Biostatistics

Eva Petkova, Ph. D., Acting Head
JianFeng Cheng, Ph.D. Candidate, Research Associate
Mark Davies, M.S., Research Scientist IV
Steve Ellis, Ph.D., Research Scientist V
Hanga Galfalvy, Ph.D., Research Scientist II
Huiping Jiang, Ph.D., Postdoctoral Fellow
Xinhua Liu, Ph.D., Senior Biostatistician
Todd Ogden, Ph.D., Research Scientist V
Hongtu Zhu, Ph.D., Biostatistician
Songmei Wu, Ph.D. Candidate, Research Associate

Overview
The Biostatistics Division provides investigators of the New York State Psychiatric Institute access to and training in state-of-the-art statistical techniques as needed for optimal use of their research data. This includes developing and applying new methodology for the design and analysis of psychiatric studies, participating in major funded research projects, consultations on data-analytic and design issues for grant submission and manuscript preparation. In addition, the department provides contining education for statisticians and data analysts working at the Institute.

CURRENT RESEARCH
Members of the Biostatistics Division are involved both in collaborative research with colleagues from the Institute and in statistical methodological research, often motivated by their collaboration with psychiatrists. This year several new statisticians joined the Division. Huiping Jiang, Ph.D. joined us as a post-doctoral fellow funded by the CoGENT grant. Hongtu Zhu, Ph.D., was hired to support the fMRI research at the Child Psychiatry Division. Songmei Wu, a Dr.P.H. student from the Department of Biostatistics at Columbia University was hired to support research in the Division of Neuroscience.

Dr. Ellis currently is continuing his work on the association of antidepressant prescription rates and suicide rates along with Michael Grunebaum and John Mann. He is also working on developing and fitting a statistical model for dendrite branching structure (with Andrew Dwork and Gorazd Rosoklija), and is engaged in a large computationally intensive analysis of some autoradiographic data (with Mark Underwood, Victoria Arango, and John Mann).

Dr. Ogden has continued work on the development of statistical methodology for the analysis of brain imaging data and for providing statistical expertise for the Division of Brain Imaging. Recently, he has focused on functional data analytic approaches to analyzing image data as well as general methods for estimation of kinetic parameters and related quantities.

As part of her work in the Department of Neuroscience, Dr. Galfalvy is continuing research on statistical methodology for the analysis of biological and clinical data from longitudinal studies of patients with mood disorders, working on several projects related to the prediction of suicide attempt probability and lethality. She conducted research on the selection/testing of statistical techniques for analyzing gene micro array data and was the main statistician on projects for the detection of genetic changes associated with mental disorders and the aging of the brain.

Dr. Petkova maintains her collaboration with researchers from DES, Therapeutics, Smoking Cessation, Personality Studies, Eating Disorders and Substance Abuse. She actively contributes to applications for NIH funding, consults on ongoing issues related to the conduct of clinical trials at the Institute and collaborates in manuscript preparation. She has begun to develop statistical approaches to estimate the effect of clinicians’ guess about the treatment on the estimation of efficacy in pharmacological trials in psychiatry. In collaboration with a colleague from Wright State University, Dr. Thaddeus Tarpey, she has begun work on the identification of placebo responders. Preliminary results about the identification of placebo responders in an antidepressant clinical trial are available. She and Dr. Tarpey have applied for NIMH funds to continue the research and to develop statistical methods for partitioning of subjects based on the trajectory of their symptoms and incorporating covariates.

In the short period since his appointment, Dr. Hongtu Zhu has begun active collaboration with researchers from Child Psychiatry. He has initiated numerous collaborative projects in addition to continuing his methodological research in the area of non-linear regression, mixture models, latent variables and models diagnostics. His primary collaboration is with Dr. Bradley Peterson’s fMRI research center.

Dr. Huiping Jiang has started his training in clinical trials as part of his post-doctoral fellowship. He has joined members of the Biostatistics Division in several projects related to planning and monitoring of clinical trials. He has begun collaboration with several investigators from the core grants of the CoGENT. In consultation with Dr. Ogden, he has initiated methodological research in the area of brain imaging analysis utilizing results from his doctoral dissertation.

JianFeng Cheng, in collaboration with Eva Petkova and Blair Simpson, has been investigating the effects of different methods for imputation of missing data on the inference from randomized clinical trial for treatment of OCD. Under the supervision of Eva Petkova, JianFeng Cheng is finishing research on the effect of measurement error and clinicians guess about the treatment on the estimation of treatment efficacy from randomized double blind clinical trials.

Education and Training
Statistics Workshop
As part of its training activities the department offers the NYSPI Biostatistics Workshop, a series of seminars covering statistical methodology, applications and the use of advanced statistical software. Invited speakers illustrate statistical and data management issues based on examples from on-going research at the Institute, explore emerging methodologies, or present relevant papers recently published in the statistical literature. These weekly seminars are open to all Institute investigators and their staff members, as well as students from the Columbia School of Public Health.

