Estimating Transition Probabilities from a Time Series of Independent Cross Sections

This paper considers the implementation of a nonstationary, heterogeneous Markov model for the analysis of a binary dependent variable in a time series of independent cross sections. The model, previously considered by M offitt (1993), offers the opportunity to estimate entry and exit transition probabilities and to examine the effects of time-constant and time-varying covariates on the hazards. We show how ML estimates of the parameters can be obtained by Fisher's method-of-scoring and how to estimate both fixed and time-varying covariate effects. The model is exemplified with an analysis of the labor force participation decision of Dutch women using data from the Socio-economic Panel (SEP) study conducted in the Netherlands between 1986 and 1995. We treat the panel data as independent cross sections and compare the employment status sequences predicted by the model with the observed sequences in the panel. Some open problems concerning the application of the model are also discussed.     

THE AGEING POPULATION: CRUNCH TIME FOR GOVERNMENT REFORMS

Current discussions about reforms to health and long‐term care miss the most important trends that should be influencing debate. With an ageing population that includes a higher proportion of people with manageable illnesses, health and care costs will rise. Reforms must ensure that existing government spending is used more efficiently and that it harnesses – rather than works against – private financing.     

The Land Crisis in Zimbabwe Viewed from South of the Limpopo

Farm invasions in Zimbabwe have highlighted the pressing need for land reform throughout the southern African region. In South Africa, where the racial disparities in land holding are most severe, the events in Zimbabwe have raised the temperature of the land debate and led to calls for land invasions by some rural groups. The ANC-led government, facing criticism from both right and left for the slow pace of reform, has veered between strident defence of private property rights and threats to expropriate white farms. White farming interests have reacted differentially, with some progressive voices joining the calls for an accelerated reform programme. Current land reform policy in South Africa seems set to advance the interests of emerging black commercial farmers and tribal chiefs at the expense of the rural poor and landless.     

The Impact of Industrial Market Access Negotiations on African Economies

This paper proposes an extensive data simulation exercise on the likely impact of non-agricultural market access liberalization. The paper analyses real options for tariff cut reduction, special and differential treatment and the treatment of unbound tariffs. This paper also gives indications concerning the likely economic impact of this trade round of industrial market access negotiations on African economies. It shows that an ambitious tariff cut reduction formula would provide greater access to developed country markets for African producers. However, this kind of formula has a major drawback for African countries in the sense that it could accelerate the de-industrialization of African countries and limit incentives to diversify their economies.     

Saddlepoint approximations to the mean and variance of the extended hypergeometric distribution

Conditional inference on 2 x 2 tables with fixed margins and unequal probabilities is based on the extended hypergeometric distribution. If the support of the distribution is large, exact calculation of the conditional mean and variance of the table entry may be computationally demanding. This paper proposes a single‐saddlepoint approximation to the mean and variance. While the approximation achieves acceptable accuracy for ordinary practical purposes, an alternative saddlepoint approximation is provided that gives much closer to exact results. It improves the accuracy of current approximations to up to more than four powers of ten.     

The post‐application labour market consequences of employment tribunal claims

This article examines the post‐application employment consequences for individuals registering complaints to Employment Tribunals following dismissal or redundancy. We consider several pieces of evidence: (a) the probability of finding another job, (b) the time taken to get a new job and (c) the pay/status of the new job. Our results indicate that age plays a significant role in aspects (a) and (c), while those who previously held managerial positions generally took longest to get a new job and found it most difficult to achieve a similar level of pay/status in their current jobs. Long‐term health problems/disability is associated with significantly worse outcomes on all three measures. Respondents whose cases were dismissed by tribunals without hearings fared worst in terms of obtaining a new job and the time it took to do so. There are, however, fewer differences by tribunal outcome in the relative pay/status of the claimant's current job.     

The integration of fuzzy sets and statistics: toward strict falsification in the social sciences

Whilst statistics take up a prominent place in the social science research toolkit, some old problems that have been associated there with have not been fully resolved. These problems include bias through the inclusion of irrelevant variation and the exclusion of relevant variation, which may lead to hidden and spurious correlations in more extreme—however not at all unthinkable—cases. These issues have been addressed by Ragin by building a case for the usage of fuzzy set theory in social science. In this paper, we take a complementary view, insofar as we incorporate fuzzy set theory in current statistical analyses. Apart from shedding new light on the main issues associated with (population based) statistics, this approach also offers interesting prospects for the falsification of theories—rather than single relations between variables—in the social sciences.