Dr. Todd little,Director for Institute of Measurement, Methodology and Policy(IMMAP), and professor of research Evaluation Measurement of Statistics in the TTU college of Education will discuss a flexible and powerful approach for evaluating intervention.
For analysis of analysis of multi-cohort longitudinal intervention trails, features of traditional multilevel modeling approaches present numerous obstacles to model estimation and obtaining valid inferences. An alternative approach for testing interventions effects is using longitudinal multiple-group (LMG) modeling. The advantages of LMG include:
a) Robust missing data treatment
b) Estimation mean-level information in a non-arbitrary metric.
c) Incorporating standardization constructs for accurate between group comparisons.
d) Robust estimation and testing of complex interaction.
e) Testing many critical assumptions that otherwise can be tested.
The LGM approach is guided confirmatory model testing framework that places a premium on avoiding Type 2 Errors particularly when complex interactions are potentially a play. (Information: roham.agha@ttu.edu)