Kristen Juskiewicz, who recently graduated with a Ph.D. from our program, has started a job at the U.S. Government Accountability Office (GAO) where she will assist in executing evaluations and audits commissioned by Congress.
Archived Posts
Jan. 9-10, 2019. IES Annual PI meeting
Jan. 9-10, 2019. IES Annual PI meeting. Washington, D.C.
Oct. 31- Nov 3, 2018. American Evaluation Association Annual Conference
Oct. 31- Nov 3, 2018. American Evaluation Association Annual Conference. Cleveland, OH.
(https://www.eval.org/eval18)
October 17-19, 2018. Northeastern Educational Research Association Annual Conference
Northeastern Educational Research Association Annual Conference. Trumbull, CT.
Prof. Betsy McCoach interviewed on the radio about how students in poverty are less likely to be identified as gifted
Gifted children
Betsy McCoach Professor, Measurement, Evaluation, and Assessment program Department of Educational Psychology discusses how students in poverty are less likely to be identified as gifted. Airdate: March 22, 2018.
You can listen to a recording of the interview or a copy can be downloaded from the WILI 1400 AM show archive website.
Read the article on UConn Today
Data Analysis Training Institute of Connecticut (DATIC) 2018 Summer Workshops
DATIC (www.datic.uconn.edu) is offering 4 workshops at the University of Connecticut in June, 2018: Mixture Modeling, Introduction to Data Analysis in R, Multilevel Modeling in R, and Dyadic Analysis with R. Registration is now open. Go to www.datic.uconn.edu for more information and to register for the workshops.
Mixture Modeling
June 4-6, 2018
Dr. Eric Loken
This 3-day mixture modeling workshop will survey techniques for exploring heterogeneous latent structure in data. We will begin by defining a variety of mixture models. The main focus will be on latent class analysis (LCA) and latent profile analysis (LPA), with applications in health and education. Additional models will include mixture regression models, mixture IRT, k-means clustering, and growth mixture models for longitudinal data. The course will emphasize hands-on work by participants, who will also be encouraged to make connections to their own data, learning to execute many of these models in R. Particular attention will be paid to issues that arise in applied settings including model assumptions, parameter estimation, and interpretation.
Introduction to Data Analysis in R
Instructor: Dr. Randi L. Garcia
Two separate sessions of the R workshop are being offered.
Session 1: June 7 – June 8, 2018
· Thursday and Friday (prior to Multilevel Modeling with R Workshop)
Session 2: June 21 – June 22, 2018
· Thursday and Friday (prior to Dyadic Data Analysis with R workshop)
Are you curious about using R for data analysis? Have you been thinking about making the switch to R, but don’t know where to start? This two-day workshop is the perfect quick start guide to analyzing your data with R. We will cover the fundamentals of data analysis in R with a special focus on translating your existing knowledge and skills from other software (e.g., SPSS) into R. The goal of this workshop is to develop proficiency in R for data preparation and preliminary data analysis. We will build confidence in importing data from different sources into RStudio and getting that data ready for any advanced technique you might then employ. Among the topics to be covered are intro to the RStudio environment, packages, and RMarkdown, data manipulation, data visualization, correlations, reliability tests, basic inference tests, ANOVA, linear regression, Exploratory Factor Analysis (EFA), Confirmatory Factor Analysis (CFA), and more. Instruction on the specific statistics and statistical models will be minimal to zero. It is assumed that you already know how to do these analyses, but you want to see how to do them in R. You do not need to be registered for any other DATIC workshops to enroll in the 2 day Introduction to Data Analysis in R workshop.
Multilevel Modeling Using R Workshop
June 11-15, 2018
Drs. D. Betsy McCoach & Randi Garcia
This workshop covers the basics and applications of multilevel modeling with extensions to more complex designs. Participants will learn how to analyze both organizational and longitudinal (mostly growth curve) data using multilevel modeling and to interpret the results from their analyses. Although the workshop does not require any prior knowledge or experience with multilevel modeling, participants are expected to have a working knowledge of multiple regression. The emphasis will be practical with minimal emphasis on statistical theory, but those seeking more statistical information can arrange an individualized session with the instructors. All analyses will be demonstrated using R. Instruction will consist of lectures, computer demonstrations of data analyses, and hands-on opportunities to analyze practice data sets using R. The workshop emphasizes practical applications and places minimal emphasis on statistical theory. No prior familiarity with R is required, but if you have never used R and want to gain a general proficiency working with data in R, we encourage you to take the two-day DATIC Intro to R and RStudio workshop held on Thursday, June 7, through Friday, June 8, 2018.
Dyadic Data Analysis with R
June 25 – June 29, 2018
Instructors: Drs. Randi L. Garcia and David A. Kenny
The Dyadic Data Analysis workshop focuses on the analysis of dyadic data when both members of a dyad are measured on the same variables. All analyses will use multilevel modeling in R via the RStudio graphical interface. Participants will learn how to analyze dyadic data and to interpret the results from their analyses. Among the topics to be covered are the vocabulary of dyadic analysis, non-independence, data structures, and the Actor-Partner Interdependence Model. We also discuss mediation and moderation of dyadic effects. On day 4, participants choose from one of two break-out sessions: 1) the analysis of over-time dyadic data (e.g., growth curve models) or 2) dyadic data analysis with SEM using the lavaan R package (e.g., Actor‑Partner Interdependence Model and Common Fate Model). The discussion of over‑time data is limited to one day so the workshop should not be construed as workshop on longitudinal dyadic analysis. Participants should have a working knowledge of multiple regression. No prior familiarity with R is required, but if you have never used R and want to gain a general proficiency working with data in R, we encourage you to take the two-day DATIC Intro to R and RStudio workshop.
