Education Commons^™

The Impact Of Nested Testing On Experiment-Wise Type I Error Rate, Jack Sawilowsky

Wayne State University Dissertations

When conducting a statistical test the initial risk that must be considered is a Type I error, also known as a false positive. The Type I error rate is set by nominal alpha, assuming all underlying conditions of the statistic are met. Experiment-wise Type I error inflation occurs when multiple tests are conducted overall for a single experiment. There is a growing trend in the social and behavioral sciences utilizing nested designs. A Monte Carlo study was conducted using a two layer design. Five theoretical distributions and four real datasets taken from Micceri (1989) were used, each with five different …

Factors That Are Associated With Workkeys® Assessment Scores Of Inmates In Michigan Department Of Correction's Community And Employment Readiness Training Program And Michigan State Industries Program, Pamela S. Jackson

Wayne State University Dissertations

Inmates face challenges in obtaining employment once they leave prison because many are undereducated and lack work skills. This study examined demographic and criminogenic variables of inmates in Michigan Department of Correction's (MDOC) Community and Employment Readiness Training (CERT) and Michigan State Industries (MSI) programs that were associated with their scores obtained on the WorkKeys® assessment test. MDOC uses the WorkKeys® to assess the gaps between inmates' current job readiness skill level and skills needed for various types of jobs upon release. There is no published literature comparing MDOC's Community and Employment Readiness Training (CERT) and Michigan State Industries (MSI) …

An Empirical Examination And Metaevaluation Of The Impact Evaluation Process, Anne Maechling Blake

Wayne State University Dissertations

This dissertation empirically examines the Guerra-Lopez (2007a) Impact Evaluation Process (IEP), which is a prescriptive program evaluation model. Since there is no generally accepted process for arriving at final judgments about the usefulness, appropriateness, effectiveness, reliability, and validity of evaluation models, this study used a combination of approaches to begin to build a body of evidence about the effectiveness of the IEP. Primarily, the study used Stufflebeam's (2011) recently revised Program Evaluations Metaevaluation Checklist to examine the model. The Checklist is based on the Joint Committee on Standards for Educational Evaluation's (2010) Program Evaluation Standards. Fitzpatrick, Sanders, & Worthen (2011) …

Supporting The Growth Of Principals As Instructional Leaders: An Interpretive Study About The New Work Of School Leaders, Jeffrey Thomas Hillman

Wayne State University Dissertations

This study explored the emerging context of elementary school principals as they engaged in the work of Instructional Leadership. Naturalistic Inquiry was adopted as a methodological framework to explore the unique perspectives and understandings of participants. Focus Group activities, surveys, small group interviews, and recursive ethnographic interviews were used to capture rich and descriptive representations of principal understandings. Research questions explored the experiences and conditions that participants identified as essential for their growth as Instructional Leaders. The concept of paradigm and the implications of system structures and hierarchies was investigated as it relates to the supporting conditions necessary for principal …

Descriptive Statistical Attributes Of Special Education Datasets, Valerie Felder

Wayne State University Dissertations

ABSTRACT

Descriptive Statistical Attributes of Special Education Data Sets

by

VALERIE FELDER

December 2013

Advisor: Dr. Shlomo Sawilowsky

Major: Educational Evaluation and Research

Degree: Doctor of Philosophy

Micceri (1989) examined the distributional characteristics of 440 large-sample achievement and psychometric measures. All the distributions were found to be nonnormal at alpha = .01. Micceri indicated three factors that might contribute to a non-Gaussian error distribution in the population. The first factor is subpopulations within a target population. The second factor is ceiling effects and the third factor is treatment effects that may change the location parameter, variability, or shape of the …

Estimating The Efficiency Of Michigan's Rural And Urban Public School Districts, Rita Ann Maranowski

Wayne State University Dissertations

This study examined student achievement in Michigan public school districts to determine if rural school districts are demonstrating greater financial efficiency by producing higher levels of student achievement than school districts in other geographic locations with similar socioeconomics. Three models were developed using multiple regression analysis of student achievement for high school graduation rates and student proficiency rates for eleventh grade students in mathematics and English language arts as reported from the Michigan Merit Examination results. These models compared student achievement by geographic location which included a selection of 10 independent variables and a sample size of 496 Michigan public …

Robustness Of The Achievable Benchmark Of Care Method, Jeff Arthur Capobianco

Wayne State University Dissertations

The Achievable Benchmark of Care Method is a process of care performance improvement measurement approach for identifying top performing healthcare providers. The purpose of this study was to investigate the robustness of the method. This was achieved by comparing the robustness of the standard ABC method, which uses the mean to calculate the benchmark, to versions of the ABC method where the mean was replaced with either a 5%, 10%, or 20% trimmed mean, a 15% Winsorized mean or the one-step Huber ø1.28 calculation. Monte Carlo simulations where conducted using publically available, Medicare process of care data. The mean was …

Miblsi Program Evaluuation Of Participatory Elementary Schools From 2003-20009, Marvin Gibbs

Wayne State University Dissertations

This dissertation details the use of the Program Evaluations Metaevaluation Checklist (PEMC), Stufflebeam, 1999, which is for performing final, summative metaevaluations. It is organized according to the Joint Committee Program Evaluation Standards. For each of the 30 standards the checklist includes 6 checkpoints drawn from the substance of the standard. It reports the use of the PEMC in evaluating the use of So, How Are We Doing? A MiBLSi Evaluation Study. The study shows that the PEMC could be a functional tool for a metaevaluation if modified for a specific evaluation. The results of the Kruskal- Wallis one way analysis …

