2013 CTSI Novel Biostatistical and Epidemiologic Methods Awardees

Three URMC faculty members earned CTSI Novel Biostatistical and Epidemiologic Methods (NBEM) pilot awards for 2013-2014. The CTSI’s NBEM program offers investigators one- or two-year awards for up to $20,000, to stimulate the development of novel biostatistical and epidemiologic methods to help overcome specifically identified limitations that will significantly enhance the validity, accuracy, scope or speed of translational research.  Click here to see the newly-released RFA for 2014 pilot awards. The 2013 NBEM awardees are:

Anthony Almudevar

Anthony Almudevar, Bsc, Msc, PhD

Associate Professor of Biostatistics and Computational Biology

Predictive Models for Longitudinal Technological Home Monitoring Data

Technological monitoring systems are widely used to assess elderly or at-risk subjects living at home. Recent years have seen significant improvement in the accuracy, range and cost of a wide variety of sensor devices and supporting computing and communication network components. What remains is the development of statistical models and algorithms able to convert the output of sensor networks into clinical outcome measures and predictions. The current proposal addresses this need.

Changrong Feng

Changyong Feng, PhD

Associate Professor of Biostatistics and Computational Biology

Allowance for center effects in the analysis of randomized clinical trial with time-to-event outcomes

Many randomized clinical trials (RCT) have time-to-event outcomes. The log-rank test is widely used to analyze such event-time data, however the log-rank test assumes that individuals in the same treatment group are all homogeneous. Heterogeneity among individuals in a randomized study does not invalidate the log-rank tests, but it may make them less efficient. It is common to control heterogeneity using a stratified log-rank test (SLRT). In this proposal we will compare the relative efficiency of SLRT and ULRT under two different scenarios and obtain an optimal linear combination of these test statistics which maximize statistical power.

Xing Qiu

Xing Qiu, PhD

Assistant Professor of Biostatistics and Computational Biology

A Unified Method for Differential Expression and Differential Association Analyses

Thousands of basic research projects use the microarray technology, yet very few of them have been successfully translated into clinical applications. This proposal responds to this challenge by integrating normalization, DE analysis, and DA analysis, in such a way that not only the computational cost is reduced, but also false positives/negatives are reduced by using one MTP for both analyses simultaneously.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s