Amy Wagler

Addressing the Lack of Measurement Invariance for the Measure of Acceptance of the Theory of Evolution

The Measure of Acceptance of the Theory of Evolution (MATE) was constructed to be a single-factor instrument that assesses an individuals overall acceptance of evolutionary theory. The MATE was validated and the scores resulting from the MATE were found to be reliable for the population of inservice high school biology teachers. However, many studies have utilized the MATE for different populations, such as university students enrolled in a biology or genetics course, high school students, and preservice teachers. This is problematic because the dimensionality and reliability of the MATE may not be consistent across populations. It is not uncommon in science education research to find examples where scales are applied to novel populations without proper assessment of the validity and reliability. In order to illustrate this issue, a case study is presented where the dimensionality of the MATE is evaluated for a population of non-science major preservice elementary teachers. With this objective in mind, factor analytic and item response models are fit to the observed data to provide evidence for or against a one-dimensional latent structure and to detect which items do not conform to the theoretical construct for this population. The results of this study call into question any findings and conclusions made using the MATE for a Hispanic population of preservice teachers and point out the error of assuming invariance across substantively different populations.

Finding a Happy Median: Another Balance Representation for Measures of Center

This paper explores the use of a lesser-known dynamic model for the median, a foundational topic that starts in the middle school curriculum and is associated with student misconceptions and knowledge gaps. This model appears to offer a rich vehicle to explore the median interactively in greater conceptual depth that includes some of its more subtle associated ideas. An exploratory study to assess performance of this model in a class for pre-service middle school teachers yielded evidence that students who completed the dataset sequence associated with the model gained further insight about the median, especially concerning how the mean and median are affected differently by outliers. Analyses of open ended questions as well as empirical results of multiple-choice questions are used to assess the overall learning outcomes gained by students. A one-minute video is offered to illustrate key points of the model.

Assessing Effectiveness of Mnemonics for Tertiary Students in a Hybrid Introductory Statistics Course

ABSTRACT Mnemonics (memory aids) are often viewed as useful in helping students recall information, and thereby possibly reducing stress and freeing up more cognitive resources for higher-order thinking. However, there has been little research on statistics mnemonics, especially for large classes. This article reports on the results of a study conducted during two consecutive fall semesters at a large U.S. university. In 2014, a large sample (n = 1487) of college students were asked about the usefulness of a set of 19 published statistics mnemonics presented in class, and in 2015, the students (n = 1468) were presented 12 mnemonics related to inference and then asked whether or not they used mnemonics on that exam. This article discusses how students assess the usefulness of mnemonics and evaluates the relationship between using mnemonics and reducing anxiety. Additionally, the relationship between mnemonic usage and learning outcomes achievement will be discussed, along with this studys limitations and implications for teaching.

Beliefs about Future Curriculum: How Avoidance Emotions Affect Curriculum Choice in Science

This article investigates how emotions of avoidance affect curriculum choice in a science classroom and also evaluates a research-based social form of learning for changing emotions of avoidance towards a specific science topic (arachnids) for a population of preservice teachers. It was found that there is a strong invariant structural relationship between emotions of avoidance and beliefs about incorporation of science concepts about arachnids. However, participation in the arachnid learning activities decreased emotions of avoidance and increased beliefs about incorporation into a science classroom. The implications of these findings are that social forms of learning can change avoidance emotions and beliefs of teachers and may even be effective for addressing other classroom topics that are socially sensitive, such as biological evolution or climate change.

Confidence Intervals for Assessing Heterogeneity in Generalized Linear Mixed Models

Generalized linear mixed models are frequently applied to data with clustered categorical outcomes. The effect of clustering on the response is often difficult to practically assess partly because it is reported on a scale on which comparisons with regression parameters are difficult to make. This article proposes confidence intervals for estimating the heterogeneity due to clustering on a scale that is easy to interpret. The performance of the proposed asymptotic intervals and percentile bootstrap intervals are compared by simulations and in an application.

Bias-Reduced Simultaneous Confidence Bands on Generalized Linear Models With Restricted Predictor Variables

When multiple inferences on the mean response of a generalized linear model are utilized to make overall decisions, control of the familywise error rate is warranted. Moreover, in many applications, the predictor variable does not span Euclidean space but can reasonably be restricted to a smaller domain. Simultaneous intervals for the mean response of generalized linear models are presented that (1) control the family-wise error rate over a restricted predictor variable space, (2) provide less conservative simultaneous bounds than when utilizing the Scheffé critical value, (3) reduce bias in the interval estimates, and (4) avoid inestimable cases due to separability of the data. Simulations provide evidence that the proposed bias-reduced simultaneous bounds are preferable to MLE-based Scheffé bounds in a wide variety of settings.

