Evaluating the effectiveness of family therapies: An integrative review and analysis.

A number of previous reviews of studies evaluating the effectiveness of family therapy have varied in their conclusions. This review is the first attempt at an integrated statistical analysis of family therapy effectiveness research. Family therapy was found to have positive effects compared with both no-treatment and alternative treatment controls, as measured by family interactions and behavior ratings. Follow-up data demonstrated that family therapy continued to show positive effects over time, but the effects were diminished and more variable than at posttreatment assessment. Future research should concentrate on comparative outcome studies with specific populations and with both legitimate alternative treatments and placebo controls. In addition, researchers need to describe in greater detail the family therapy procedures that are used. Outcome measures should represent multiple vantage points and should include measures of family interactions, preferably using both self-report and observational methods. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Bilateral isolated metastases of malignant melanoma to the cerebellopontine angle

PURPOSE: Peak drug concentration (Cmax) measures the extremity of drug exposure and is a secondary indicator of the extent of absorption after area under the concentration time curve (AUC). Cmax serves as the indicator of absorption rate in bioequivalence (BE) studies in the US (1). The use of Cmax, not the time to Cmax (Tmax), as the metric to assess absorption rate causes erratic inferences in BE studies, and incorrect conclusions for some. We can improve BE efficiency (i.e., get the answer right the first time), by properly analyzing the time to Cmax (Tmax) instead of Cmax. METHODS: We have previously redirected attention to Tmax as the unconfounded absorption rate variable, instead of Cmax, and have called for equally spaced sampling times during the suspected absorption phase to improve the performance of the rate metric (2). Equal spacing converts Tmax easily into a count variable and we illustrated an appropriate statistical analysis for counts. This paper provides some measurement theory concepts to help judge which is the more appropriate analysis, and also provides parametric confidence limits for Tmax treatment differences. Three separate BE studies are then analyzed by both methods. RESULTS: By focusing on the differences in conclusions, or inferences, this paper identifies three major issues with the current FDA "recommended" analysis of BE studies. First, Cmax, a continuous variable peak-height or extent measure has usurped Tmax's function and performs erratically as a substitute measure for the rate of absorption. Second, Tmax, should be analyzed as a discrete attribute, not as a continuous variable. Third, since several extent measures (AUC, Cmax), not one, are actually being analyzed, an adjustment for multiple testing is mandatory if we are to maintain the size of the test at the desired alpha level (13), and not inadvertently use a narrower bioequivalence window than is intended. These actions all can have serious unintended consequences on inferences, including making inappropriate ones.     

The implications of linking the dynamic performance and turnover literatures.

This article examines how the literatures of dynamic performance and the performance–turnover relationship inform each other. The nonrandom performance–turnover relationship suggests that dynamic performance studies may be biased by their elimination of participants who do not remain for the entire study period. The authors demonstrated that the performance slopes of those who leave an organization differ from the performance slopes of those who remain. This finding suggests that studies of the performance–turnover relationship need to consider employee performance trends when predicting turnover. Replicating and extending the research of D. A. Harrison, M. Virick, and S. William (1996), the authors found that performance changes from the previous month and performance trends measured over a longer time period explained variance in voluntary turnover beyond current performance. Finally, the authors showed that performance trends interacted with current performance in the prediction of voluntary turnover. (PsycINFO Database Record (c) 2011 APA, all rights reserved)     

An introduction to survival analysis: Statistical methods for analysis of clinical trial data.

The randomized controlled clinical trial (RCT) is a prospective study using random assignment of subjects to treatment groups to compare the effect and value of a therapeutic intervention against a control. The RCT is the most definitive clinical research tool for evaluating the efficacy of a new therapy in human subjects. Often the outcome of interest in an RCT is the length of time until an event occurs after treatment or intervention. In this article we introduce statistical methods for evaluating differences in the patterns of time to response between two groups of subjects to determine whether one therapy is better than another. The collection of methods for analyzing such data, known as survival data, is called survival analysis. Using data from a hypothetical clinical trial for the prevention of the recurrence of depression, we illustrate two elementary methods for analyzing survival data. We also discuss generalizations of these methods to incorporate covariates and conclude with a general discussion of clinical trials of psychiatric therapies. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Applying the realized probability of dying to cancer survival