The Dependent Samples T And Wilcoxon Sign Rank Maximum Test, Saverpierre Maggio

Wayne State University Dissertations

A maximum test using the parametric dependent samples t-test and the non-parametric Wilcoxon sign rank test was created using a FORTRAN program and various subroutines of the International Mathematical and Statistical Libraries (IMSL, 1980). Two tailed critical values were derived from a mixed normal distribution. Critical values obtained were at the 0.05, 0.025, 0.01 and 0.005 alpha levels via sample sizes (n) 8 through 30, 45, 60, 90 and 120. Critical values were compared to values obtained through the application of the Bonferroni correction method. It was concluded that the Bonferroni is an unnecessary method. Findings of the study are …

The Effect Of Nonrandom Selection Of Clusters In A Two Stage Cluster Design, Jason Christopher Parrott

Wayne State University Dissertations

Although not as efficient as simple random sampling, cluster sampling has been regarded as a valid sampling technique when the researcher is attempting to save cost. However in order to do so, it is necessary that random selection occurs in all stages of sampling. This simulation study examines purposeful selection of cluster sampling in the second stage of a two stage cluster design. Using Monte Carlo methods a simulation was conducted comparing the random selection of both stages of a two stage cluster sample to purposeful selection of the second stage of a two stage cluster sample. The study compares …

Tell Me More About It: A Query Into Intelligence Scores And Their Relations With Achievement And Problem Behavior, Alicia Mariana January

Wayne State University Dissertations

Research has demonstrated negative outcomes associated with significant childhood cognitive, behavioral, emotional, or academic problems. These associations may reflect the importance of cognitive skills for mediating social and emotional functioning, however the directions of these relations remain a point of contention. Additionally, most of the child research is based on early editions of the Wechsler Intelligence Scale for Children. Little attention has been given to examining the relations between behavioral adjustment, achievement, and IQ utilizing the Wechsler Intelligence Scale for Children (WISC-IV). The WISC-IV uses different subtests, index scores, and norms than its predecessors and has been described as being …

A Comparison Of The Effects Of Non-Normal Distributions On Tests Of Equivalence, Linda Ellington

Wayne State University Dissertations

Statistical theory and its application provide the foundation to modern systematic inquiry in the behavioral, physical and social sciences disciplines (Fisher, 1958; Wilcox, 1996). It provides the tools for scholars and researchers to operationalize constructs, describe populations, and measure and interpret the relations between populations and variables (Weinbach & Grinnell, 1997; Wilcox, 1996). Given that the majority of real data analysis in the behavioral and social sciences is comprised of non-normally distributed data, it is important that researchers be aware of the effects of non-normal distributions on the probability of detecting equivalence between populations.

The present study examined the effects …

Reliability Generalization: Lapsus Linguae, Julie Marilyn Smith

Wayne State University Dissertations

This study examines the proposed Reliability Generalization (RG) method for studying reliability. RG employs the application of meta-analytic techniques similar to those used in validity generalization studies to examine reliability coefficients. This study explains why RG does not provide a proper research method for the study of reliability, including describing how reliability is not a singular metric but a family of coefficients that are not interchangeable, along with other issues, such as sample and test administration. This research used Monte Carlo simulations designed to illustrate how the same instrument, administered repeatedly, can result in different reliability coefficients and to show …

Cultural Enrichment: Connecting African American Elementary Children To Academic Achievement, Deborah L. Winston

Wayne State University Dissertations

A large, growing number of mis-educated American citizens are being produced by America's public schools. Many of these students are being funneled into the penal system shortly after dropping out of high school. This phenomenon is especially prevalent among African American male students, many of whom have withdrawn academically years prior to permanently dropping out of school. Additionally, to further underscore the importance of successfully educating African American students are the debilitating effects brought about after incarceration. About 4 million people in the United States, including 1.4 million Black men (13 percent of the adult male Black population) have currently …

Approximate Vs. Monte Carlo Critical Values For The Winsorized T-Test, Michael Lance

Wayne State University Dissertations

Historically, it has been accepted practice for critical values for the Winsorized t test for independent samples to be based on adjusted degrees of freedom depending on the number of total non-Winsorized (approximate) values. Recently, a new such table of Winsorized critical values has been developed via approximate randomization by Monte Carlo simulation.

Based on eight common data distributions estimated from Psychology and Education along with the normal and five Mathematical distributions, these two tables of values were compared with respect to robustness to types I and II errors through Monte Carlo simulations for one and 10% Winsorized values per …

Development And Validation Of A Measurement Scale To Analyze The Environment For Evidence-Based Medicine Learning And Practice By Medical Residents, Fangqiong Mi

Wayne State University Dissertations

A growing number of residency programs are instituting curricula to include the component of evidence-based medicine (EBM) principles and process. However, these curricula may not be able to achieve the optimal learning outcomes, perhaps because various contextual factors are often overlooked when EBM training is being designed, developed, and implemented. The purpose of the study was to develop and validate an instrument, the EBM Environment Scale, to analyze the environment for EBM learning and practice as perceived by medical residents.

The development of the EBM Environment Scale underwent the process of content domain identification, item generation, review by content experts …