DATIC MLM Using HLM Workshop Schedule

Day 1 Monday

8:30 – 9:00 Continental Breakfast, 319 Gentry
9:00 – 9:15 Introduction to HLM – overview of the week
9:15 – 10:30 Basics of Multilevel Modeling

Regression Example – High School and Beyond

10:30 – 10:45 Break
10:45 – 11:30 Continuation: Regression Example

·         High School and Beyond (HSB) Example: Two-level model

o    Within school regressions

o    Comparing regressions across schools

o    Conditional model example and interpretation

11:30 – 12:15 Start Building Two-level Models
12:15 – 1:30 Lunch (on your own)
1:30 – 3:15 Building two-level models

·         Model 1 One-way random effects ANOVA (totally unconditional model)

o    ICC

o    Reliability

o    Interpretation of fixed and random effects

·         Model 2 Random coefficients model (unconditional model)

o    Change in level-1 variance

o    Variance and covariance components

o    Interpretation of fixed and random effects

·         Model 3 Intercepts and slopes as outcomes (conditional model)

o    Reduction in level-2 variance

o    Residual variance and covariance components

o    Interpretation of fixed and random effects

·         Model 4:  Adding MeanSES (time permitting)

3:15 – 3:30 Break
3:30 – 5:00 Using the HLMv7 software – Analysis walkthrough

·         Manipulating files using SPSS

o    Aggregating variables in SPSS

·         Level 1 and level 2 data files

·         Creating MDM files for HLMv7

·         Building models

 

Day 2:  Tuesday

8:30 – 9:00 Continental Breakfast, 319 Gentry
9:00 – 9:15 Q & A from Day 1
9:15 – 10:45 Model Assessment Issues

·         Model fit

o    Deviance, model comparison procedures, multiparameter tests, AIC and BIC

·         Estimation and Maximum likelihood

10:45 – 11:00 Break
11:00-12:30 Centering

 

12:30 – 1:45 Lunch (on your own)

 

1:45 – 3:30 Longitudinal Models in HLM

§  Re-conceptualizing Longitudinal Data for Multilevel Models

§  Person period data sets

§  Centering Time

§  Growth trajectories and individual growth curves

§  Correlation between rate of change and initial status

§  Time in different metrics

3:30- 3:45 Break
3:45 – 4:45 Structured Lab I – Organizational Data

 

4:45 – 5:00 Questions and Answers – Lab review

 

Day 3:  Wednesday

8:30 – 9:00 Continental Breakfast
9:00 – 9:15 Q & A from Day 2
9:15 – 10:30 Longitudinal Continued: PIAT reading examples

 

10:30 – 10:45 Break
10:45 – 12:00 §  Intro to time varying covariates

NYS Output

12:00 – 1:15 Lunch (on your own)

 

1:15 – 2:15 ·         Interaction between time and covariate

o    Unemployment example

2:15 – 3:30 ·         Modeling discontinuity

o    Wages example

3:30 – 3:45 Break
3:45 – 4:45 Structured Lab II – Longitudinal data

 

4:45 – 5:00 Recap and Q&A


Day 4: Thursday

8:30 – 9:00 Continental Breakfast
9:00 – 9:15 Q & A from Day 3
9:15 – 10:30 Piecewise and Polynomial Models for Non-Linear Growth

·         Fit and interpretation

o    NYS as a non-linear model (Piecewise)

10:30 – 10:45 Break
10:45 – 12:00 Polynomial Models for Non-Linear Growth

o    NYS as a non-linear model (Cubic)

Comparison to piecewise model

12:00 – 1:15 Lunch (on your own)

 

1:15 – 2:30 Heterogeneous Variances
2:30-2:45 Break

 

2:45-3:45 Residual Files and Graphing
3:45-5:00 Open lab time and Office Hours

 

Day 5: Friday

8:30 – 9:00 Continental Breakfast
9:00 – 9:15 Q & A from Day 4
9:15 – 10:45 Power Analysis and Sample Size

  • Optimal Design Software (freeware)
10:45-11:00 Break and Evaluations
11:00-12:00 Closing thoughts and special requests
12:00 Closing Luncheon –  Gentry Room TBA