Nearest neighbor hazard estimation with left-truncated duration data

Duration data often suffer from both left-truncation and right-censoring. We show how both deficiencies can be overcome at the same time when estimating the hazard rate nonparametrically by kernel smoothing with the nearest-neighbor bandwidth. Smoothing Turnbull’s estimator of the cumulative hazard rate, we derive strong uniform consistency of the estimate from Hoeffding’s inequality, applied to a generalized empirical distribution function. We also apply our estimator to rating transitions of corporate loans in Germany.     

Ordinary least squares estimation of the functional errors-in-variables model with trended data:some monte carlo evidence

This note summarizes some Monte Carlo experiments that were designed to investigate the finite sample relevance of the asymptotic normality and efficiency of OLS in the errors-in-variables model with trended data. The experiments show that the normal approximation is not very satisfactory for sample size up to T=400, but that OLS is quite efficient relative to competing estimators when there is a trend in the exogenous variables of the model.     

An exact two-sample test based on the baumgartner-weiss-schindler statistic and a modification of lepage's test

It is shown that the nonparametric two-saniDle test recently proposed by Baumgartner, WeiB, Schindler (1998, Biometrics, 54, 1129-1135) does not control the type I error rate in case of small sample sizes. We investigate the exact permutation test based on their statistic and demonstrate that this test is almost not conservative. Comparing exact tests, the procedure based on the new statistic has a less conservative size and is, according to simulation results, more powerful than the often employed Wilcoxon test. Furthermore, the new test is also powerful with regard to less restrictive settings than the location-shift model. For example, the test can detect location-scale alternatives. Therefore, we use the test to create a powerful modification of the nonparametric location-scale test according to Lepage (1971, Biometrika, 58, 213-217). Selected critical values for the proposed tests are given.     

Estimating Prediction Error: Cross-Validation vs. Accumulated Prediction Error

We study the validation of prediction rules such as regression models and classification algorithms through two out-of-sample strategies, cross-validation and accumulated prediction error. We use the framework of Efron (1983 Efron , B. ( 1983 ). Estimating the error rate of a prediction rule: improvement on cross-validation . Journal of the American Statistical Association 78 : 316 – 331 .[Taylor & Francis Online], [Web of Science ®] , [Google Scholar]) where measures of prediction errors are defined as sample averages of expected errors and show through exact finite sample calculations that cross-validation and accumulated prediction error yield different smoothing parameter choices in nonparametric regression. The difference in choice does not vanish as sample size increases.     

Unternehmenserfolg, Wechsel im Vorstandsvorsitz und Disziplinierung von Finanzvorständen

The Chief Financial Officer (CFO) is often referred to as a company’s No. 2 on contemporary management boards; yet corresponding empirical evidence is scarce. As a result, academic literature has not yet investigated whether CFOs—like CEOs—are dismissed more frequently if corporate performance is poor and to what extent forced Chief Executive Officer (CEO) turnover also influences disciplinary action towards CFOs. Therefore, in this paper we examine the antecedents of forced CFO departures in the largest German corporations between 1999 and 2006. Building on principal-agent theory, we expect respective relationships between the board of directors, the CEO, and the CFO. Moreover, we propose that principals also take team-specific and firm-specific human capital into consideration when disciplining agents. We find that poor corporate performance and forced CEO turnover both independently increase the likelihood of CFO dismissal. In addition, we find indications for a close team relationship between CFOs and CEOs. In summary, our results support the prominent role of CFOs alongside CEOs on contemporary management boards and suggest a more detailed consideration of CFOs in future research on performance consequences of managerial successions.     

Vulnerable children's rights to participation,protection, and provision: The process of defining the problem in Swedish child and family welfare

This study addresses the relationship between children's participation and the protection and provision offered to them by social services in Sweden. It applies a theoretical framework for analysing child welfare that is anchored in the United Nations Convention on the Rights of the Child. How child participation may affect child protection and provision is examined empirically using case documentation from 2 municipalities. The main finding is that when children are not given voice or opportunity to influence the framing of what “the problem” is, the design of protection and care tends to be poorly matched to the actual problems documented in the child investigation and vice versa; when children can influence framing, this is associated with well‐matched protection and care. This suggests that traditional child welfare ethos, to the effect that protection should be of such overriding concern that children even should be protected from participation, is misguided. The study further illustrates the intrinsic problems with the family orientation of Swedish social services and its reliance on partnership with parents, which makes it difficult to live up to the Convention on the Rights of the Child. Incorporating child participation into existing service models can transform Swedish social services to an augmented child‐focused system that by ensuring participation also promotes protection and provision.     

Traits of a representative welfare state: the Swedish example

Järkestig Berggren U, Blomberg S, Petersson J. Traits of a representative welfare state: the Swedish example Int J Soc Welfare 2010: 19: 402–411 © 2009 The Author(s), Journal compilation © 2009 Blackwell Publishing Ltd and the International Journal of Social Welfare. The care manager reform and the case manager reform are new reforms in the social care services in Sweden, which are evolving during the 2000s. Together they shape the social care services introducing a new way of decision‐making where representatives for the organisation (care manager) and the users (case manager) negotiate. The reforms have been analysed in two studies with results presented in this article. Using the concepts of role, orientation, function and assignments, it is argued that the managers come to the negotiations on rights from different positions that are both conflicting and complementary. They further mediate the development towards a welfare mix, where the market, social networks and users interact to obtain the public welfare provision. Through this negotiated rights model, it is argued that traits of a representative welfare state emerge, with the distinction of moving the focus to the administrative practices and their differences away from political ideologies.     

Bayesian inference for Gaussian excursion set generated Cox processes with set-marking

This work considers spatial Cox point processes where the random intensity is defined by a random closed set such that different point intensities appear in the two phases formed by the random set and its complement. The point pattern is observed as a set of point coordinates in a bounded region W?? ^d together with the information on the phase of the location of each point. This phase information, called set-marking, is not a representative sample from the random set, and hence it cannot be directly used for deducing properties of the random set. Excursion sets of continuous-parameter Gaussian random fields are applied as a flexible model for the random set. Fully Bayesian method and Markov chain Monte Carlo (MCMC) simulation is adopted for inferring the parameters of the model and estimating the random set. The performance of the new approach is studied by means of simulation experiments. Further, two forestry data sets on point patterns of saplings are analysed. The saplings grow in a clear-cut forest area where, before planting and natural seeding, the soil has been mounded forming a blotched soil structure. The tree densities tend to be different in the tilled patches and in the area outside the patches. The coordinates of each sapling have been measured and it is known whether this location is in a patch or outside. This example has been a motivation for the study.     

A multilevel analysis of longitudinal ordinal data: evaluation of the level of physical performance of women receiving adjuvant therapy for breast cancer

Longitudinal health-related quality-of-life (QOL) data are often collected as part of clinical studies. Here two analyses of QOL data from a prospective study of breast cancer patients evaluate how physical performance is related to factors such as age, menopausal status and type of adjuvant treatment. The first analysis uses summary statistic methods. The same questions are then addressed using a multilevel model. Because of the structure of the physical performance response, regression models for the analysis of ordinal data are used. The analyses of base-line and follow-up QOL data at four time points over two years from 257 women show that reported base-line physical performance was consistently associated with later performance and that women who had received chemotherapy in the month before the QOL assessment had a greater physical performance burden. There is a slight power gain of the multilevel model over the summary statistic analysis. The multilevel model also allows relationships with time-dependent covariates to be included, highlighting treatment-related factors affecting physical performance that could not be considered within the summary statistic analysis. Checking of the multilevel model assumptions is exemplified.