Fear and Disgust of Spiders: Factors that Limit University Preservice Middle School Science Teachers

Spiders perform many essential ecological services, yet humans often experience negative emotions toward spiders. These emotions can lead to the avoidance of beneficial events. These emotions may affect beliefs about what should or should not be included in a science curriculum. This study investigated how activities with living spiders affected preservice middle school science teachers’ emotions and beliefs. Prior to the activities both groups (i.e., treatment and control) had moderate to extreme fear and disgust toward the spider. The teachers that participated in the spider activities (i.e., treatment group) had much lower levels of fear and disgust after performing the spider activities than the control group that did not participate in the spider activities. The control group continued to have elevated levels of fear and disgust toward the spider throughout the study. Before the spider activities neither group planned to incorporate information about spiders or information about the essential ecological services of spiders into their science classroom. After the treatment group participated in the spider activities, the teachers had definitive plans to teach their students about spiders and the essential ecological services that they provide. The control group remained unchanged and had no plans to teach this information to their students.

OncoMiner: A Pipeline for Bioinformatics Analysis of Exonic Sequence Variants in Cancer

With recent developments in high-throughput sequencing technologies, whole exome sequencing (WES) data have become a rich source of information from which scientists can explore the overall mutational landscape in patients with various types of cancers. We have developed the OncoMiner pipeline for mining WES data to identify exonic sequence variants, link them with associated research literature, visualize their genomic locations, and compare their occurrence frequencies among different groups of subjects. This pipeline, written in Python on an IBM High-Performance Cluster, HPC Version 3.2, is accessible at oncominer.utep.edu. It begins with taking all the identified missense mutations of an individual and translating the affected genes based on Genome Reference Consortium’s human genome build 37. After constructing a list of exonic sequence variants from the individual, OncoMiner uses PROVEAN scoring scheme to assess each variant’s functional consequences, followed by PubMed searches to link the variant to previous reports. Users can then select subjects to visualize their PROVEAN score profiles with Circos diagrams and to compare the proportions of variant occurrences between different groups using Fisher’s exact tests. As such statistical comparisons typically involve many hypothesis tests, options for multiple-test corrections are included to control familywise error or false discovery rates. We have used OncoMiner to analyze variants of cancer-related genes in 14 samples taken from patients with cancer, six from cancer cell lines, and ten from normal individuals. Variants showing significant differences between the cancer and control groups are identified and experiments are being designed to elucidate their roles in cancer.

Assessing the Lexico-Grammatical Characteristics of a Corpus of College-Level Statistics Textbooks: Implications for Instruction and Practice:

A corpus of current editions of statistics textbooks was assessed to compare aspects and levels of readability for the topics of measures of center, line of fit, regression analysis, and regression inference. Analysis with lexical software of these text selections revealed that the large corpus can be described well by three index variables that summarize the lexical and grammatical complexity of the textbook excerpts. Assessment of those three variables indicates that substantial differences exist in the readability of the topics within textbooks with respect to lexical and grammatical complexity. This analysis suggests that general readability of introductory statistics topics within textbooks varies substantially and it is a recommendation that instructors: (1) be prepared to provide additional support for topics that are more grammatically and lexically complex, and (2) be aware that they can input their instructional materials into LexTutor VP or Coh-metrix as a quick screen for possible readability issues.

Improved simultaneous intervals for linear combinations of parameters from generalized linear models

When employing generalized linear models, interest often focuses on estimation of odds ratios or relative risks. Additionally, researchers often make overall conclusions, requiring accurate estimation of a set of these quantities. Consequently, simultaneous estimation is warranted. Current simultaneous estimation methods only perform well in this setting when there are a very small number of comparisons and/or the sample size is relatively large. Additionally, the estimated quantities can have significant bias especially at small sample sizes. The proposed bounds: (1) perform well for a small or large number of comparisons, (2) exhibit improved performance over current methods for small to moderate sample sizes, (3) provide bias adjustment not reliant on asymptotics, and (4) avoid the infinite parameter estimates that can occur with maximum-likelihood estimators. Simulations demonstrate that the proposed bounds achieve the desired level of confidence at smaller sample sizes than previous methods.