Columbia-Penn-Yale Statistics in Psychiatry Forum
The Biostatistics Department is a co-founder of the annual Columbia-Penn-Yale Statistics in Psychiatry Forum. The Forum is unique in its focus on methodological and statistical issues pertaining to research in psychiatry. The practice of psychiatric research has features that make the statistical problems associated with it distinct from the statistical issues in other areas of medicine, such as cancer research, cardiovascular research, AIDS and others. The challenges of biostatistics in psychiatry usually have a low profile at biostatistical conferences and the Forum is the only meeting where these challenges are exclusively discussed. The one-day round-table of biostatisticians from the Institute and faculties from the Departments of Epidemiology and Biostatistics at the University of Pennsylvania and Yale has become an important tool for collaboration, development and exchange of ideas related to statistics in psychiatric research. Beginning with this year’s 6th Annual Columbia-Penn-Yale Statistics in Psychiatry Forum, the event includes an invited speaker in addition to the talks presented by each of the participating institutions. This year’s invited speaker was Robert Gibbons from the University of Illinois at Chicago.

BaDMaN Workshops
As part of the Division of Biostatistics work with the Biostatistics and Data Management and Networking (BaDMaN) Core, Dr. Petkova organized the BaDMaN Workshops to further the exchange of information, foster collaboration and facilitate the development of new ideas between NYSPI researchers, biostatisticians and data managers. This bi-monthly seminar runs during the academic year and is open to all researchers at the Institute. Biostatistics Department members have been presenting at the series.

Awards and Honors
Dr. Ogden was a Visiting Scholar in the Department of Mathematics and Statistics at Wright State University and Dr. Zhu received awards at the University of Florida’s Sixth Annual Winter Workshop on Data Mining, Statistical Learning and Bioinformatics in January 2004 and the International Biometric Society, ENAR, March 2004.

Bibliography
Brown AS, Susser ES, Gorman JM, Schaefer CA, Hooton J, Zhang H, Petkova E, Babulas V, Perrin M. Elevated Maternal Interleukin-8 Levels and Risk of Schizophrenia in Adult Offspring. American Journal of Psychiatry, 161, 889-895, 2004.

Ellis SP. "Instability in nonlinear estimation and classification: Examples of a general pattern," in Denison DD; Hansen MH; Holmes CC; Mallick B; and Yu B, eds. Nonlinear Estimation and Classification. Lecture Notes in Statistics, Vol. 171. Springer, New York, pp. 405-415, 2003.

Feinstein SB, Fallon BA, Petkova E, Liebowitz MR. Item-by-item Factor Analysis of the Yale-Brown Obsessive Compulsive Scale Symptom Checklist. Journal of Neuropsychiatry and Clinical Neuroscience, 15, 187-193, 2003.

Grunebaum MF, Oquendo MA, Burke AK, Ellis SP, Echavarria G, Brodsky BS, Malone KM, Mann JJ. Clinical impact of a two-week psychotropic medication washout in unipolar depressed inpatients. Journal of Affective Disorders, 75, 291-296, 2003.

He FL, Zhou JL, Zhu HT. Autologistic regression model for the distribution of vegetation. Journal of Agricultural, Biological and Environmental Statistics, 8, 205-222, 2003.

Kegeles LS, Malone KM, Slifstein M, Ellis SP, Xanthopoulos E, Keilp JG, Campbell C, Oquendo M, Van Heertum RL, Mann JJ: Response of cortical metabolic deficits to serotonergic challenge in familial mood disorders. American Journal of Psychiatry , 160:76-82, 2003.

Ogden RT, Tarpey T, Mann JJ, Parsey RV. Standard errors for parameter estimation in kinetic modeling with an input function. Journal of Cerebral Blood Flow and Metabolism, 23S, 672, 2003.

Ogden RT. Estimation of kinetic parameters in graphical analysis of PET imaging data. Statistics in Medicine, 22, 3557-3568, 2003.

Parsey RV, Ogden RT, Mann JJ. Determination of volume of distribution using likelihood estimation in graphical analysis: Elimination of estimation bias. Journal of Cerebral Blood Flow and Metabolism, 23, 1471-1478, 2003.

Quitkin FM, Petkova E, McGrath PJ, Taylor B, Beasley C, Stewart J, Amsterdam J, Fava M, Rosenbaum J, Reimherr F, Fawcett J, Chen Y, Klein D. When Should a Trial of Fluoxetine For Major Depression Be Declared Failed? American Journal of Psychiatry,16(4), 734-740, 2003.

Tarpey T, Petkova E, Ogden RT. Profiling Placebo Responders by Self-Consistent Partitioning of Functional Data. Journal of the American Statistical Association, 98 (464), 850-858, 2003.

Zhang HP, Fui R, Zhu HT. A latent variable model of segregation analysis for ordinal outcome. Journal of American Statistical Association, 98, 1023-1034, 2003.

Zhang HP, Yu CY, Zhu HT, Shi J. Identification of linear directions in multivariate adaptive spline models. Journal of American Statistical Association, 98, 369-376, 2003.

Zhou JL and Zhu HT. Robust estimation and design procedures for random effect model. Canadian Journal of Statistics, 31, 99-110, 2003.

Zhu HT and Lee SY. Local influence for generalized linear mixed models. Canadian Journal of Statistics, 31, 293-309, 2003.

Zhu HT, Yu CY, Zhang H P. Tree-based Disease Classification for the Protein Data. Proteomics, 3, 1673-1677, 2003.

Zhu HT and Zhang HP. Hypothesis testing in a class of mixture regression models. Journal of the Royal Statistical Society, Series B., 66, 3-16, 2004.