Keynote #1. Stratified Micro-randomized Trials with Applications in Mobile Health
Susan Murphy, Harvard University
Tuesday, May 22 8:30-10:00am
Technological advancements in the field of mobile devices and wearable sensors make it possible to deliver treatments anytime and anywhere to users like you and me. Increasingly the delivery of these treatments is triggered by detections/predictions of vulnerability and receptivity. These observations are likely to have been impacted by prior treatments. Furthermore the treatments are often designed to have an impact on users over a span of time during which subsequent treatments may be provided. Here we discuss our work on the design of a mobile health smoking cessation study in which the above two challenges arose. This work involves the use of multiple online data analysis algorithms. Online algorithms are used in the detection, for example, of physiological stress. Other algorithms are used to forecast at each vulnerable time, the remaining number of vulnerable times in the day. These algorithms are then inputs into a randomization algorithm that ensures that each user is randomized to each treatment an appropriate number of times per day. We develop the stratified micro-randomized trial which involves not only the randomization algorithm but a precise statement of the meaning of the treatment effects and the primary scientific hypotheses along with primary analyses and sample size calculations. Considerations of causal inference and potential causal bias incurred by inappropriate data analyses play a large role throughout.
Keynote#2. Alternative forms of Granger causality, heterogeneity
Peter C.M. Molenaar, The Pennsylvania State University
Tuesday, May 22 3:45-5:00pm
Alternative forms of Granger causality based on standard vector autoregressive (VAR), structural VAR and unified structural equation models are presented, including time-frequency domain extensions. The group iterative multiple model estimation (GIMME) approach is proposed as the best method to accommodate heterogeneity and avoid limitations of structural VAR modeling. A new type of VAR – hybrid VAR – is introduced to obtain a unique data-driven solution to Granger causality testing.
Keynote#3. Item Response Theory and Classical Test Theory: Too Long Too Far
Tenko Raykov, Michigan State University
Wednesday, May 23 2:30-4:00pm
This talk is concerned with a view of item response theory that is inclusive of classical test theory rather than juxtaposing the former to the latter. In the widely employed setting in empirical research of homogeneous binary or binary scored items with no guessing, popular item response theory models can be directly obtained from appropriately developed classical test theory based models accounting for the discrete nature of the observed items. Two distinct (observational) equivalency approaches are pointed out that render these item response theory models from corresponding classical test theory based models, and can each be used to obtain the former from the latter models. Similarly, classical test theory based models can be furnished utilizing the reverse application of either of those approaches from corresponding item response theory models.