The randomized clinical trial emerged from areas such as pharmacology where interventions typically consist of a single component, e.g. a drug. Today, interventions are increasingly behavioral, and increasingly multi-component. This talk will review the Multiphase Optimization Strategy, an extension of clinical trials methods aimed at optimizing multi-component behavioral interventions. MOST consists of the following three phases: (1) screening, in which randomized experimentation closely guided by theory is used to asses an array of program and/or delivery components and select the components that merit further investigation; (2) refining, in which interactions among the identified set of components and their interrelationships with covariates are investigated in detail, again via randomized experiments, and optimal dosage levels and combinations of components are identified; and (3) confirming, in which the resulting optimized intervention is evaluated by means of a standard randomized clinical trial. In order to make the best use of available resources, MOST relies on design and analysis tools that help maximize efficiency, such as fractional factorials. MOST has the potential to husband program development resources while increasing understanding of the individual program and delivery components that make up interventions.

<a href="http://chcr.umich.edu/who_we_are/people/person.2005-04-22.2651040386/person_view"><b>Linda Collins</b></a> is a Professor of <b></b><span class="body"><a href="http://www.hhdev.psu.edu/hdfs/">Human Development and Family Studies</a> in the <a href="http://www.hhdev.psu.edu/">College of Health and Human Development</a> and</span><span class="body"> <a href="http://methodology.psu.edu/">Director of the Methodology Center</a></span><span class="body"> at Penn State University. Her research program is devoted to developing,
evaluating, and disseminating cutting-edge methodology for behavioral
and biomedical applications, particularly in the area of substance use
prevention and treatment.</span><b><br>
<br>
</b><span class="body">Dr. Collin's research interests fall into two areas. </span>The first area is Latent Transition Analysis (LTA), a
statistical method for fitting a wide variety of stage-sequential
models in longitudinal data. The second area is research design and related topics. She has worked in
areas such as temporal spacing of observations in longitudinal
research, dealing with missing data, and design for time-varying
adaptive interventions and has recently become interested in the
<u>M</u>ultiphase <u>O</u>ptimization <u>St</u>rategy (MOST), a
method of systematic scientific inquiry inspired by ideas from
engineering.<a href="http://www.hhdev.psu.edu/hdfs/faculty/collins.html"></a><br>