Physical Sciences and Mathematics Commons^™

Cohomology Operations On Random Spaces, Matthew John Zabka

Wayne State University Dissertations

Topology has recently received more attention from statisticians as some its tools have been applied to understanding the shape of data. In particular, a data set can generate a topological space, and this space’s topological structure can give us insight into some properties of the data. This framework has made it necessary to study random spaces generated by data. For example, without an understanding of the probabilistic properties of random spaces, one cannot conclude with any degree of confidence what the tools of topology tell us about a data set. While some results are known about the cohomological structure of …

The Impact Of Multiple Imputation On The Type Ii Error Rate Of The T Test, Tammy A. Grace

Wayne State University Dissertations

ABSTRACT

THE IMPACT OF MULTIPLE IMPUTATION ON THE TYPE II ERROR RATE OF

THE T TEST

by

TAMMY A. GRACE

August 2016

Advisor: Shlomo Sawilowsky, PhD

Major: Evaluation and Research

Degree: Doctor of Philosophy

The National Academy of Science identified numerous high priority areas for missing data research. This study addresses several of those areas by systematically investigating the impact of multiple imputation on the rejection rate of the independent samples t test under varying conditions of sample size, effect size, fraction of missing data, distribution shape, and alpha. In addition to addressing gaps in the missing data literature, this …

Consensus Regularized Selection Based Prediction, Ping Wang

Wayne State University Theses

Integrating regularization methods within a regression framework has become a popular choice for researchers to build predictive models with lower variance and better generalization. Regularizers also aid in building interpretable models with high-dimensional data which makes them very appealing. Regularizers in general are unique in nature as they cater to data specific features such as correlation, structured sparsity, and temporal smoothness. The problem of obtaining a consensus among such diverse regularizers is extremely important in order to determine the optimal regularizer for the model. This is called the consensus regularization problem which has not received much attention in the literature, …

Distribution-Free Trends Test To Determine The Construct Validity Of An Anti-Social Criminal Attitudes Scale, Holly Ann Child

Wayne State University Dissertations

The Sawilosky's I-Test was developed to as an alternative method to evaluate construct validity, more specifically, in regards to the Multitrait-Multimethod Matrix designed by Campbell and Fiske (1959). Typically, researchers use a method by Campbell and Fiske that involves a subjective “physical” look at the matrix to determine validity. Sawilowsky’s I-Test offers a statistical approach that incorporates the current practice but removes the subjectivity involved in this process.

There are only two existing studies that look at the I-Test, Sawilowsky in 2002 and Cuzzocrea in 2007. Both studies found that although the I-Test is not a perfect statistic, it provides …

Estimating Effects Of Non-Normality In Assessing Structural Equation Model Fit For Use Of Physical Science Data, Sarah Rose

Wayne State University Dissertations

ABSTRACT

ESTIMATING EFFECTS OF NON-NORMALITY IN ASSESSING

STRUCTURAL EQUATION MODEL FIT FOR USE OF PHYSICAL SCIENCE DATA

by

SARAH ALTA ROSE

May 2016

Advisor: Dr. Barry Markman

Major: Education (Evaluation and Research)

Degree: Doctor of Philosophy

The purpose of this study was to evaluate the sensitivity of selected fit index statistics in determining model fit when the distribution varied from normality, as is typically true of data research for the physical sciences. SEM is a popular statistical method and is used in many physical and social behavioral science research projects; however, the sensitivity of the model fit indices when normality …