Biomedical subjects

R J Boik

Publications and source records attributed to R J Boik.

6 recordsLinked to original sources

PubMed2000

An examination of the robustness of the empirical Bayes and other approaches for testing main and interaction effects in repeated measures designs.

In a previous paper, Boik presented an empirical Bayes (EB) approach to the analysis of repeated measurements. The EB approach is a blend of the conventional univariate and multivariate approaches. Specifically, in the EB approach, the underlying covariance matrix is estimated by a weighted sum of the univariate and multivariate estimators. In addition to demonstrating that his approach controls test size and frequently is more powerful than either the epsilon-adjusted univariate or multivariate approaches, Boik showed how conventional multivariate software can be used to conduct EB analyses. Our investigation examined the Type I error properties of the EB approach when its derivational assumptions were not satisfied as well as when other factors known to affect the conventional tests of significance were varied. For comparative purposes we also investigated procedures presented by Huynh and by Keselman, Carriere, and Lix, procedures designed for non-spherical data and covariance heterogeneity, as well as an adjusted univariate and multivariate test statistic. Our results indicate that when the response variable is normally distributed and group sizes are equal, the EB approach was robust to violations of its derivational assumptions and therefore is recommended due to the power findings reported by Boik. However, we also found that both the EB approach and the adjusted univariate and multivariate procedures were prone to depressed or elevated rates of Type I error when data were non-normally distributed and covariance matrices and group sizes were either positively or negatively paired with one another. On the other hand, the Huynh and Keselman et al. procedures were generally robust to these same pairings of covariance matrices and group sizes.

Bayes Theorem↗

PubMed1995

MSU Rurality Index: development and evaluation. Montana State University.

The construction and validation of a residence-based index of the degree of rurality are reported. The MSU Rurality Index is a locally normal index and assigns a quantitative measure of rurality to each participant in a study. Data required to compute the index are minimal; only two variables need be measured. Statistical analysis effort required to compute the index is somewhat more intensive than usual, but this tradeoff between data collection and data analysis seems sensible. Data collection is generally more expensive than data analysis. The two required variables, county population and distance to emergency care, are optimally transformed to achieve normality and weighted to achieve validity. A measure of departure from normality is automatically obtained while constructing the index. A positive score reflects a rural residence and a negative score reflects an urban residence relative to the group under study. A score of zero reflects average rurality. Reliability and construct validity were examined using two data sets. The MSU Rurality Index has high test-retest reliability, is appropriately related to a set of ordered categories concerning place of residence, and is as or more strongly related to these categories than alternative indices computed from distance or population alone. The validity of the MSU Rurality Index does not appear to be compromised by its parsimony. Even though the MSU Rurality Index is based on only two variables, it was found to be associated with various health care variables as strongly or more strongly than an 11 variable county-based index developed in Texas.

Adult↗

PubMed1995

Thought disorder on the WAIS-R relative to the Rorschach: assessing identity-disordered adolescents.

Clinical researchers have noted that compared with other diagnostic groups, adults with Borderline Personality Disorder tend to demonstrate relatively more thought disorder on unstructured projective tests (e.g., Rorschach) than on structured objective tests of cognitive performance (e.g., Wechsler Adult Intelligence Scale; WAIS). Using archival data, our study found evidence that adolescents with Identity Disorder tend to exhibit this same phenomenon. The records of 62 adolescent inpatients who had been administered the WAIS or WAIS-R and the Rorschach were examined. Of the 62 cases, 25 were diagnosed with Identity Disorder, 14 with Conduct Disorder (Group Type), 15 with Oppositional Defiant Disorder, and 8 with Schizophreniform Disorder. For each participant, the WAIS or WAIS-R and the Rorschach were scored according to the Thought Disorder Index (TDI; Johnson & Holzman). Adolescents with Identity Disorder revealed a significantly larger discrepancy between TDI scores on the WAIS or WAIS-R and TDI scores on the Rorschach than did adolescents with other diagnoses. The findings suggested that the discrepancy between the degree of thought disorder on structured versus unstructured psychological tests (i.e., differential decompensation) is related to diagnosis.

Adolescent↗

PubMed1993

Technical note: computing tests of fixed effects in a restricted class of mixed models.

Inferences about fixed effects in mixed linear models are important in a variety of animal science studies. The statistical theory for making such inferences is well known, and if the variance components are known up to a proportionality constant, then optimal exact tests can be performed. Computing the test statistics, however, can still be problematic when the random effects have many levels. In practice, approximate tests that are easily computed but less efficient are usually employed. This article describes reduction in error sum of squares procedures for performing the exact test and for computing associated confidence intervals. By taking advantage of iterative algorithms for solving Henderson's mixed-model equations, the tests can be performed without inverting the covariance matrix or computing a generalized inverse of the mixed-model coefficient matrix. The procedures are illustrated on an animal model that has three random effects, two with 1,372 levels and one with 450 levels.

Algorithms↗

PubMed1989

Susceptibility of Eimeria bovis and Toxoplasma gondii to oxygen intermediates and a new mathematical model for parasite killing.

Eimeria bovis and Toxoplasma gondii differ in their susceptibility to macrophages activated by lymphokines. Interferon-gamma can activate macrophages to totally inhibit E. bovis sporozoite development, whereas growth of T. gondii tachyzoites in macrophages is not totally affected. The susceptibility of these parasites to oxygen intermediates and their ability to evade the oxidative burst by macrophages were investigated in cell-free systems. Using a logistic model to assess growth inhibition, T. gondii growth was impaired by 50% at 10(-4.25) M (56 microM) H2O2, with 30 min as the optimum time for measuring inhibition. Preliminary results indicate that T. gondii follows mode-one and mode-two killing with relation to time after exposure to H2O2, implying a role for OH. and the induction of a DNA repair mechanism. The same model was used to assess inhibition of E. bovis growth that was more susceptible, being inhibited to 50% by 10(-5) M (10 microM) H2O2. Both parasites were susceptible to the effects of xanthine-xanthine oxidase that releases a full complement of oxygen intermediates (H2O2, OH., (1)O2, and O2-). Adding quenchers or scavengers to the system confirmed that T. gondii was susceptible to products of the interaction of O2- and H2O2 (OH. and (1)O2), and that E. bovis sporozoites were at least partially susceptible to H2O2 and O2-, but extremely susceptible to OH.. These data were supported by studies on scavenging enzymes present in the parasites. Toxoplasma gondii was rich in superoxide dismutase (SOD), catalase, and glutathione peroxidase (GPO), and E. bovis had less catalase and SOD.(ABSTRACT TRUNCATED AT 250 WORDS)

Animals↗

PubMedDate not supplied

Predicting alcohol use in rural children: a longitudinal study.

The purposes of this study were to describe the prevalence and correlates of alcohol use and to examine the ability to predict alcohol use among rural sixth- and seventh-grade children. The sample consisted of 625 children from six schools in small Montana towns. Self-administered questionnaires contained measures of sociodemographic characteristics, self-concept, school attitudes, beliefs about the effects of alcohol, and alcohol use. Fifty-eight percent of the children reported using alcohol. Children's beliefs about alcohol were significantly correlated with alcohol use. Logistic regression analysis failed to identify a model having adequate sensitivity and specificity for classifying sixth- and seventh-grade students as "users" and "nonusers" based on variables assessed in Grades 3 and 4. Nevertheless, holding other variables constant, children who displayed both negative self-concept and negative school attitudes in Grades 3 and 4 were most likely to use alcohol in Grades 6 and 7.

Alcohol Drinking↗