2018 Modern Modeling Methods Conference: Call for Proposals
The Modern Modeling Methods (M3) conference is an interdisciplinary conference designed to showcase the latest modeling methods and to present research related to these methodologies. The 8th annual M3 conference will be held May 21nd-24th, 2018 at the University of Connecticut. Keynote speakers for the 2018 conference include Dr. Susan Murphy (Harvard University), Dr. Tenko Raykov (Michigan State University) and Dr. Peter Molenaar (Pennsylvania State University). In addition, Susan Murphy and David Almirall will offer a day long pre-conference workshop on Just In Time Adaptive Interventions on Monday, May 21st. Tenko Raykov will offer a post-conference workshop on Item Response Theory: A Latent Variable Modeling Approach on Thursday, May 24th.
Submissions for the 2018 conference are due 2/1/18. We welcome both methodological research papers and papers that illustrate novel applications of methodological techniques in the area of modeling, broadly defined. Papers related to latent variable modeling, multilevel modeling, mixture modeling, longitudinal modeling, and item response theory are especially encouraged. Given the interdisciplinary focus of the conference, it is completely acceptable to present papers that have been published or presented elsewhere. Presenters may select the length of the session that they prefer: 30 minutes, 60 minutes, or 90 minutes. We also welcome proposals for multi-paper symposia on thematically grouped topics. Generally, symposia sessions are 90 minutes in length. We are also soliciting proposals for the poster session. Students are also encouraged to submit proposals, especially for the poster session.
Conference proposals for the Modern Modeling Methods conference may fall into one (or more) of four categories: Methodological Innovation, Methodological Application, Methodological Illustration, or Methodological Evaluation. Methodological Innovation proposals introduce a new technique. Methodological Evaluation proposals present the results of empirical research evaluating a methodology. Most often, these will involve simulation studies. Methodological Application proposals present the methods and results of a real research study in which the technique was used. Methodological Illustration proposals provide a pedagogical illustration of when and how to use the technique; these papers are designed to help the audience be able to implement the technique themselves.
There are three different types of presentations: Paper sessions (in which authors submit a single paper), Symposia (in which a group of authors submit a set of related talks/papers), and posters. All papers should include a 150-200 word abstract that will appear in the conference program. Methodological Research paper proposals should be no longer than 1000 words and should include purpose, background, methods, results, discussion, and significance. Methodological Illustration paper proposals should be no longer than 1,000 words and should include a description of the methodology to be illustrated as well as an outline of the paper/talk. Proposals for symposia should be include titles, authors, an abstract for the symposium, and brief descriptions/abstracts for all of the paper presentations within the symposium. Symposium proposals may be longer than 1000 words if needed, but they should be less than 2000 words. Proposals for the poster session need only submit an abstract: the 1000 word proposal is not required for poster session proposals.
Proposals for the 2018 conference are due February 1st, 2018. Notifications of presentation status will be emailed by February 19th, 2018. To submit a conference proposal, please go to MMM2018 . For more information about the 2018 Modern Modeling Methods conference, please visit http://www.modeling.uconn.edu/ .
Kristen Juskiewicz co-authored report recently released by the U.S. Government Accountability Office
Kristen Juskiewicz served as a Program Analyst for the Forensic Audits and Investigative Service team during her Summer 2017 internship with the U.S. Government Accountability Office (GAO) in Washington, D.C. She was assigned to the federal audit of the Affordable Care Act, specifically an audit of the applicant enrollment and eligibility-verification process for the Federal Health-Insurance Marketplace. The purpose of this audit was to investigate possible fraudulent or improper enrollments for plan year 2015.
During the course of her 11-week internship, Ms. Juskiewicz assisted in the qualitative analysis of sample cases, interviews with stakeholders, source documentation and management, and the presentation of initial findings. She co-authored a number of internal reports, which served to document legal background, interviews records, and analysis records. Through this internship, she was able to experience portions of the entire GAO audit process via a shadowing program with team directors and assistant directors. Ms. Juskiewicz also forged a relationship with the GAO Applied Research and Methodology team, and aided them in exploration of Geographic Information Systems (GIS) via R packages.
The report is available at: https://www.gao.gov/products/GAO-18-169
RMME Community Members Discuss Research at NERA 2017
RMME Community members (now, both RMME PhD alumni), David Alexandro and Xiaowen Liu, discuss presented research at NERA 2017. Congratulations on this successful presentation, from the Research Methods, Measurement, & Evaluation Community!
Presenter: David Alexandro
Authors: Charles Martie, David Alexandro, William Estepar-Garcia, & Ajit Gopalakrishnan
Poster Presentation Title: Every Target and Milestone Matters: Developing Connecticut’s Evidence-Based Early Indication Tool (EIT)
Poster Abstract: Early warning systems typically focus on students’ dropout risk. The Connecticut State Department of Education extended this model to create the Early Indication Tool (EIT), a K-12 system that predicts student performance, identifies students who are at-risk of missing milestones and/or dropping out, and ultimately facilitates more timely interventions.
We are seeking graduate students for the 2018-2019 academic year!
The MEA program is seeking bright, motivated, quantitatively oriented graduate students for our M.A. and Ph.D. programs. All current faculty will consider accepting new advisees for the 2018-2019 academic year. We anticipate being able to offer full graduate assistantships to 3-5 incoming graduate students. To learn more about our graduate programs, feel free to email any of the MEA program faculty.