David A. Kenny
March 12, 2008

~ DATIC 2008  ~
Data Analysis Training Institute of Connecticut

Workshop on Hierarchical Linear Models

Instructors: D. Betsy McCoach & Ph.D.Ann A. O'Connell, Ed.D. and
University of Connecticut


BOTH OF THESE WORKSHOPS ARE SOLD OUT. THERE IS A WAITING LIST.

Main DATIC Website

Overview

Registration Details

Benefits

Curriculum

Recommended Readings


Overview

Two workshops on Hierarchical Linear Models will be held at the University of Connecticut (both workshops cover the same material). Dates are:
    Session A: 
Monday, June 16, through Friday, June 20 (currently sold out)
    Session B:  Monday, June 23 to Friday June 27 (slots still available)

Each workshop covers basics and applications of multilevel modeling with extensions to more complex designs. Participants will learn how to analyze data via a multilevel model, and be able to interpret the results from their analyses. Participants are expected to have a working knowledge of multiple regression as well as SPSS (or SAS). Analyses will be demonstrated using the software HLMv6. Alternative software packages, including SPSS, will be discussed, and examples provided.  Instruction will consist of lecture, computer workshops, and individualized consultations. The emphasis will be practical with minimal emphasis on statistical theory, but those seeking more statistical information can arrange an individualized session during instructor office hours.

Because the number of spaces is limited, please apply soon to reserve a space.  To register, send an email to daticworkshops@gmail.com in order to save a place, and complete the registration form (click here to get the form).

Participants are encouraged to bring their own data.  They should contact the instructors beforehand to ensure that data are appropriately formatted for analysis using HLMv6 or SPSS.

The workshop covers the following topics:

  • Random and fixed effects
  • Intraclass correlation and estimation of proportion of variance explained
  • Methods of centering
  • Two-level general linear models
  • Three-level general linear models
  • Applications of two- and three-level models to organizational data
  • Applications of two- and three-level models to longitudinal data
  • The flexible treatment of time within multilevel models
  • Piecewise Growth Curves using HLM
  • Two-level generalized (logistic) linear models
  • Residual Analyses

Registration Details

Dates and Times:

HLM Workshop Session A:  Monday June 16 to Friday June 20, 2008

Opening Reception planned for Sunday June 15, at 6:00PM


HLM Workshop Session B:  Monday June 23 to Friday June 27, 2008

Opening Reception planned for Sunday, June 22, at 6:00PM

Schedule:       9AM to 5PM Monday-Thursday,

                       9AM to 12PM Friday with complimentary luncheon

Location:


Cost:

Registration:

  • Link to Regform.doc (please send check made payable to the University of Connecticut)


Benefits

    The following materials and events are included in the cost of the workshop:

  • CD-ROM containing workshop instructional materials and sample data sets
  • Binder with workshop outline, computer outputs, and reprints
  • Sunday pre-workshop reception
  • Continental breakfast each morning
  • Friday luncheon


Curriculum (to be adapted somewhat to the specific needs of participants)


Day 1
       • Introduction
       • Basics of multilevel modeling
       • Fixed and random effects, ICC
       • Examples of two-level models for clustered data
       • Using the HLMv6 software
       • Intro to HLM Software
       • Applications (HLMv6)

Day 2
       • Model building, model testing,
       • Estimation, model fit
       • Centering
       • Heterogeneous Variances
       • Using SPSS for two-level organizational data
       • Lab time

Day 3
       • Reconceptualizing longitudinal data for multilevel models
       • Two-level longitudinal analyses
       • The flexible treatment of time
       • Adding time invariant predictors
       • Adding time-varying predictors
       • Developing the piecewise growth curve
       • Applications
       • Lab time

Day 4
       • Additional applications for longitudinal data
       • Polynomial models for non-linear growth
       • Three-level longitudinal analyses
       • Generalized multilevel Linear Models (logistic HLM)
       • Graphing in HLM, and residual diagnostics
       • Lab Time

Day 5
       • Power Analysis and effect size; Using the Optimal Design Software
       • Questions and answers
       • Wrap-up
       • LUNCHEON

Recommended Readings

Raudenbush, S.W. & Bryk, A. S. (2002). Hierarchical Linear Models:  Applications and Data Analysis Methods (2nd ed.). Newbury Park, CA:  Sage. 

Raudenbush, S., Bryk, A., Cheong, Y.F., & Congdon, R. (2004). HLM 6: Hierarchical Linear and Nonlinear Modeling. Lincolnwood, IL: Scientific Software International.

Singer, J. D. & Willett, J. B. (2003).  Applied longitudinal data analysis: Modeling change and event occurrence. Oxford: Oxford University Press.

Link to the SSI site to buy the Raudenbush & Bryk books here.


Main DATIC Website

Overview

Registration Details

Benefits

Curriculum

Recommended Readings