Basal ganglia dysfunction, working memory, and sentence comprehension in patients with Parkinson's disease.

To investigate the role of the basal ganglia in working memory and sentence comprehension, 14 patients with Parkinson's disease (PD) were administered experimental measures of semantic and phonological working memory, and a measure of sentence comprehension, while receiving dopaminergic medications and after a period of withdrawal from these medications. An age- and education- matched control group (N=14) received the same measures. Comparison with control subjects revealed deficits in patients with PD in sentence processing regardless of medication status, but no deficits in working memory. In contrast to previous studies, withdrawal of dopaminergic medications had no significant impact on task- related working memory functions or on sentence comprehension. Results suggest that basal ganglia dysfunction does not solely account for sentence comprehension deficits seen in PD.

The analysis of repeated measures designs: a review.

Repeated measures ANOVA can refer to many different types of analysis. Specifically, this vague term can refer to conventional tests of significance, one of three univariate solutions with adjusted degrees of freedom, two different types of multivariate statistic, or approaches that combine univariate and multivariate tests. Accordingly, it is argued that, by only reporting probability values and referring to statistical analyses as repeated measures ANOVA, authors convey neither the type of analysis that was used nor the validity of the reported probability value, since each of these approaches has its own strengths and weaknesses. The various approaches are presented with a discussion of their strengths and weaknesses, and recommendations are made regarding the 'best' choice of analysis. Additional topics discussed include analyses for missing data and tests of linear contrasts.

The assessment of unidimensionality of normal and lognormal data: a look at two nonparametric procedures.

In this Monte Carlo study, the Type I error rate and the power of the Stout T procedure (DIMTEST) and the Holland-Rosenbaum procedure (HR) were examined for normal and lognormal data sets. Both procedures are based on a nonparametric item response model, where the key assumption is the item response function is monotonically nondecreasing. The two procedures performed adequately under certain conditions for both normal and lognormal data sets. Of the two, however, the Stout T procedure showed adequate power under more conditions than the Holland-Rosenbaum procedure.

Testing treatment effects in repeated measures designs: trimmed means and bootstrapping.

Non-normality and covariance heterogeneity between groups affect the validity of the traditional repeated measures methods of analysis, particularly when group sizes are unequal. A non-pooled Welch-type statistic (WJ) and the Huynh Improved General Approximation (IGA) test generally have been found to be effective in controlling rates of Type I error in unbalanced non-spherical repeated measures designs even though data are non-normal in form and covariance matrices are heterogeneous. However, under some conditions of departure from multisample sphericity and multivariate normality their rates of Type I error have been found to be elevated. Westfall and Young's results suggest that Type I error control could be improved by combining bootstrap methods with methods based on trimmed means. Accordingly, in our investigation we examined four methods for testing for main and interaction effects in a between- by within-subjects repeated measures design: (a) the IGA and WJ tests with least squares estimators based on theoretically determined critical values; (b) the IGA and WJ tests with least squares estimators based on empirically determined critical values; (c) the IGA and WJ tests with robust estimators based on theoretically determined critical values; and (d) the IGA and WJ tests with robust estimators based on empirically determined critical values. We found that the IGA tests were always robust to assumption violations whether based on least squares or robust estimators or whether critical values were obtained through theoretical or empirical methods. The WJ procedure, however, occasionally resulted in liberal rates of error when based on least squares estimators but always proved robust when applied with robust estimators. Neither approach particularly benefited from adopting bootstrapped critical values. Recommendations are provided to researchers regarding when each approach is best.

Measures of Effect Size for Comparative Studies: Applications, Interpretations, and Limitations.

Although dissatisfaction with the limitations associated with tests for statistical significance has been growing for several decades, applied researchers have continued to rely almost exclusively on these indicators of effect when reporting their findings. To encourage an increased use of alternative measures of effect, the present paper discusses several measures of effect size that might be used in group comparison studies involving univariate and/or multivariate models. For the methods discussed, formulas are presented and data from an experimental study are used to demonstrate the application and interpretation of these indices. The paper concludes with some cautionary notes on the limitations associated with these measures of effect size. Copyright 2000 Academic Press.

Electroencephalographic, volumetric, and neuropsychological indicators of seizure focus lateralization in temporal lobe epilepsy.

