Constructing the exact significance level for a person fit statistic

This paper uses an extension of the network algorithm originally introduced by Mehta and Patel to construct exact tail probabilities for testing the general hypothesis that item responses are distributed according to the Rasch model. By assuming that item difficulties are known, the algorithm is applicable to the statistical tests either given the maximum likelihood ability estimate or conditioned on the total score. A simulation study indicates that the network algorithm is an efficient tool for computing the significance level of a person fit statistic based on test lengths of 30 items or less.     

Combinatorial data analysis: Association and partial association

A combinatorial data analysis strategy is reviewed that is designed to compare two arbitrary measures of proximity defined between the objects from some set. Based on a particular cross-product definition of correspondence between these two numerically specified notions of proximity (typically represented in the form of matrices), extensions are then pursued to indices of partial association that relate the observed pattern of correspondence between the first two proximity measures to a third. The attendant issues of index normalization and significance testing are discussed; the latter is approached through a simple randomization model implemented either through a Monte Carlo procedure or distributional approximations based on the first three moments. Applications of the original comparison strategy and its extensions to partial association may be developed for a variety of methodological and substantive tasks. Besides rank correlation, we emphasize the topics of spatial autocorrelation for one variable and spatial association between two and mention the connection to the usual randomization approach for one-way analysis-of-variance.     

TESTICULAR SELF-EXAMINATION: VALIDATION OF A TRAINING STRATEGY FOR EARLY CANCER DETECTION

Testicular self-examination (TSE) can lead to early diagnosis and treatment of testicular cancer, the third leading cause of death in young men. We evaluated the effectiveness of a brief and specific checklist for teaching TSE skills. Ten men were videotaped while performing testicular self-examinations before and after training. The TSE training resulted in large and significant increases in the number of TSE steps completed and duration of the TSE. Two urological validation measures supported the improvements observed in the mens' self-examinations. Subjects reported continued performance of TSE during a follow-up telephone interview. This pilot study indicates that a brief and specific checklist is an effective strategy for teaching early cancer detection skills.     

Extending exploratory diagnostic classification models: Inferring the effect of covariates

Diagnostic models provide a statistical framework for designing formative assessments by classifying student knowledge profiles according to a collection of fine-grained attributes. The context and ecosystem in which students learn may play an important role in skill mastery, and it is therefore important to develop methods for incorporating student covariates into diagnostic models. Including covariates may provide researchers and practitioners with the ability to evaluate novel interventions or understand the role of background knowledge in attribute mastery. Existing research is designed to include covariates in confirmatory diagnostic models, which are also known as restricted latent class models. We propose new methods for including covariates in exploratory RLCMs that jointly infer the latent structure and evaluate the role of covariates on performance and skill mastery. We present a novel Bayesian formulation and report a Markov chain Monte Carlo algorithm using a Metropolis-within-Gibbs algorithm for approximating the model parameter posterior distribution. We report Monte Carlo simulation evidence regarding the accuracy of our new methods and present results from an application that examines the role of student background knowledge on the mastery of a probability data set.     

Whose Gene Is It? A Case Discussion About Familial Conflict over Genetic Testing for Breast Cancer

A multidisciplinary group of genetic and other professionals discuss a complex case of familial conflict over access to genetic information. One twin wishes to know the results of her deceased mother's tests for BRCA1 mutations; a second twin objects to researchers making this information available. As the case discussion unfolds, the apparent facts of this case are called into question and the lines of ethical certainty become less clear.     

Knowledge of Breast Cancer Genetics Among Breast Cancer Patients and First-Degree Relatives of Affected Individuals

The cloning of BRCA1, a susceptibility gene for inherited breast cancer, has made genetic screening possible for individuals and families whose medical histories are suggestive of an inherited predisposition to breast cancer. To date, few systematic attempts have been made to determine the level of knowledge about breast cancer genetics among women who are likely to seek BRCA1 screening when it becomes widely available. The present study attempted to assess the general knowledge about BRCA1 mutations in two groups: (1) first-degree relatives (FDRs) of breast cancer patients; and (2) women with a previous diagnosis of breast cancer. A self-administered, thirty-item questionnaire was developed through a pilot study. Ten of the items were objective, factual questions about breast cancer genetics. Responses to these questions were used to generate an overall knowledge score for each respondent. The study population was moderately knowledgeable about breast cancer genetics, with an average score of 5.35 out of 10. Counselors should not underestimate the importance of evaluating each counselee's existing knowledge about breast cancer, which can affect the provision and reception of genetic information. In particular, specific areas of knowledge that may be confusing or misunderstood were identified and these topics are discussed in detail.     

The specific action of different personality risk factors on cancer of the breast, cervix, corpus uteri and other types of cancer: A prospective investigation

We report the results of a prospective study of a random sample of 1353 elderly but healthy men and women who were followed up for a period of 10 yr, when mortality and cause of death were ascertained. Overall results have been reported elsewhere for mortality from cancer, coronary heart disease and other causes; here we are concerned with the personality factors predicting breast cancer, cervical cancer, cancer of the corpus uteri specifically, as well as other types of cancer in women. Ten specific hypotheses were tested, using specially constructed questionnaires for the purpose, and for most of these statistically significant support was obtained. The results justify belief that specific types of cancer may be related to specific stress/personality factors.     

An empirical study of the diathesis-stress theory of disease

One thousand, one hundred and twenty-one Jewish concentration camp survivors were compared with 367 Jewish controls who had not been in a concentration camp, and had not lost any family members in such a camp. Of interest was the mortality of camp and comparison groups, on the hypothesis that the stress of being in a camp would adversely affect inmates. It was found that former camp inmates were over twice as likely to die of cancer, coronary heart diesease, or other causes as the comparison subjects of similar age and sex composition, and that severity of stress was correlated with mortality in the expected direction. Diathesis, determined by means of a special interviewer-administrated questionnaire, was found to interact synergistically with stress in producing high mortality.     

Group climate in an open-ended cancer support group

A number of well-described, controlled studies assessing cancer support group intervention support their effectiveness. All of these experimental groups have been close-ended and typically involve six to eight weekly sessions. Because many cancer patients are unable or unwilling to participate in closed, extended-session groups, there is particular need for analysis of the effectiveness of short-term, open-ended groups. Additionally, objective measures are needed to delineate the factors contributing to a successful outcome in cancer support groups. We used the Short Form of the Group Climate Questionnaire (GCQ-S) to characterize 23 sessions in an open-ended, short-term, Veterans Hospital based cancer support group. The cancer group scored significantly lower on the Avoiding and Conflict dimensions (p<.001) compared to a normative psychotherapy group sample. There was no difference on the Engaged dimension. This pilot study suggests that a cancer support group in this setting can create an environment where members are cohesive and take responsibility for their own change process, while keeping interpersonal conflict to a minimum. Based on these preliminary findings, we encourage controlled clinical trials examining the efficacy of open-ended cancer support groups.At the time of this study, Dr. Daroff was a resident in Psychiatry, University of California, San Francisco.     

Time-series analysis in operant research

A time-series method is presented, nontechnically, for analysis of data generated in individual-subject operant studies, and is recommended as a supplement to visual analysis of behavior change in reversal or multiple-baseline experiments. The method can be used to identify three kinds of statistically significant behavior change: (a) changes in score levels from one experimental phase to another, (b) reliable upward or downward trends in scores, and (c) changes in trends between phases. The detection of, and reliance on, serial dependency (autocorrelation among temporally adjacent scores) in individual-subject behavioral scores is emphasized. Examples of published data from the operant literature are used to illustrate the time-series method.