Übergangsratenmodelle bei intervalldatierten Ereignissen

Statistical Papers - In event history data, events often are not dated exactly but only a time interval is recorded. In contrast, common estimators for transition rate models assume exactly dated...     

PARAMETER ESTIMATION AND APPLICATIONS FOR A GENERALISATION OF THE BETA-BINOMIAL DISTRIBUTION

A three-parameter generalisation of the beta-binomial distribution (BBD) derived by Chandon (1976) is examined. We obtain the maximum likelihood estimates of the parameters and give the elements of the information matrix. To exhibit the applicability of the generalised distribution we show how it gives an improved fit over the BBD for magazine exposure and consumer purchasing data. Finally we derive an empirical Bayes estimate of a binomial proportion based on the generalised beta distribution used in this study.     

Preparation,support, and satisfaction of adoptive families in agency and independent adoptions

Information gathered from over 1000 adoptions in the fourth year of a prospective study of adoptions finds satisfaction levels to be quite high, with those families adopting through private agencies to feel best prepared and satisfied. Differences by adoption auspice are detailed and discussed.The senior authors are Co-Principal Investigators of the California Long-range Adoption Study. This research was supported by the Child Welfare Research Center, Family Welfare Research Group, University of California at Berkeley, through a grant from the Children's Bureau, Administration for Children and Families, Department of Health and Human Services. The authors wish to thank the families for their participation. Please address correspondence to Mary Berry at the Center for Child Welfare, UTA School of Social Work, P.O. Box 19129, Arlington, Texas 76019.     

Drug addiction as a lifestyle

Drug addict rehabilitation programs receive a small proportion of the funds made available through the social welfare system. Emphasis has traditionally been placed on the pathological rather than the salutogenic elements of an addicted lifestyle. A new test of a person's sense of coherence in life (Antonovsky's 9-item Sense of Coherence scale) may be of interest in rehabilitation work with drug addicts, and in focusing more attention on this aspect of addiction treatment. Thirty drug addicts in treatment and rehabilitation and 10 former drug addicts were interviewed using the 9-item Sense of Coherence scale. The results obtained were compared to a well known test of distress, the 24-item Symptom Checklist. Drug addicts in treatment facilities had significantly lower mean scores on the 9-item Sense of Coherence scale (2.3) and higher scores on the 24-item Symptom Checklist (2.3) than both drug addicts in rehabilitatively oriented institutions (3.3 and 1.6) and the long-term rehabilitated non-using former drug addicts (4.2 and 1.5 respectively). The differences between the group in rehabilitation and the former drug addicts were also statistically significant. The levels of the two psychometric tests suggested a gradual movement towards normal values and an increased sense of meaning in life among the former drug addicts, contrary to findings by other researchers. The length of time before these tests return to normal values may exceed the observation period often used in follow-up at treatment facilities. Increased social welfare may follow if a disclosure of salutogenic possibilities in drug addicts is obtained. Further prospective research is, however, necessary to confirm our findings.     

Resources and strategies of interest groups and industry representatives involved in federal forest policy

This study analyzes the resources and strategies of public interest groups and industry representatives involved in federal forest policy in the state of Oregon during the early 1990s. While many studies have examined the role of interest groups in the policy process, few have compared empirically the resources available and strategies pursued by industry representatives and public interest groups in a particular policy domain. Utilizing survey data from 133 business representatives and 326 public interest groups involved in federal forest policy, the study argues that public interest group influence derives primarily from the ability to mobilize human resources; the financial resources of these groups tend to be modest. Industry and industry-supported groups, in contrast, possess considerable financial power while enjoying less support from the public. Consequently, industry interests tend to focus their efforts on more traditional forms of influence such as the persistent lobbying of natural resource agencies and elected officials. Public interest groups, in contrast, tend to devote considerable efforts to building public support in urban core areas to build the capacity to pressure governmental decision-makers.     

INTERVENTION STRATEGIES: PREDICTING FAMILY THERAPY OUTCOME*

A pre-defined list of family therapy intervention strategies was used to predict post-therapy perceived life happiness and marital happiness among husbands and wives. Clients presented with both child and marriage-focused problems. The data were analyzed separately for husbands and wives. In general, favorable outcome for husbands was associated with active restructuring operations on the part of the therapist. Prediction of outcome for wives was less clear. However, wives did appear to respond favorably to less active interventions such as actualizing transactional patterns and reframing.     

Psychopathology in pathological gamblers seeking treatment

High rates of psychiatric symptoms have been reported in pathological gamblers. This study of psychiatric comorbidity in pathological gamblers is the first to use structured psychiatric interviews assessing DSM-III-R Axis I and II disorders. The Structured Clinical Interview for DSM III-R (SCID-P, SCID-II) was administered to 40 (25 male, 15 male) pathological gamblers seeking outpatient treatment in Minnesota for gambling, and 64 (41 male, 23 female) controls. High lifetime rates of Axis I (92%) but not Axis II (25%) psychopathology were found in pathological gamblers as compared to controls. No differences between male and female gamblers were found in rates of affective, substance use or personality disorders. Females had higher rates of anxiety disorders and histories of physical/sexual abuse. Possible associations between psychiatric disorders and pathological gambling are discussed along with gambler typologies and implications for future research.The authors wish to gratefully acknowledge the assistance of: Gary Christenson, M.D., Carol Peterson, Ph.D., William Meller, M.D., Thomas Mackenzie, M.D.     

Asymptotic properties of a generalized regression-type predictor of a finite population variance in probability sampling

A system of predictors for estimating a finite population variance is defined and shown to be asymptotically design-unbiased (ADU) and asymptotically design-consistent (ADC) under probability sampling. An asymptotic mean squared error (MSE) of a generalized regression-type predictor, generated from the system, is obtained. The suggested predictor attains the minimum expected variance of any design-unbiased estimator when the superpopulation model is correct. The generalized regression-type predictor and the predictor suggested by Mukhopadhyay (1990) are compared.