Statistical Theory Commons^™

An Error In Statistical Logic In The Application Of Genetic Paternity Testing, Ernest P. Chiodo, Joseph L. Musial, J. Sia Robinson

Journal of Modern Applied Statistical Methods

A Bayes probability computer program was written in Fortran to examine issues related to genetic paternity testing. An application was given to demonstrate the effects improper assumptions of prior probability of culpability. The seriousness of such errors include the potential of assigning paternity to wrongly accused men, or wrongly refuting paternity.

An Adaptive Inference Strategy: The Case Of Auditory Data, Bruno D. Zumbo

Journal of Modern Applied Statistical Methods

By way of an example some of the basic features in the derivation and use of adaptive inferential methods are demonstrated. The focus of this paper is dyadic (coupled) data in auditory and perceptual research. We present: (a) why one should not use the conventional methods, (b) a derivation of an adaptive method, and (c) how the new adaptive method works with the example data. In the concluding remarks we draw attention to the work of Professor George Barnard who provided the adaptive inference strategy in the context of the Behrens-Fisher problem -- testing the equality of means when one …

Parametric Analyses In Randomized Clinical Trials, Vance W. Berger, Clifford E. Lunneborg, Michael D. Ernst, Jonathan G. Levine

Journal of Modern Applied Statistical Methods

One salient feature of randomized clinical trials is that patients are randomly allocated to treatment groups, but not randomly sampled from any target population. Without random sampling parametric analyses are inexact, yet they are still often used in clinical trials. Given the availability of an exact test, it would still be conceivable to argue convincingly that for technical reasons (upon which we elaborate) a parametric test might be preferable in some situations. Having acknowledged this possibility, we point out that such an argument cannot be convincing without supporting facts concerning the specifics of the problem at hand. Moreover, we have …

Alternatives To SW In The Bracketed Interval Of The Trimmed Mean, Jennifer Bunner, Shlomo S. Sawilowsky

Journal of Modern Applied Statistical Methods

The aim of this Monte Carlo study is to examine alternatives to estimated variability in building bracketed intervals about the trimmed mean.

Generation Of Combinations Using Excel, Constantine Stamatopoulos

Journal of Modern Applied Statistical Methods

Theoretical development of combinations via enumeration methods are considered. An Excel macro is provided.

Jmasm1: Rangen 2.0 (Fortran 90/95), Gail F. Fahoome

Journal of Modern Applied Statistical Methods

Rangen 2.0 is Fortran 90 module of subroutines used to generate uniform and nonuniform pseudo-random deviates. It includes uni1, an uniform pseudo-random number generator, and non-uniform generators based on unil. The subroutines in Rangen 2.0 were written using Essential Lahey Fortran 90, a proper subset of Fortran 90. It includes both source code for the subroutines and a short description of each subroutine, its purpose, and the arguments including data type and usage.

Asymptotic And Exact Tests In 2 X C Ordered Categorical Contingency Tables With Statxact 2.0 - 4.0, Margaret Posch

Journal of Modern Applied Statistical Methods

The purpose of this study was to compare the statistical power of a variety of exact tests in the 2 x C ordered categorical contingency table using StatXact software. The Wilcoxon Rank Sum, Expected Nonnal Scores, Savage Scores (or its Log Rank equivalent), and Permutation tests were studied. Results indicated that the procedures were nearly the same in terms of comparative statistical power.

Quantifying Bimodality Part I: An Easily Implemented Method Using Spss, B. W. Frankland, Bruno D. Zumbo

Journal of Modern Applied Statistical Methods

Scientists in a variety of fields are faced with the question of whether or not a particular sample of data are best described as unimodal or bimodal. We provide a simple and convenient method for assessing bimodality. The use of the non-linear algorithms in SPSS for modeling complex mixture distributions is demonstrated on a unimodal normal distribution (with 2 free parameters) and on bimodal mixture of two normal distributions (with 5 free parameters).

A Measure Of Relative Efficiency For Location Of A Single Sample, Shlomo S. Sawilowsky

Journal of Modern Applied Statistical Methods

The question of how much to trim or which weighting constant to use are practical considerations in applying robust methods such as trimmed means (L-estimators) and Huber statistics (M-estimators). An index oflocation relative efficiency (LRE), which is a ratio of the narrowness of resulting confidence intervals, was applied to various trimmed means and Huber M-estimators calculated on seven representative data sets from applied education and psychology research. On the basis of LREs, lightly trimmed means were found to be more efficient than heavily trimmed means, but Huber M-estimators systematically produced narrower confidence intervals. The weighting constant of ψ = 1.28 …

Two-Sided Equivalence Testing Of The Difference Between Two Means, R. Clifford Blair, Stephen R. Cole

Journal of Modern Applied Statistical Methods

Studies designed to examine the equivalence of treatments are increasingly common in social and biomedical research. Herein, we outline the rationale and some nuances underlying equivalence testing of the difference between two means. Specifically, we note the odd relation between tests of hypothesis and confidence intervals in the equivalence setting.

Jmasm3: A Method For Simulating Systems Of Correlated Binary Data, Todd C. Headrick

Journal of Modern Applied Statistical Methods

An efficient algorithm is derived for generating systems of correlated binary data. The procedure allows for the specification of all pairwise correlations within each system. Intercorrelations between systems can be specified qualitatively. The procedure requires the simultaneous solution of a system of equations for obtaining the threshold probabilities to generate each system of binary data. A numerical example is provided to demonstrate that the procedure generates correlated binary variables that yield correlations in close agreement with the specified population correlations.

