Papers by Dr. Mitchell Colp
Testing the equality of variances during hypothesis testing is an important preliminary step befo... more Testing the equality of variances during hypothesis testing is an important preliminary step before using statistical tests such as the t-test or ANOVA. It has been demonstrated that many tests for equality of variances are sensitive to non-normal distributions. Using computer simulation, the present simulation study investigates the Type I error rate and statistical power of the nonparametric and median versions of the Levene test for equality of variances when there are three, four or five groups used in the analysis. For each of the three, four and five group conditions there are several levels of sample size, variance ratio, group sample size imbalance, and degree of skew in the population distribution included in the simulation. Results show that the nonparametric Levene test shows good statistical properties when samples come from heavily skewed population distributions, when overall sample size was small, and when groups were unbalanced. The findings also allow for a relative...
Practical Assessment, Research and Evaluation, 2018
Often, when testing for shift in location, researchers will utilize nonparametric statistical tes... more Often, when testing for shift in location, researchers will utilize nonparametric statistical tests in place of their parametric counterparts when there is evidence or belief that the assumptions of the parametric test are not met (i.e., normally distributed dependent variables). An underlying and often unattended to assumption of nonparametric tests of location is that of identical distributions. The assumption of identical distributions requires that distributions conform to one another in terms of variability and shape (i.e., variance, skew and kurtosis). The purpose of the current study is to demonstrate, via the use of Monte Carlo simulation, the assumption of identical distribution using the Wilcoxon-Mann-Whitney (WMW) test and the Student t-test for comparison. For each of the conditions, there are several levels of sample size, variance ratio, group sample size ratio, and degree of skew in the parent distribution. Empirical Type I error rates are compared to nominal Type I e...
It is undisputed that raising children with an Autism Spectrum Disorder (ASD) can be an isolating... more It is undisputed that raising children with an Autism Spectrum Disorder (ASD) can be an isolating and stressful experience for families. Children diagnosed with this disorder can vary considerably in terms of their adaptive functioning, cognitive ability, and functional communication, and this collectively compounds an individual’s ability to parent effectively. Adding to this strain, early intervention programs which address these foundational difficulties are costly and government assistance is greatly reduced as children age. As a result, many early intervention programs have attempted to empower parents through providing coaching, tools, and strategies for them to apply at home. While previous research has examined the gains associated with specific early intervention programs, limited research has been completed which evaluates parental confidence for implementing direct interventions after government assistance declines and/or parents prepare to leave these services. This study examined the confidence of parents who were transitioning out of an early intervention program called Specialized Autism Services, facilitated by Renfrew Educational Services in Calgary, AB. The results of this study will highlight the importance of evaluating parental confidence as a factor of intervention success.
A common design strategy utilized in psycho-educational research is matching. Through adopting th... more A common design strategy utilized in psycho-educational research is matching. Through adopting this procedure, influential variables are held constant to increase the sensitivity of statistical tests used to detect significant differences between groups. An issue related to matching is its implementation when researchers wish to match using multifaceted constructs, such as intelligence. A review of online research databases highlights a number of recent studies which utilize an overall intelligence value, provided by norm-referenced instruments, as their initial matching variable (e.g., MacCabe et al, 2012). Difficulties emerge in utilizing such techniques because overall intelligence values generally represent an unequally weighted composite of multiple sub-factors (e.g., perceptual reasoning). That is, utilizing a composite value for the purpose of matching may silence important discrepancies found within individual sub-factors and have significant repercussions for research conclusions. This study demonstrates the gravity of this methodological issue by analyzing ≥300 intellectual assessment reports from the University of Calgary Applied Psychological and Educational Service’s data repository and using multidimensional profile analysis to highlight the within-participant intellectual variance.
Pediatrics, 2015
This article reviews current evidence for autism spectrum disorder (ASD) interventions for childr... more This article reviews current evidence for autism spectrum disorder (ASD) interventions for children aged <3 years, based on peer-reviewed articles published up to December 2013. Several groups have adapted treatments initially designed for older, preschool-aged children with ASD, integrating best practice in behavioral teaching methods into a developmental framework based on current scientific understanding of how infants and toddlers learn. The central role of parents has been emphasized, and interventions are designed to incorporate learning opportunities into everyday activities, capitalize on "teachable moments," and facilitate the generalization of skills beyond the familiar home setting. Our review identified several comprehensive and targeted treatment models with evidence of clear benefits. Although some trials were limited to 8- to 12-week outcome data, enhanced outcomes associated with some interventions were evaluated over periods as long as 2 years. Based on...