CONTEXT: Anterior temporal lobectomy is an effective treatment for medically intractable temporal lobe seizures. Identification of seizure focus is essential to surgical success. OBJECTIVE: To examine the usefulness of presurgical electroencephalography (EEG), magnetic resonance imaging (MRI), and neuropsychological data in the lateralization of seizure focus. DESIGN: Presurgical EEG, MRI, and neuropsychological data were entered, independently and in combination, as indicators of seizure focus lateralization in discriminant function analyses, yielding correct seizure lateralization rates for each set of indicators. SETTING: Comprehensive Epilepsy Program, Shands Teaching Hospital, University of Florida, Gainesville. PATIENTS: Forty-four right-handed adult patients who ultimately underwent successful anterior temporal lobectomy. Left-handed patients, those with less-than-optimal surgical outcome, and any patients with a history of neurological insult unrelated to seizure disorder were excluded from this study. MAIN OUTCOME MEASURES: For each patient presurgical EEG was represented as a seizure lateralization index reflecting the numbers of seizures originating in the left hemisphere, right hemisphere, and those unable to be lateralized. Magnetic resonance imaging data were represented as left-right difference in hippocampal volume. Neuropsychological data consisted of mean scores in each of 5 cognitive domains. RESULTS: The EEG was a better indicator of lateralization (89% correct) than MRI (86%), although not significantly. The EEG and MRI were significantly superior to neuropsychological data (66%) (P=.02 and .04, respectively). Combining EEG and MRI yielded a significantly higher lateralization rate (93%) than EEG alone (P<.01). Adding neuropsychological data improved this slightly (95%). CONCLUSIONS: The EEG and MRI were of high lateralization value, while neuropsychological data were of limited use in this regard. Combining EEG, MRI, and neuropsychological improved focus lateralization relative to using these data independently.

Determining Sample Size for Accurate Estimation of the Squared Multiple Correlation Coefficient.

While several resources are available to help researchers determine the minimum sample size needed to achieve target power for a wide variety of hypothesis tests, such resources are generally not available for determining the sample size when accurate parameter estimation is of interest. Sample size tables and procedures used to determine sample size for hypothesis tests should not be used for estimation because providing evidence that a parameter is not equal to some specific value is a fundamentally different task than accurately estimating the parameter. In particular, the necessary sample size required for hypothesis testing declines as the difference between the parameter and the specified value increases, but this difference does not have the same relationship to the sample size needed for accurate estimation. As interest in reporting estimates of effect sizes increases, sample size guidelines are needed for accurate estimation of these parameters. The present article focuses on the squared multiple correlation coefficient and presents regression equations that permit determination of sample size for estimating this parameter for up to 20 predictor variables. A comparison of the sample sizes reported here with those needed to test the hypothesis of no relationship between the predictor and criterion variables demonstrates the need for researchers to consider the purpose of their research and what is to be reported when determining the sample size for the study.

A Comparison of Methods for Constructing Confidence Intervals for the Squared Multiple Correlation Coefficient.

Four methods for constructing 100(1 - a)% confidence intervals for the population squared multiple correlation coefficient (r2) were compared. In one method the confidence interval was constructed by using the distribution of R². Provided r² > 0 the coverage probability for this method is exactly 1 - a when the data are multivariate normal. The other three methods are based on results in Olkin and Finn (1995) and are approximate. Results show that each of the approximate methods works very poorly for some combinations of r². The method based on the distribution of R² is recommended.

Efficacy of parent-child interaction therapy: interim report of a randomized trial with short-term maintenance.

Describes interim results of a study examining the effectiveness of parent-child interaction therapy (PCIT) with families of preschool-age children with oppositional defiant disorder. Following an initial assessment, 64 clinic-referred families were randomly assigned to an immediate treatment (i.t.) or a wait-list control (WL) condition. Results indicated that parents in the IT condition interacted more positively with their child and were more successful in gaining their child's compliance than parents in the WL condition. In addition, parents who received treatment reported decreased parenting stress and a more internal locus of control. Parents in the IT group reported statistically and clinically significant improvements in their child's behavior following PCIT. All families who received treatment reported high levels of satisfaction with both the content and process of PCIT. Preliminary 4-month follow-up data showed that parents maintained gains on all self-report measures.

Stage II breast cancer: differences between four coping patterns in side effects during adjuvant chemotherapy.

Fifty-six women with stage II breast cancer receiving adjuvant chemotherapy were recruited for a study evaluating and comparing coping patterns for differences in physical and psychological side effects during treatment with adjuvant chemotherapy. Cluster analyses were used to split women into confrontive, avoidant-confrontive, avoidant-resigned, and resigned coping clusters. Side-effect measurements were taken on the day of adjuvant chemotherapy infusion and 3 and 7 days later. Repeated measures ANCOVAs indicated that coping clusters predicted significant variance in physical, psychological, and total side effects when variance in covariates was held constant. Confrontive subjects reported significantly fewer psychological and physical symptoms than avoidant-confrontive and avoidant-resigned copers. Confrontive copers also reported fewer side effects than resigned copers, but this difference was not significant when differences in covariate distributions were controlled. Particularly robust differences were noted when confrontive copers were compared with avoidant-confrontive copers. Results suggest that a critical component in optimal coping may be a willingness to discuss and think about illness.

Testing Repeated Measures Hypotheses when Covariance Matrices are Heterogeneous: Revisiting the Robustness of the Welch-James Test.