Combining Two Nonparametric Tests Of Location, R. Clifford Blair

Journal of Modern Applied Statistical Methods

A distribution-free test is proposed whose power is similar to that of the Wilcoxon Rank-Sum or Terry-Hoeffding Normal Scores tests depending on which of these two tests is more powerful in a given data analysis situation, regardless of the population. This new statistic is distribution-free, and adds no new assumptions to those associated with the constituent tests. A table of critical values for the new statistic is given and some of its Type I error and power properties are examined.

An Unconditional Exact Test For Small Samples Matched Binary Pairs, Robert A. Malkin

Journal of Modern Applied Statistical Methods

When investigators have N pairs of binary data, a common test for an increased rate of response is McNemar's test. However, McNemar's is an approximate, conditional test. An exact, unconditional test exists, but requires restrictive assumptions. Critical values and power tables are presented for an exact, unconditional test free of these assumptions.

Hotelling's T2 Vs. The Rank Transform With Real Likert Data, Michael J. Nanna

Journal of Modern Applied Statistical Methods

Monte Carlo research has demonstrated that there are many applications of the rank transformation that result in an invalid procedure. Examples include the two dependent samples, the factorial analysis of variance, and the factorial analysis of covariance layouts. However, the rank transformation has been shown to be a valid and powerful test in the two independent samples layout. This study demonstrates that the rank transformation is also a robust and powerful alternative to the Hotellings T² test when the data are on a Likert scale.

Applying Spatial Randomness To Community Inclusion, Michael Wolf-Branigin

Journal of Modern Applied Statistical Methods

A spatial analytic methodology incorporating true locations is demonstrated using Monte Carlo simulations as a complement to current psychometric and quality of life indices for measuring community inclusion. Moran's I, a measure of spatial autocorrelation, is used to determine spatial dependencies in housing patterns for multiple variables, including family/friends involvement in future planning, home size, and earned income. Simulations revealed no significant spatial autocorrelation, which is a socially desirable result for housing locations for people with disabilities. Assessing the absence of clustering provides a promising methodology for measuring community inclusion.

Shifting Goals And Mounting Challenges For Statistical Methodology, Pranab K. Sen

Journal of Modern Applied Statistical Methods

Modern interdisciplinary research in statistical science encompasses a wide field: agriculture, biology, biomedical sciences along with bioinformatics, clinical sciences, education, environmental and public health disciplines, genomic science, industry, molecular genetics, socio-behavior, socio-economics, toxicology, and a variety of other disciplines. Statistical science has historically had mathematical perspectives dominating theoretical and methodological developments. Yet, the advent of modern information technology has opened the doors for highly computation intensive statistical tools (i.e., software), wherein mathematical aspects are often de-emphasized. Knowledge discovery and data mining (KDDM) is now becoming a dominating force, with bioinformatics as a notable example. In view of this apparent discordance …

The Q-Sort Method: Assessing Reliability And Construct Validity Of Questionnaire Items At A Pre-Testing Stage, Abraham Y. Nahm, S. Subba Rao, Luis E. Solis-Galvan, T. S. Ragu-Nathan

Journal of Modern Applied Statistical Methods

This paper describes the Q-sort, which is a method of assessing reliability and construct validity of questionnaire items at a pre-testing stage. The method uses Cohen's Kappa and Moore and Benbasat's Hit Ratio in assessing the questionnaire.

Using The T Test With Uncommon Sample Sizes, Shlomo S. Sawilowsky, Barry S. Markman

Journal of Modern Applied Statistical Methods

Monte Carlo techniques were used to determine the effect of using common critical values as an approximation for uncommon sample sizes. Results indicate there can be a significant loss in statistical power. Therefore, even though many instructors now rely on computer statistics packages, the recommendation is made to provide more specificity (i.e., values between 30 and 60) in tables of critical values published in textbooks.

Modeling Strategies In Logistic Regression With Sas, Spss, Systat, Bmdp, Minitab, And Stata, Chao-Ying Joanne Peng, Tak-Shing Harry So

Journal of Modern Applied Statistical Methods

This paper addresses modeling strategies in logistic regression within the context of a real-world data set. Six commercially available statistical packages were evaluated in how they addressed modeling issues and in the accuracy of their regression results. Recommendations are offered for data analysts in terms of each package's strengths and weaknesses.

Rank-Based Procedures For Mixed Paired And Two-Sample Designs, Suzanne R. Dubnicka, R. Clifford Blair, Thomas P. Hettmansperger

Journal of Modern Applied Statistical Methods

This paper presents a rank-based procedure for parameter estimation and hypothesis testing when the data are a mixture of paired observations and independent samples. Such a situation may arise when comparing two treatments. When both treatments can be applied to a subject, paired data will be generated. When it is not possible to apply both treatments, the subject will be randomly assigned to one of the treatment groups. Our rank-based procedure allows us to use the data from the paired sample and the independent samples to make inferences about the difference in the mean responses. The rank-based procedure uses both …

Statistical Calibration Theory, James John Mckeon

Mathematics & Statistics Theses & Dissertations

A calibration method substitutes for measurements, X(,i), that are accurate but impractical or costly, a set of measurements, Y(,i), that are less accurate but simpler or less costly. There are two general types of calibration methods. The classical approach in which once the calibration sample is drawn, the estimates of the X values for a given unit is found without any consideration of the distribution of X values for the other units to be measured. This corresponds best to the literal meaning of the word "calibration". Maximum likelihood estimation is the statistical formulation of the classical approach.

The second approach …