Workshop Series
Quantitative Methods Workshops
The Statistical Consulting Studio has held a formal workshop series during fall and spring semesters (not summer) for the past six years. The topics were chosen to benefit a broad range of researchers with various backgrounds. Currently the content, format, and delivery of these workshops is being re-evaluated to better serve the faculty and graduate students in our college. If you would like to receive periodic emails announcing new sessions and links to register, send an email to Sarah.Schwartz@usu.edu requesting you be added to mailing list.
There are 3 options for participation each semester: university credit, continuing education, or a ’la cart.
|
|
University Credit |
Continuing Education |
A’la Cart |
|
Registration |
Use the Banner system EDUC 6560 (CRN’s for various locations) |
Online link for registration CEPY 5700 (email Sarah for the link) |
Use EventBrite to RSVP for any single day(s) |
|
Cost |
All traditional USU tuition and fees apply |
$30 fee for the entire semester (no other USU tuition or fees) |
None |
|
Transcript |
0.5 Academic Credit |
1 Continuing Education Unit (CEU) |
Nothing |
|
Requirements |
Attend at least 5 of the 7 days AND complete a small applied project |
None |
|
Regression: Basics & Beyond |
||
|
Fall 2022: Thursdays 1:30 – 2:20 pm Education 272 |
Lecture |
Lab |
|
Basic: Multiple Linear Regression Did you know that ANOVA is just a special case of regression? Regression permits the inclusion of continuous predictors, customized interactions (moderation), quadratic terms, and can better model the results of observational studies. |
Oct 6 | Oct 20 |
|
More: Binary Logistic Regression Many outcomes in education are binary in nature: accept or decline an offer of admission, pass or fail a course, persist to another year or stop out. Binary logistic regression, rather than multiple regression, is the standard approach to analyzing discrete outcomes. We will focus the parallels between logistic and multiple regression, and how to interpret model results for a wide audience. We will demystify odds, log odds, odds ratios, and probabilities, while also covering assumptions and the interpretation of results. |
Oct 27 | Nov 3 |
|
Beyond: Intro to Multilevel Modeling (MLM) Multilevel modeling (MLM) is growing in use throughout the social sciences due to the common hierarchical or clustered structure of data collected. Although daunting from a mathematical perspective, MLM is relatively easy to employ once some basic concepts are understood. Whether your participants are nested (eg. students in classes, multi-site trials) or you are monitoring repeated measurements (eg. longitudinal), correlation between observations should not be ignored, but leveraged. This workshop will provide a solid foundation and introduction to multi-level models. |
Nov 10 | Nov 17 |
|
Beyond: Intro to General Estimating Equations (GEE) In some instances, MLM is not viable. An alternative approach to incorporating correlation between observation is to model the marginal effects through the specification of a correlation structure. GEE models are especially useful for outcomes that are not continuous: binary, categorical, or counts. |
Nov 17 | - |
|
Working knowledge of basic statistics, including linear regression, is assumed. All examples and interactive labs are conducted using the R computer software. Send questions to: Sarah.Schwartz@usu.edu |
||