It is now
possible to register for the workshops without registering for the conference.
Further information is available here |
| Pre-Conference Workshops, Tuesday June 13th |
| A Workshop on Functional Data Analysis |
Jim Ramsay - McGill University |
Functional data are defined by curves or images. The goals of functional data analysis (FDA) are those of statistics in general: To study variation and to propose models. Because the processes that generate functional data are usually smooth, we can use derivatives to impose smoothness on estimated functions, and we can construct differential equations to model of functional data.
We will first review basic techniques for manipulating functional data, including smoothing methods. The registration problem, involving aligning salient features across several curves, will be a central issue. We then consider functional versions of analysis of variance, regression and principal components. Differential equations, being also functional linear models, can also be estimated from functional data.
The workshop will be based on the books, Functional Data Analysis (2005) and Applied Functional Data Analysis (2002) by J. O. Ramsay and B. W. Silverman and published by Springer, and on a revision of the first book that is in progress. Copies of these books will be available for sale. The workshop will also use software developed for both S-PLUS and Matlab, and sample data and analyses will be available.
|
|
|
| Introduction to Nonparametric Item Response Theory |
Klaas Sijtsma, L. Andries van der Ark, and Wilco H. M. Emons - Tilburg University |
(This workshop has been cancelled due to low enrollment.)
|
| More details |
|
|
| Skills Diagnosis with Latent Variable Models |
Jeff Douglas and Hua-Hua Chang - UIUC
Jon Templin - University of Kansas
Jimmy de la Torre - Rutgers
Robert Henson - UNCG
|
The primary aim of skills diagnosis is to develop and analyze tests in ways that reveal information with more diagnostic value, when compared with traditional approaches. In the methods for skills diagnosis that we consider mastery of particular skills or states of knowledge can be represented by a list of binary latent variables, indicating mastery of each of a finite set of skills under diagnosis. The main objective of skills diagnosis is to classify examinees according to this list of skills. In this training session, several popular modeling and classification approaches will be discussed. Three conjunctive latent class models known as the DINA, NIDA, and Fusion models will be introduced, and software for fitting these models with Mplus will be demonstrated. Because of the multidimensional nature of these models, estimation benefits greatly if it can adapt to previous responses. To address this, computerized adpative testing (CAT) is considered. Because Fisher information does not apply to discrete latent variables, alternative and computationally simple item selection rules are introduced. For CAT settings in which both traditional and diagnostic models are being used, CAT algorithms are introduced for ensuring reliable information for these dual objectives. In addition to sequential methods of test construction, indices for use in fixed-length test construction are also given. The training session is meant to provide practical guidelines for implementing skills diagnosis, and considers the essential topics of identifying the attributes measured by items as well as test equating. |
| More details |
|
|
| Post Conference Workshops, Sunday June 18th |
| Factor Analysis and Structural Equation Modeling |
Jamshid Etezadi -- Concordia University, Montreal |
This workshop is intended to provide a comprehensive introduction to social science measurement models and structural equation modeling (SEM) also known as covariance structure analysis, latent variable analysis, and causal modeling. Participants will learn fundamentals of SEM including distribution assumptions, model identifications, estimation methods, goodness-of-fit tests, and model re-specifications. Since error of measurement is an essential part of SEM, the concept of reliability and validity will also be covered. The emphasis is on applications, participants will use the computer lab and a popular software such as EQS or LISREL to explore a range of models, researchers typically encounter including latent means and multi-group analysis. By the end of the workshop, they will be able to formulate their research problems into testable hypotheses using a computer program. Although the emphasis is on the applications, participants will obtain a conceptual understanding of the relevant theories.
|
|
|
| WinBUGS |
Steven N. MacEachern - Ohio State University |
(This workshop has been cancelled)
|
|
|
Questions?