclical or weakly procyclical pattern and a much higher volatility than the unemployment rate.     

Attrition in longitudinal panel data and the empirical analysis of dynamic labour market behaviour

In the empirical analysis of unemployment durations and job durations, it is generally assumed that the stochastic processes underlying labour market behaviour and the behaviour concerning participation in a panel survey are independent. However, there are reasons to believe that the probability of dropping out of the panel is related to the rate at which a (different) job is found. If there is such a relation, and if it is ignored, then the estimator of the rate at which individuals become employed or change jobs will generally be inconsistent. In this paper we analyse the relation between the duration spent in a particular labour market state and the duration of panel survey participation, by explicitly modelling and estimating the joint distribution of both durations. The emphasis will be on models allowing for stochastically related unobserved determinants of both types of duration. We estimate models both for unemployment durations and for job durations.     

What determines inflation in the US,job growth or unemployment?

An empirical investigation of postwar US data reveals that movements in inflation are much more strongly associated with job growth than the unemployment rate. Job growth is found to be strongly related to inflation even after accounting for the effect of the unemployment rate. The residual influence of the unemployment rate on inflation is small, however, after accounting for the effect of job growth. The data shows that in the past inflation has tended to decline when job growth is weak even if unemployment is low. This suggests that the relatively slow job growth of recent years may partly explain the puzzle that, during much of the current expansion, the US economy has experienced little inflation in spite of low unemployment.     

HOW EFFECTIVE ARE UNEMPLOYMENT BENEFIT SANCTIONS? LOOKING BEYOND UNEMPLOYMENT EXIT

This paper provides a comprehensive evaluation of the effects of benefit sanctions on post‐unemployment outcomes such as post‐unemployment employment stability and earnings. We use rich register data which allow us to distinguish between a warning that a benefit reduction may take place in the near future and the actual withdrawal of unemployment benefits. Adopting a multivariate mixed proportional hazard approach to address selectivity, we find that warnings do not affect subsequent employment stability but do reduce post‐unemployment earnings. Actual benefit reductions lower the quality of post‐unemployment jobs both in terms of job duration as well as in terms of earnings. Copyright © 2012 John Wiley & Sons, Ltd.     

Labor market policy evaluation in equilibrium: Some lessons of the job search and matching model

We analyze the consequences of counseling provided to job seekers in a standard job search and matching model. It turns out that neglecting equilibrium effects induced by counseling can lead to wrong conclusions. In particular, counseling can increase steady state unemployment although counseled job seekers exit unemployment at a higher rate than the non-counseled. Dynamic analysis shows that permanent and transitory policies can have effects of opposite sign on unemployment.     

Unions and the economic basis of attitudes

Unions make differences to employee satisfaction that correspond to their effects on individual economic advantage. Panel data reveal how changes in economic circumstance and changes in job satisfaction are linked to changes in union coverage. When individuals move into a union covered job they receive a wage mark‐up and express enhanced pay satisfaction. Conversely, those moving from a union covered job on average lose any mark‐up and have significantly reduced satisfaction. Similar findings emerge for working hours. On average individuals prefer shorter hours, something they tend (not) to achieve on moving (out of) into a unionised job, resulting in higher (lower) satisfaction. Switching into union coverage lowers satisfaction with job security, even though coverage has no effect on the risk of unemployment. This is because covered employees suffer greater costs of re‐employment for a given level of unemployment risk, partly because of loss of the union mark‐up.     

Do Low‐Wage Workers React Less to Longer Unemployment Benefits? Quasi‐Experimental Evidence*

The fact that unemployed workers have different abilities to smooth consumption entails heterogeneous responses to extended unemployment benefits. Our empirical exercise explores a quasi‐experimental setting generated by an increase in the benefits entitlement period. The results suggest a hump‐shape response of unemployment duration over the one‐year pre‐unemployment wage distribution; individuals at the bottom and top of the wage distribution reacted less than those in the interquartile range. This behaviour of job searchers is consistent with labour supply models with unemployment insurance and savings. It questions the optimality of very long entitlement periods to target the unemployment experiences of low‐wage workers.     

Treatment effect of job-training programmes on unemployment duration in Slovakia

There is a large literature evaluating job-training programmes. In this paper, we evaluate three such job-training programmes that are used in Slovakia. Individuals participating in a job-training programme during their unemployment spell are usually not a random subsample of the population. To determine the treatment effect of a job-training programme on unemployment duration, one has to correct for this selection effect. Therefore, we use a multivariate mixed proportional hazard-type model to describe the hazard of getting a job simultaneously with the hazard of entering a programme. We allow for a heterogeneous treatment effect and for the treatment effect to vary over time. Furthermore, we add the monthly unemployment rate as a time-varying explanatory variable. The estimation results show that two of the three programmes shorten the unemployment duration quite substantially.     

How do workers decide their jobs? The influence of income,wage and job characteristics

This paper provides results on the economic decision‐making process of Spanish workers, who decide their jobs from the effects of variations in the non‐wage income, the wage and the prices of non‐pecuniary job characteristics. To that end, we formulate a non‐separable generalization of the Linear Expenditure System (NLES) as a joint model of labor supply and job characteristics demand, estimated separately for both males and females, using a 1991 Spanish survey. The main results show that: (i) some job characteristics have a positive effect on the wage, whereas others have a negative effect; (ii) the average percentage effect of employer size and the complexity index are higher for males than for females, with the fatal accident risk displaying similar values; (iii) if the non‐wage income of every worker increases, these individuals will prefer to devote less hours to work, and will also prefer jobs in smaller companies and with a lower risk; and (iv) if the wage and hedonic prices of non‐pecuniary job characteristics increase, then both males and females will prefer to reduce their labor supply, and devote their available time to jobs in bigger firms, with a higher risk and complexity. Copyright © 1999 John Wiley & Sons, Ltd.