Age comparisons of survival in cancer cohorts generally utilize relative survival rates, which are based on indicators of the probability of survival for a given number of years after diagnosis. Cancer relative survival rates for the same number of years tend to decline as age at diagnosis increases. However, the same number of years of survival reflects higher relative longevity at older ages than at younger ages. The realized probability of dying (RPD) is a survival measure that expresses individual survival time after diagnosis relative to the survival distribution of an age-, race-, and sex-specific reference population, in effect weighing individual survival time more heavily as age at diagnosis increases. The purpose of this study was to apply the RPD as a survival measure in cancer epidemiology. Two cohorts of cancer patients, white males with prostate cancer and white females with breast cancer, aged 55 years and over at diagnosis, were followed for 15 years. Although older subjects survived less time after diagnosis than younger subjects, they achieved more favorable RPD values. We present survival analysis methods for analyzing the RPD in this population, an approach not previously used with this measure. The implications for use of the RPD in cancer epidemiology are discussed.     

A new SAS procedure for latent transition analysis: Transitions in dating and sexual risk behavior.

The set of statistical methods available to developmentalists is continually being expanded, allowing for questions about change over time to be addressed in new, informative ways. Indeed, new developments in methods to model change over time create the possibility for new research questions to be posed. Latent transition analysis, a longitudinal extension of latent class analysis, is a method that can be used to model development in discrete latent variables, for example, stage processes, over 2 or more times. The current article illustrates this approach using a new SAS procedure, PROC LTA, to model change over time in adolescent and young adult dating and sexual risk behavior. Gender differences are examined, and substance use behaviors are included as predictors of initial status in dating and sexual risk behavior and transitions over time. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

When it comes to pay, do the thin win? The effect of weight on pay for men and women.

Cultivation theory suggests that society holds very different body standards for men versus women, and research indicates that the consequences of defying these social norms may not be linear. To test these notions in the employment context, we examined the relationship between weight and income and the degree to which the relationship varies by gender. For women, we theorized a negative weight–income relationship that is steepest at the thin end of the distribution. For men, we predicted a positive weight–income relationship until obesity, where it becomes negative. To test these hypotheses, we utilized 2 longitudinal studies, 1 German and 1 American. In Study 1, weight was measured over 2 time periods, and earnings were averaged over the subsequent 5 years. Study 2 was a multilevel study in which weight and earnings were within-individual variables observed over time, and gender was a between-individual variable. Results from the 2 studies generally support the hypotheses, even when examining within-individual changes in weight over time. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Stroop interference and attention-deficit/hyperactivity disorder: A review and meta-analysis.

Previous reviews and meta-analyses that addressed abnormal Stroop interference in attention-deficit/hyperactivity disorder (ADHD) yielded mixed results. The authors of the present study argue that the inconsistencies may reflect the problematic nature of 2 frequently used methods to quantify Stroop interference-the difference score and Golden's method (C. J. Golden, 1978). Golden's method correction for base-word reading is inadequate, and the difference score is sensitive to the nature of the outcome variable. The latter can be remedied with a ratio score. Contrasting previous meta-analyses, this meta-analysis covers all age groups and all Stroop test variants, and it excludes studies using the Golden quantification method. Mean effect sizes for interference in ADHD as quantified by difference scores relative to control scores were 0.24 across all studies but 1.11 for time-per-item studies; outcome variable was a significant moderator variable, reflecting the sensitivity of the difference score to this variable. Consistency analysis of ratio scores across 19 studies reveals more interference for the ADHD groups relative to the control groups. It is concluded that interference control is consistently compromised in individuals with ADHD. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Gender bias in subject samples in counseling psychology.

