Adaptive weights smoothing with applications to image restoration

We propose a new method of nonparametric estimation which is based on locally constant smoothing with an adaptive choice of weights for every pair of data points. Some theoretical properties of the procedure are investigated. Then we demonstrate the performance of the method on some simulated univariate and bivariate examples and compare it with other nonparametric methods. Finally we discuss applications of this procedure to magnetic resonance and satellite imaging.     

Evaluating the Simplified Conjoint Expected Risk Model: Comparing the Use of Objective and Subjective Information

The simplified Conjoint Expected Risk (CER) model by Holtgrave and Weber posits that perceived risk is a linear combination of the subjective judgments of the probabilities of harm, benefit, and status quo, and the expected harm and benefit of an activity. It modifies Luce and Weber's original CER model—that uses objective information to evaluate financial gambles—to accommodate activities such as health/technology activities where values of the model variables are subjective. If the simplified model is a valid modification of the original model, its performance should not be sensitive to the use of subjective information. However, because people may evaluate information differently when objective information is provided to them than when they generate information on their own, the performance of the simplified CER model may not be robust to the source of model-variable information. We compared the use of objective and subjective information, and results indicate that the estimates of the simplified CER model parameters and the proportion of variance in risk judgments accounted for by the model are similar under these two conditions. Thus, the simplified CER model is viable with activities for which harm and benefit information is subjective.     

A note on modelling underreported Poisson counts

In this paper we present a parsimonious model for the analysis of underreported Poisson count data. In contrast to previously developed methods, we are able to derive analytic expressions for the key marginal posterior distributions that are of interest. The usefulness of this model is explored via a re-examination of previously analysed data covering the purchasing of port wine (Ramos, 1999).     

Six‐Month‐Olds' Detection of Clauses Embedded in Continuous Speech: Effects of Prosodic Well‐Formedness

Three experiments investigated the role of prosodic structure for infants' recognition of embedded word sequences. Six‐month‐olds were familiarized with 2 versions of the same sequence, 1 corresponding to a well‐formed prosodic unit and the other to a prosodically ill‐formed sequence (although a successive word series). Next, infants heard 2 test passages. One included the well‐formed unit, and the other included the ill‐formed sequence. In Experiment 1, infants listened longer to the passage containing the well‐formed unit, suggesting that such units, even when they are embedded, are better recognized. Experiments 2 and 3 showed that this better recognition does not depend on an acoustic match between the familiarized sequences and their later embeddings. This suggests that the advantage of the well‐formed unit is at least partially due to infants' use of prosody to parse continuous speech.     

Prosoziales Arbeitsverhalten: Entwicklung und Überprüfung eines Messinstruments zur Erfassung des freiwilligen Arbeitsengagements

A German version of the Organizational Citizenship Behavior Questionnaire (GOCBQ) is developed and tested. Study 1 was conducted with 150 students working together in 39 project groups. The results show that the internal consistency and test-retest-reliability of the GOCBQ are good. Moreover, the GOCBQ measures a general altruism orientation which can be interpreted as a stable trait. The GOCBQ does neither correlate substantially with demographical variables nor with extroversion or neuroticism. Instead, substantial correlations are registered with mood and group atmosphere. In study 2 results from study 1 were cross-validated with data from 128 voluntary and professional helpers, in study 3 with data from 43 professionals. Implications for future research and applications in working life are discussed.     

The Educational Orientations of Graduate Social Work Faculty

For this exploratory study of the educational orientations of graduate social work faculty, the author surveyed faculty in 38 randomly selected graduate social work departments in the United States in Spring 1991. All were sent a revised Hadley Educational Orientation Questionnaire, which measured their agreement with 12 items each on Mentoring Orientation and Master Teaching Orientation scales. The survey also asked about the source of their educational philosophies. Analysis of 346 responses suggests that faculty tend toward a master teaching approach in attempting to impart essential knowledge and to empower students, but they also incorporate elements from the mentoring approach. Faculty indicated that their educational philosophies were derived principally from work experiences, personal experiences, and professional socialization.     

GNR,MGR, and exact misspeclfication testing

The Gauss-Newton regression (GNR) is widely used to compute Lagrange multiplier statistics. A regression described by Milliken and Graybill yields an exact F test in a certain class of nonlinear models which are linear under the null. This paper shows that the Milliken-Graybill regression is a GNR. Hence one interpretation of Milliken-Graybill is that they identified a class of nonlinear models for which the GNR yields an exact test.     

Bayes prediction of number of failures in weibull samples

This work is concerned with the Bayesian prediction problem of the number of components which will fail in a future time interval, when the failure times are Weibull distributed. Both the 1-sample and the 2-sample prediction problems are dealed with, and some choices of the prior densities on the distribution parameters are discussed which are relatively easy to work with and allow different degrees of knowledge on the failure mechanism to be incorporated in the predictive procedure. Useful relations between the predictive distribution on the number of future failures and the predictive distribution on the future failure times are derived. Numerical examples are also given.     

A Note on Superiority Comparisons of Homogeneous Linear Estimators

This note extends some results on homogeneous linear estimators to the general, even nonlinear case.A Sufficient condition for the difference of mean square error matrices of minimum conditional mean square error estimator and minimum average risk linear estimator to be postive definite is derived.