The present study explored the coping strategies used by victims of school bullying. Though victi... more The present study explored the coping strategies used by victims of school bullying. Though victims of bullying have been repeatedly shown to experience considerable and lasting negative outcomes (Hawker & Boulton, 2000), some victims are able to recover and successfully “bounce back” from being bullied (Willis & Griffith, 2010). The use of adaptive coping strategies may explain why some victims effectively cope while others suffer negative outcomes (Hunter & Boyle, 2010). Fifty-three participant reports on strategy use were examined through thematic analysis. A coping model emerged which included two primary themes: active and passive coping strategies. Seven sub-themes were also identified. Subsequent quantitative analyses suggest that strategy use significantly predicts positive beliefs about bullying and ego resilience. Adaptive coping strategy use may help to explain why some victims of bullying successfully “bounce back.”
Testing the equality of variances during hypothesis testing is an important preliminary step befo... more Testing the equality of variances during hypothesis testing is an important preliminary step before using statistical tests such as the t-test or ANOVA. It has been demonstrated that many tests for equality of variances are sensitive to non-normal distributions. A nonparametric Levene test was introduced by Nordstokke and Zumbo (2010) and has been shown to have good statistical properties in both simulated and real data settings (Nordstokke & Zumbo, 2010; Nordstokke, Zumbo, Cairns, & Saklofske, 2011). Using computer simulation, the present paper investigates the ANOVA case of the nonparametric Levene when there are three, four or five groups included in the analysis. For each of the three, four and five group conditions there will be several levels of sample size, variance ratio, group sample size imbalance, and degree of skew in the population distribution included in the simulation. To be consistent with Nordstokke and Zumbo (2010), the simulation includes results of the test that...
Resilience is often conceptualized as a unidimensional construct that is composed by intrinsic an... more Resilience is often conceptualized as a unidimensional construct that is composed by intrinsic and extrinsic factors that have the ability to augment or hinder an individuals’ likelihood of overcoming challenges (Kaplan, 1999). While modeling resilience in this manner has proven useful in the past, many researchers have argued that such an approach has been fundamentally flawed (e.g., Masten, Best, & Garmezy, 1990). Recognizing this argument, constructs such as academic resilience were created to offer greater assessment and prediction specificity to resilience research. Academic resilience can be defined as the increased likelihood of educational success despite personal adversities or vulnerabilities brought on by environmental conditions. Over the years, research into the construct of academic resilience has primarily occurred secondary learning level and is reflected in our contemporary measurement practices (Martin and Marsh, 2006). The purpose of this study is to examine the p...
Encyclopedia of Quality of Life and Well-Being Research, 2014
Reading & Writing Quarterly, 2019
Grade 4 represents a critical juncture in the literacy development of young students. This articl... more Grade 4 represents a critical juncture in the literacy development of young students. This article explores the role of handwriting in unlocking the higher order psycholinguistic and metacognitive resources needed to compose quality text. In particular, we investigate the threshold of control over handwriting needed to unlock vocabulary that contributes the greatest proportion of the variance in the quality of 245 students’ writing samples. Using online vocabulary profiling tools we tap 2 measures of vocabulary use in addition to a standard vocabulary measure. Outcomes provide direction to classroom practitioners for focusing sustained instructional attention on handwriting in the Grade 4 year, ongoing vocabulary work, and metacognitive strategies in the writing process that have potential for ameliorating academic literacy outcomes.
Practical Assessment, Research & Evaluation, 2018
This computer simulation study evaluates the robustness of the nonparametric Levene test of equal... more This computer simulation study evaluates the robustness of the nonparametric Levene test of equal variances (Nordstokke & Zumbo, 2010) when sampling from populations with unequal (and unknown) means. Testing for population mean differences when population variances are unknown and possibly unequal is often referred to as the Behrens-Fisher problem when the populations are normally distributed, and the generalized Behrens-Fisher problem when the populations are nonnormal. The nonparametric Levene test was developed to overcome reductions in power of the original Levene test of equal variances in the case of the generalized Behrens-Fisher problem. We use a Monte Carlo computer simulation to demonstrate that sampling from populations with unequal and unknown means can lead to incorrect (either inflated or decreased) Type I error rates of the nonparametric Levene test. Centering samples using either sample means or medians does not correct the Type I error rates. This note is intended to make applied researchers aware of this problem when testing for the equality of population variances with the NPL test and in general.