In the past decades, there has been a disproportionate emphasis on the use of male subjects in psychological research (e.g., Carlson & Carlson, 1960; Schwabacher, 1972). In this study, we examined how the use and reporting of the gender of subjects in counseling psychology research has changed during the decade from 1971-1972 to 1981-1982. For this time period, articles from two journals, the Journal of Counseling Psychology (JCP) and the Journal of Vocational Behavior (JVB), were examined for specification of sex of subjects, analysis for sex differences, and appropriate generalization of single-sex studies. Results indicate that (a) reporting of gender as a subject variable increased from 1971-1972 to 1981-1982; (b) in 58% of the studies, results were analyzed for gender differences; (c) JVB was more likely than JCP to publish articles in which gender differences were analyzed; and (d) in over 60% of the studies in 1971-1972 and 26% of the studies in 1981-1982, findings regarding subject gender seemed to be overgeneralized. The results are discussed in terms of the need to develop gender-specific data bases, journal policies, and future research. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

A meta-analytical structural equations analysis of a model of employee turnover.

Combined meta-analysis with structural equations modeling (SEM) to validate the W. H. Mobley et al (1978) turnover theory as well as alternative structural networks proposed by A. Dalessio et al (1986), P. W. Hom et al (1984), and B. D. Bannister and R. W. Griffeth (1986). The authors aggregated correlations from 17 studies (N?=?5,013 employees), correcting for unreliability and sampling error. Then they used SEM to assess the models, comparing their relative fits to data. SEM analyses corroborated the Mobley et al model better than did past research, but these analyses also showed that the Dalessio et al and the Hom et al theories explained sample data more plausibly. Additional SEM tests found that turnover base rates, time lags between turnover and model assessments, unemployment rates, and occupational differences moderated the models' pathways. The present findings suggest various implications for these theories and for turnover research. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Deciding when, how, and if to correct turnover correlations.

E. R. Kemery et al (see record 1989-10678-001) and R. P. Steel et al (1990) offered correction formulas that adjust the point-biserial correlations used in turnover research for "inopportune splits in the dichotomous variable." Both suggested that their formulas could be used whenever turnover deviated from 50%. However, the proper criterion for choosing to correct turnover point-biserial correlations is not statistical but theoretical. Researchers should first determine which construct, tenure or turnover, they are investigating. Then they can decide which correction formula to use, if any. In this article, how and when to correct turnover correlations is discussed, an empirical comparison of 4 correction procedures is presented, and the necessary corrections for conducting turnover meta-analyses are specified. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Use and misuse of the consolidated standards of reporting trials (CONSORT) guidelines to assess research findings: Comment on Coyne, Stefanek, and Palmer (2007).

Comments on the article titled Psychotherapy and survival in cancer: The conflict between hope and evidence by J. C. Coyne, M. Stefanek, and S. C. Palmer (see record 2007-06095-001).The basic principles underlying randomized clinical trials have been known for more than 50 years. The Consolidated Standards of Reporting Trials (CONSORT) guidelines, published in 1996 and based on those principles, are a valuable guide to what needs to be reported from any trial within word-limit constraints, but they do not provide guidelines to the decisions that have to be made to generate a trial with credible results. Using these guidelines as do J. C. Coyne, M. Stefanek, and S. C. Palmer (2007) is a misinterpretation of their purpose. Furthermore, Coyne et al. misrepresented the methods and findings of studies of the effects of psychosocial intervention on cancer survival. These errors are systematically reviewed. The results of these questionable analyses led Coyne et al. to recommend stopping research in an area that may be highly productive. Recent developments in the field are summarized. It is a mistaken and dangerous conclusion to declare this or other areas of scientific research off limits. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Patient variable biases in clinical judgment: Conceptual overview and methodological considerations.

Specific conceptual factors are presented as having contributed to the negative findings of past psychotherapy bias research. Among these factors are the restrictive nature of both the definition of bias and the model of the biased clinician. A review of published studies of several patient variable biases (e.g., gender, race/ethnicity, and age) indicates that bias may best be defined in broader terms and that its occurrence may be more circumscribed than originally conceived. In addition, the lack of a theoretical perspective in this area of research is noted and the applicability of some social cognitive processes is discussed. Methodological factors are also considered, and recommendations for future research are offered. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

How different survey techniques can impact consultant recommendations: A scientist-practitioner study comparing two popular methods.

