15th ANNUAL EARLY HEARING DETECTION & INTERVENTION MEETING
March 13-15, 2016 • San Diego, CA
3/13/2016 | 9:00 AM - 4:00 PM | Sunset
Introduction to Multilevel/HLM Modeling
With the growth of longitudinal, population-based EHDI data systems, state and territorial EHDI programs have an increasing wealth of data that can be used to inform their practice and policy efforts. The purpose of this instructional session is to provide a hands-on introduction to multi-level or hierarchical linear (HLM) modeling – one particularly powerful tool that can be used to understand EHDI program effects on child health and development.
We will focus on two applications of HLM that are particularly relevant to the EDHI community. The first is where data for individual children are nested within larger entities, such as birthing hospitals. In this case, HLM might help EHDI programs accurately assess whether there are characteristics of hospitals (e.g., size, access to services, percentage of births to low-income parents, etc.) that are related to child outcomes, such as infants who fail their hearing screening becoming lost to follow-up. The second application is where one has longitudinal data on child measures, such as language development over time. In this case, HLM might help EHDI researchers assess whether early identification and intervention lead to more rapid growth in language skills for children with hearing loss.
This work session will be hands-on, with participants analyzing and interpreting data using a free version of a widely used software program (HLM, by Scientific Software International – note the presenters have no affiliation or financial relationship with the software company). Participants will be asked to download the software prior to attending the training. The session will involve lecture and discussion regarding the principles of HLM analyses, paired with collaborative analysis and interpretation of simulated EHDI data provided by the presenters. Participants will also be provided with detailed handouts used in the training session that illustrate the basics of HLM modeling and the interpretation of HLM statistical output.
Presentation:
This presentation has not yet been uploaded or the speaker has opted not to make the presentation available online.
Handouts:
Handout is not Available
CART:
CART transcripts are NOT YET available, but will be posted shortly after the conference
Presenters/Authors
Craig Mason
(POC,Primary Presenter), University of Maine, craig.mason@maine.edu;
Craig Mason, Ph.D. is a Professor of Education and Applied Quantitative Methods at the University of Maine. He received his PhD in Clinical Child Psychology from the University of Washington and his interests include informatics, newborn hearing loss, and quantitative methods. Dr. Mason has been PI or Co-PI on numerous grants and contracts from the National Science Foundation, the National Institutes of Health, the Centers for Disease Control and Prevention, and the Department of Education. In addition, he has published, presented, and taught on multivariate analysis, multi-level modeling, epidemiological analysis, structural equation modeling, and growth modeling. He has been invited to present on methodology and informatics by the Centers for Disease Control and Prevention, the National Association for Public Health Statistics and Information Systems, the Department of Health and Human Services, the Association of Maternal and Child Health Programs, and other national organizations.
ASHA DISCLOSURE:
Financial -
No relevant financial relationship exist.
Nonfinancial -
No relevant nonfinancial relationship exist.
Shihfen Tu
(Co-Presenter), University of Maine, ;
Shihfen Tu, Ph.D. is an Associate Professor of Education and Applied Quantitative Methods at the University of Maine. Dr. Tu received her PhD in Cognitive/Experimental Psychology from the University of Washington. Her areas of interest are research methodology, informatics, and cognitive development.
Together, Drs. Mason and Tu have been PI or Co-PI on nearly $15 million in grants and contracts from the National Science Foundation, the National Institutes of Health, the Centers for Disease Control and Prevention, and the U.S. Department of Education. They have published, presented, and taught on univariate and multivariate analysis, multi-level modeling, epidemiological analysis, structural equation modeling, and growth modeling, and served as statisticians / methodologists on multiple grants funded by the National Institutes of Health, the National Science Foundation, and the Centers for Disease Control and Prevention.
They have been invited to make presentations on methodology and informatics by the Centers for Disease Control and Prevention, the National Association for Public Health Statistics and Information Systems, the U.S. Department of Health and Human Services, the Association of University Centers on Disabilities, and the Association of Maternal and Child Health Programs.
ASHA DISCLOSURE:
Financial -
Nonfinancial -