Roy T. St. Laurent

EVALUATING AGREEMENT WITH A GOLD STANDARD IN METHOD COMPARISON STUDIES

: We develop a statistical model for method comparison studies where a gold standard is present and propose a measure of agreement. This measure can be interpreted as a population correlation coefficient in a constrained bivariate model. An estimator of this coefficient is proposed and its statistical properties explored. Applications of the new methodology to data from the medical literature are presented.

Leverage and Superleverage in Nonlinear Regression

Abstract Several measures of the leverage of an observation in a nonlinear regression model are defined and developed. In contrast to the upper bound on the leverage in a linear model, it is found that in a nonlinear model the leverage of an observation may exceed 1. Such a case is said to exhibit superleverage. Relationships between the leverage measures are explored, and several examples are developed to illustrate the proposed methodology.

Alternative calculation of the global clinical dementia rating

SummaryThe Clinical Dementia Rating (CDR) is a widely used instrument for rating the global severity of dementia, with scores in six independently rated categories used as a basis for computing a global score. We have found that the algorithms currently used to calculate the global score from the six component scores produce results that are sometimes inconsistent with the goals of the rating scale. We systematically analyzed these incongruities and developed an alternative algorithm that eliminates them while retaining the fundamental features of the original method.

Bartlett correction factors in logistic regression models

Bartlett correction factors for likelihood ratio tests of parameters in conditional and unconditional logistic regression models are calculated. The resulting tests are compared to the Wald, likelihood ratio, and score tests, and a test proposed by Moolgavkar and Venzon in Modern Statistical Methods in Chronic Disease Epidemiology, (Wiley, New York, 1986).

The Effects of Misconceptions on the Properties of Friedman's Test

Friedmans test is a widely used rank-based alternative to the analysis of variance (ANOVA) F-test for identifying treatment differences in a randomized complete block design. Many texts provide incomplete or misleading information about when Friedmans test may be appropriately applied. We discuss the assumptions needed for the test and common misconceptions. We show via simulation that when the variance or skew of the treatment distributions differ, application of Friedmans test to detect differences in treatment location can result in Type I error probabilities larger than the nominal α, and even when α is unaffected, the power of the test can be less than expected.

A blended estimator for a measure of agreement with a gold standard

St. Laurent developed a measure of agreement for method comparison studies in which an approximate method of measurement was compared to a gold standard method of measurement. The measure of agreement proposed was shown to be related to a population intraclass correlation coefficient. In this paper, the authors develop a family of estimators for the measure of agreement based on pivotal quantities. A blend of two particular members of the family is suggested as an estimator itself. In general, the blended estimator outperforms the maximum likelihood estimator in terms of bias and mean-squared error.

Confidence intervals for the comparison of two poisson distributions

Confidence interval construction the difference in mean event rates for two Index independent , Poisson samples is discussed. Intervals are derived by considering Bayes estimates of the mean event rates using a family of noninformative priors. The coverage probabilities of the proposed are compared to those of the standard Wald interval for of observed events. A compromise method of constructing interval based on the data is suggested and its properties are evaluated. The method is illustrated in several examples.

The Equivalence of the Milliken—Graybill Procedure and the Score Test

Abstract Milliken and Graybill (1970) proposed a widely applicable test of a nonlinear specification in a regression model. In this note I show that their ad hoc procedure is equivalent to a score test and hence asymptotically equivalent to tests based on the maximum likelihood ratio.

Advanced Placement Statistics: Expanding the Scope of Statistics Education

A list of consequential developments in the field of statistics for the past quarter-century must include the creation and implementation of the Advanced Placement (AP) program in Statistics. This program has introduced millions of high school students to our discipline over the past 18 years, contributing to the large increase in the number of undergraduate students pursuing statistics as their major in college. ASA members and leaders have played a substantial role in shaping this program and furthering its success.

Inverted Pedagogy in Second Semester Calculus.

Abstract This study investigates the effects of applying an inverted classroom model in a second-semester calculus course at a large regional university in the southwest during the Spring of 2013. The sample consisted of four class sections with the same instructor, with a total of 173 students; two class sections were in the experimental group, whereas the other two sections served as a control group. In the experimental sections, students watched video lectures of the course content outside of class, and class time was dedicated to solving problems associated with the content. Learning gains and academic differences between the two groups were investigated by analyzing exam scores and homework grades. In addition a survey (Motivated Strategies for Learning Questionnaire) was used to measure the students’ motivational orientations and their use of various learning strategies. Results showed there was a significant difference between the two groups on conceptual portions of some exams, where the control group outperformed the experimental group. There were also some significant differences on some aspects of the survey. This paper will discuss the details of the instructional methods, the results of the data analysis, present reasons for the results, and make suggestions for further study.