Practical Assessment, Research & Evaluation, 2018
Often, when testing for shift in location, researchers will utilize nonparametric statistical tes... more Often, when testing for shift in location, researchers will utilize nonparametric statistical tests in place of their parametric counterparts when there is evidence or belief that the assumptions of the parametric test are not met (i.e., normally distributed dependent variables). An underlying and often unattended to assumption of nonparametric tests of location is that of identical distributions. The assumption of identical distributions requires that distributions conform to one another in terms of variability and shape (i.e., variance, skew and kurtosis). The purpose of the current study is to demonstrate, via the use of Monte Carlo simulation, the assumption of identical distribution using the Wilcoxon-Mann-Whitney (WMW) test and the Student t-test for comparison. For each of the conditions, there are several levels of sample size, variance ratio, group sample size ratio, and degree of skew in the parent distribution. Empirical Type I error rates are compared to nominal Type I error rates to determine the validity of the result for each run of the simulation. Violation of the assumption of identical distributions lead to bias in the result of the WMW test and the Student t-test. Practical implications are also discussed.
Canadian Journal of School Psychology, 2014
The following paper outlines a review of the Insight Test of Cognitive Abilities.
Thesis Chapters by Dr. Mitchell Colp
PhD Dissertation: University of Calgary, 2015
Entry into post-secondary studies from high school presents students with an assortment of challe... more Entry into post-secondary studies from high school presents students with an assortment of challenges that extend far beyond conventional academic demands. These students are often required to modify their orientations to learning, foster, and maintain new social support networks, manage complex responsibilities, regulate personal freedoms, and navigate the many environmental and psychological stressors that will likely appear along the way. In the empirical literature, there is consensus that high school grade point average (HSGPA) represents the best predictor of success during this time of transition. Although HSGPA is often used to screen for entrance into higher education, little is known as to how or why it facilitates positive adjustment. Some have argued that HSGPA is influential because it is represents an interaction of internal and external factors. The purpose of this study was to undertake an empirical investigation to determine whether academic resilience, as defined by specific traits found within students that help them overcome situational adversity to achieve academically, mediates the relation between HSGPA and post-secondary success (i.e., achievement and retention outcomes). Using structural equation modeling, the responses from 655 first-year undergraduate participants were examined and demonstrated positive findings. Specifically, academic resilience accounted for approximately 5% of shared variance between HSGPA and post-secondary academic achievement. Due to the limited number of students who identified themselves as leaving academic studies, the mediational properties of academic resilience could not be explored within the context of post-secondary retention. The limitations of this study and future directions are discussed in relation to the obtained results.
MSc Thesis: University of Calgary, 2012
It has been well-documented that combined phonological awareness and word-identification training... more It has been well-documented that combined phonological awareness and word-identification training provide the most effective way of strengthening reading ability in children with Reading Disabilities (RDs). With that said, these findings are based on the assumption that all children with RDs represent a homogenous population and react similarly to specific intervention approaches. Recognizing the heterogeneity within the RD population, preliminary research has surfaced which challenges the combined approach in favor of techniques which address the relative deficit in either phonological or word-discrimination (orthographic) processes. Continuing in this line of research, a study was conducted to examine the effectiveness of an orthographic-based intervention design to improve reading ability for children with orthographic skill deficits. The study took place at a private, not-for-profit, school designed for children with a variety of Learning Disabilities. Through utilizing a single-case multiple-baseline research design, 12 children with RDs in grades 3 through 6 (3 students per grade) were matched on reading ability and intelligence prior to beginning the intervention. The results of this study will be discussed in relation to the importance of assessing and intervening for specific reading difficulties within RD populations.
Uploads
Papers by Dr. Mitchell Colp
Thesis Chapters by Dr. Mitchell Colp