This article examines the recommendations given by Keselman, Carriere and Lix (1993) regarding choice of sample size for obtaining robust tests of the repeated measures main and interaction hypotheses in a one Between-Subjects by one Within-Subjects design with a Welch-James type multivariate test when covariance matrices were heterogeneous and data were non-normal in unbalanced designs. We examined the generalizablility of their recommendations by varying the (a) size of the design, (b) degree of covariance heterogeneity, and (c) degree of nonsphericity. Our results indicate that the Keselman et al. recommendations for the test of the repeated measures main effect hold in some situations and can be relaxed in others. Consequently, with a relatively modest sample size, the Welch-James test provides a robust test of the main effect. On the other hand, the required sample size for the interaction can be quite large; accordingly, the Keselman et al. recornmendations must be increased as the number of groups increases and when the data are skewed. We recommend the Welch-James test for testing the main effect hypothesis. The Welch-James test should also be used to test the interaction hypothesis when the sample sizes are sufficiently large to permit a robust test. In other conditions, the researcher should use an alternative such as Huynh's (1978) Improved General Approximation test.

Relationships among performance scores of four diagnostic decision support systems.

OBJECTIVE: To examine the relationships among different performance scores for each of four diagnostic decision support systems (DDSSs). DESIGN: Intercorrelations among seven performance scores on a set of 105 cases for each of four DDSSs (DXplain, Iliad, Meditel, QMR) were computed. METHODS: The performance scores for each case reflected: 1) presence or absence of the case diagnosis in the DDSS knowledge base; 2) presence or absence of the correct diagnosis anywhere on the DDSS diagnosis list; 3) presence or absence of the correct diagnosis in the top ten diagnoses; 4) relevance of the DDSS diagnosis list; 5) comprehensiveness of the DDSS diagnosis list; 6) whether the DDSS suggested additional diagnoses to the experts' list; and 7) the length of the DDSS diagnosis list. RESULTS: For all DDSSs, the two Correct Diagnosis scores (top ten and total list) were significantly related: 1) to the presence of the correct diagnosis in the knowledge base; 2) to the Comprehensiveness score; and 3) to each other. There were significant differences among the four DDSSs on the magnitude and/or direction of the relationships between: 1) the two Correct Diagnosis scores; 2) the Relevance and Length scores; and 3) the Relevance and Additional Diagnoses scores. CONCLUSION: The production of a correct diagnosis for a given case is not related to the number of diagnoses suggested by the DDSS and, across different DDSSs, is not consistently related to other measures of performance. These data indicate that multiple measures are needed to fully describe the performance of a DDSS.

Parent-child interaction therapy: a psychosocial model for the treatment of young children with conduct problem behavior and their families.

This article describes a treatment project designed to examine the effectiveness and generalization of Parent-Child Interaction Therapy (PCIT) with families of preschool-aged children with conduct problem behavior. The importance of early intervention and issues related to measurement of change in these young children and their families are discussed. The treatment program and the study design are described, with particular emphasis on the measures used to assess treatment outcome. The sensitivity of the measures to change is illustrated with data from the first few families who have completed treatment.

Performance of four computer-based diagnostic systems.

BACKGROUND: Computer-based diagnostic systems are available commercially, but there has been limited evaluation of their performance. We assessed the diagnostic capabilities of four internal medicine diagnostic systems: Dxplain, Iliad, Meditel, and QMR. METHODS: Ten expert clinicians created a set of 105 diagnostically challenging clinical case summaries involving actual patients. Clinical data were entered into each program with the vocabulary provided by the program's developer. Each of the systems produced a ranked list of possible diagnoses for each patient, as did the group of experts. We calculated scores on several performance measures for each computer program. RESULTS: No single computer program scored better than the others on all performance measures. Among all cases and all programs, the proportion of correct diagnoses ranged from 0.52 to 0.71, and the mean proportion of relevant diagnoses ranged from 0.19 to 0.37. On average, less than half the diagnoses on the experts' original list of reasonable diagnoses were suggested by any of the programs. However, each program suggested an average of approximately two additional diagnoses per case that the experts found relevant but had not originally considered. CONCLUSIONS: The results provide a profile of the strengths and limitations of these computer programs. The programs should be used by physicians who can identify and use the relevant information and ignore the irrelevant information that can be produced.

Performance of Four Multivariate Tests Under Variance-Covariance Heteroscedasticity.

Type I error rates (τ) of four multivariate tests - Pillai-Bartlett trace, Johansen's test, James' first order test and James' second order test - were compared for heterogeneous covariance matrices. A total of 360 simulated experiments were conducted. Johansen's test and James' second order test performed better than the other two tests. The τ of Johansen's test should be very close to a when the ratio of total sample size to number of variables (N/p) is large, and the smaller samples are associated with covariance matrices with smaller elements. James' second order test outperformed the other tests under extreme conditions; that is, when Nip is small, the heterogeneity of covariance matrices is large, the sample size ratio is large, or the smaller samples are associated with covariance matrices with larger elements.

Analysis Of Quasi-Experimental Time-Series Designs.

Multivariate procedures, based on the general linear hypothesis, are outlined for inferring treatment effects in quasi-experimental time-series designs. These procedures, which take into account the dependent nature of the data obtained in time-series experiments and which require comparing the fitted regression curves for the pre-treatment and post-treatment observations, provide exact tests of significance for the various hypotheses of interest.