Very little research has compared how consultant survey methods may result in different recommendations for change. This study compared the job satisfaction method to the reason method to understand employee turnover motives. To control for content, measures from both methods were applied to the same attribute categories, such as job pay, the work itself, and job security. Results indicated that the reason approach demonstrated considerably more predictive validity than the job satisfaction approach and provided unique insight into specific turnover motives (e.g., salary and supervisor relationships). These results directly impacted subsequent intervention choices of the client. Results suggest that consultants can generate even better recommendations for clients if they include reason scales in their survey-based projects. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Introduction to functional data analysis.

Psychologists and behavioural scientists are increasingly collecting data that are drawn from continuous underlying processes. We describe a set of quantitative methods, Functional Data Analysis (FDA), which can answer a number of questions that traditional statistical approaches cannot. These methods are applicable for analyzing many datasets that are common in experimental psychology, including time series data, repeated measures, and data distributed over time or space as in neuroimaging experiments. The primary advantage of FDA is that it allows the researcher to ask questions about when in a time series differences may exist between two or more sets of observations. We discuss functional correlations, principal components, the derivatives of functional curves, and analysis of variances models. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Propensity score methods for bias reduction in the comparison of a treatment to a non-randomized control group

In observational studies, investigators have no control over the treatment assignment. The treated and non-treated (that is, control) groups may have large differences on their observed covariates, and these differences can lead to biased estimates of treatment effects. Even traditional covariance analysis adjustments may be inadequate to eliminate this bias. The propensity score, defined as the conditional probability of being treated given the covariates, can be used to balance the covariates in the two groups, and therefore reduce this bias. In order to estimate the propensity score, one must model the distribution of the treatment indicator variable given the observed covariates. Once estimated the propensity score can be used to reduce bias through matching, stratification (subclassification), regression adjustment, or some combination of all three. In this tutorial we discuss the uses of propensity score methods for bias reduction, give references to the literature and illustrate the uses through applied examples.     

Capturing the impact of membership turnover in small groups via latent class growth analysis: Modeling the rise of the New York Knicks of the 1960s and 1970s.

In several areas of research, most notably in industrial/organizational psychology and in addictions treatment research, there have been calls for advances in modeling the impact of turnover in membership within dynamic small N groups. The present study examines the utility of latent class growth analysis (LGCA; in combination with other approaches) in modeling turnover in group membership within a dynamic work group from popular culture: the National Basketball Association’s (NBA) New York Knickerbockers (Knicks) of the 1960s and 1970s. Changes over time in the proportions of 5 longitudinal player efficiency classes accounted for variability in regular season wins, number of NBA All-Star Game appearances and the proportion of (eventual) basketball Hall-of-Fame members across a 20-year span. Using LCGA, there was a clear match between the empirical model and the “historical reality” with respect to identifying the players that were responsible for the success of the Knicks, particularly in the early 1970s. This study provides a practical example of how LCGA may be used to capture the impact of turnover in group membership on group-level outcomes across multiple areas in which groups with dynamic membership are studied. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

The role of the stimulus in Rorschach responses.

"It is apparent, from the studies reviewed, that the definition of Rorschach stimulus effects is more a task for the future than an accomplishment of the past. In fact, empirical concern with this question appears to have been something of an afterthought with users of the technique. Variation in the stimulus, in order to define an independent variable, has been such a standard procedure in psychological research that it is surprising to find it being applied only during very recent years to an analysis of the Rorschach. Other methods, as indicated, have contributed to the clarification of this problem, but they have not, as yet, gone very deeply." (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Application of two neural network paradigms to the study of voluntary employee turnover.

Two neural network paradigms—multilayer perceptron and learning vector quantization—were used to study voluntary employee turnover with a sample of 577 hospital employees. The objectives of the study were twofold. The 1st was to assess whether neural computing techniques offered greater predictive accuracy than did conventional turnover methodologies. The 2nd was to explore whether computer models of turnover based on neural network technologies offered new insights into turnover processes. When compared with logistic regression analysis, both neural network paradigms provided considerably more accurate predictions of turnover behavior, particularly with respect to the correct classification of leavers. In addition, these neural network paradigms captured nonlinear relationships that are relevant for theory development. Results are discussed in terms of their implications for future research. (PsycINFO Database Record (c) 2010 APA, all rights reserved)