Stephen Kokoska

The analysis of cancer chemoprevention experiments

This paper is concerned with the analysis of certain cancer chemoprevention experiments that involve Type I censoring. In experiments of this nature, two common response variables are the number of induced cancers and the rate at which they develop. In this study we assume that the number of induced tumors and their times to detection are described by the Poisson and gamma distributions, respectively. Using the method of maximum likelihood, we discuss a procedure for estimating the parameters characterizing these two distributions. We apply standard techniques in order to construct a confidence region and conduct a hypothesis test concerning the parameters of interest. We discuss a method for comparing the effects of two different treatments using the likelihood ratio principle. A technique for isolating group differences in terms of the mean number of promoted tumors and the mean time to detection is described. Using the techniques developed in this paper, we reanalyze an existing data set in the cancer chemoprevention literature and obtain contrasting results.

Stressors and Family Supports: Families with Children Using Augmentative & Alternative Communication Technology

A statewide survey was conducted in cooperation with the Pennsylvania Assistive Technology Center of Harrisburg to identify the stressors and family supports of 59 families with young children between the ages of 3 and 12 years who use AAC technology and technology services. Descriptive statistics and correlations were used to analyze the data. Parenting Stress Index results revealed both fathers and mothers perceived the child-related variables of acceptance and demandingness as stressful. Results revealed differences for parent-related variables for mothers and fathers. Data derived from the Family Support Scale revealed significant differences for mothers and fathers with regard to the helpfulness of social supports. Implications for family-centered intervention and future research are discussed.

CRC Standard Probability and Statistics Tables and Formulae, Student Edition

Introduction Summarizing Data Probability Functions of Random Variables Discrete Probability Distributions Continuous Probability Distributions Standard Normal Distribution Estimation Confidence Intervals Hypothesis Testing Regression Analysis Analysis of Variance Experimental Design Nonparametric Statistics Quality Control and Risk Analysis General Linear Models Miscellaneous Topics Special Functions

Critical Values For The Wilcoxon Signed-Rank Statistic

This table contains critical values and probabilities for the Wilcoxon Signed-Rank Statistic T+; n is the sample size, c1 and C2 are defined by P(T+ ≤ c1) = α and P(T+ ≥ C2) = α.

Including data from early deaths in the analysis of cancer chemoprevention experiments

Abstract This article addresses the very important problem of proper analysis of cancer chemoprevention experiments. In the experiments we consider, the number of observed tumors per animal and their times to detection are available for analysis. Very often however, animals die prior to termination of a study. These animals are often discounted from subsequent analysis, which wastes resources and may bias conclusions. There is also confounding of the number of induced tumors and their times to detection. The statistical procedures described in this paper modify an existing technique, which explicitly acknowledges the confounding inherent in these experiments, in order to provide a valid method for including early deaths in the analysis

The Development and Analysis of Interactive Videodisc Technology to Teach Speechreading

Members of the Department of Communication Disorders and Special Education and the Institute for Interactive Technologies at Bloomsburg University developed a computer-based interactive videodisc instructional program to teach speechreading skills. Speechreading Challenges on Videodisc provides users with practice in speechreading words, sentences, and stories presented by over 150 people in a user friendly environment. Unlike traditional videotapes, videodisc technology provides immediate feedback to the user. To determine the programs effectiveness in teaching speechreading, a comprehensive evaluation of the program was undertaken. Seventy-four college students participated in a study using the program to learn speechreading. Results indicated a statistically significant improvement in speechreading ability from pretest to posttest measures on both the videodisc program evaluation as well as on the Costello Test of Speechreading.

Critical Values For The Studentized Range Distribution

This table contains critical values Qα,k,v for the Studentized Range distribution defined by P(Q ≥ Qα,k,v) = α, k is the number of degrees of freedom in the numerator (the number of treatment groups) and v is the number of degrees of freedom in the denominator (s2).

The analysis of cancer chemoprevention experiments in which there is interval censoring

Abstract In certain types of cancer chemoprevention experiments animals are examined for the appearance of tumors over the duration of the investigation. If the experimental animals are inspected frequently enough, then it is reasonable to assume that the times to tumor detection accurately represent the times the cancers reach detectable size. If examinations are conducted less frequently, this assumption is not justified. In such experiments, each detectable tumor is associated with a time interval rather than a specific time point. In this paper we introduce a parametric method for the statistical analysis of experiments in which there is interval censoring that explicitly acknowledges the confounding of the number of induced tumors and tumor growth rate.

The analysis of cancer chemoprevention experiments In which there is heterogeneous poisson sampling

Abstract In certain cancer chemoprevention experiments both the number of observed tumors per animal and their times to detection are used in subsequent statistical analyses. The mathematical models used to represent these experiments usually include the Poisson distribution to characterize the tumor multiplicity data. Very often however, there is excess variance due to interanimal heterogeneity of tumor response. Thus, the number of induced tumors is better characterized by the negative binomial distribution. In this paper we modify an existing statistical technique, which explicitly acknowledges the confounding inherent in these systems, in order to provide a more efficient procedure for utilizing the information in a sample and to more accurately assess treatment effects.

Life Expectancy of Major League Baseball Umpires

ABSTRACT BACKGROUND: The on-field death 4 years ago of a veteran Major League Baseball (MLB) umpire raised questions regarding the mortality risks ot this profession. OBJECTIVE: To determine if the life expectancy of MLB umpires differs from that of the general population. DESIGN: Ages of death of MLB umpires were determined, and the differences between the ages of death and age-adjusted life expectancies were calculated. T-score analysis was performed on these differences. Correlational analysis was also done on many different factors, including umpire debut year, debut age, life expectancy at debut, and length of career. RESULTS: No significant difference was found between the age at death of MLB umpires and their age-adjusted life expectancy. Correlational analyses showed that only length of career correlated with age at death. CONCLUSION: MLB umpiring is not associated with a shortened life expectancy. While this is most likely attributable to the profession having no inherent risk, it could also be explained by inherent risks being overcome by yet unidentified, unique factors.