Home
Education Calendar
Registration


Fall 2002 Biostatistics Rotation
Instructor: Marlos Viana, Ph.D
Registration
(closed)
Time / Location
Section 1: Basic Module
Sections 2 and 3: Topic Modules
Room Changed: On October 29th, 2002, the Rotation will be held at 111 College of Pharmacy

The Biostatistics rotation is an opportunity to discuss several aspects of quantitative methods in biomedical research. The goal is to achieve an understanding of the basic grammar of common quantitative languages (e.g., statistics, mathematics, computer science, morphometry) and to develop an appreciation and an ability to assess these languages of scientific enquiry.

Investigators attending these rotations will become familiar with the scope of usefulness and limitations of a variety of quantitative methods, so that they can interact more effectively with collaborating statisticians, mathematicians and computer scientists. As suggested recently by the National Institutes of Health, current and future biomedical research is likely to be increasingly dependent on the investigator's ability to respond to a larger variety of complementary methodological tools - in contrast to the common practice of framing all experimental questions into the classical statistical hypothesis testing paradigm. The GCRC rotation will emphasize these opportunities, available from complementary paradigms.

The Rotation is open to all GCRC users and potential users, including faculty, fellows and medical residents.

Each GCRC Rotation (Spring and Fall) will consist of two or three consecutive sections. Section I covers the basic elements of a selected language (e.g., statistics) and is followed by one or two thematic sections (II and III). Each section consists of three 50 min lectures held during three consecutive Tuesday at 12 noon (lunch bags welcome). The completion of Section I in any rotation is a prerequisite for attending any of the thematic sections.

 

Time and Location:
University of Illinois Hospital
1740 W Taylor
Chicago IL. 60612
Room: 1135 (Main Floor)
Meeting time: Tuesday, 12:PM - 12:50PM

Fall Rotation Dates:
September: 10, 17, 24
October: 1, 8, 15, 29
November: 5, 12




Fall 2002 Rotation:

Section I: Probability and Statistical Inference.

Session 1.1 September 10
Session 1.2 September 17
Session 1.3 September 24

  In this basic module we will discuss the basic grammar of reasoning with uncertainty. At the end of the Section, participants will be able to understand the core of the statistical grammar (the object of statistical statements), including the notions of uncertainty, probability models, interpretation of model parameters, data simulation, data summary, meaningful data summaries, the role of sample size, modes of estimation and hypothesis testing (from the classical paradigm) and an outline of the non-classical paradigms such as the Bayesian formulation for inference.

Suggested readings:

Probability and Classical Statistics: Briefly Annotated Definitions and Concepts (view article)
Author: Marlos Viana

Some Remarks on Statistics and Scientific Explanation (view article)
Authors: Marlos Viana and Borko Javanovic
Quantitative Issues in Biomedical Research (view article)
Author: Marlos Viana
Bayes Offers a 'New' Way to Make Sense of Numbers (view article)
Author: David Malakoff
Standing Statistics Right Side Up (Editorial)
Annals of Internal Medicine 1999, 130: 1019-1021
Statistical Theories Of Mental Test Scores (Chapter 1)
Author: Allan Birnbaum, New York University;
Addison - Wesley Publishing Company, 1968
How Statistical Expertise Is Used in Medical Research (view article)
Authors: Douglas G. Altman, DSc; Steven N. Goodman, MD, PhD; Sara Schroter, Ph.D
JAMA. 2002;287 (June 5 issue) :2817-2820
A method for selecting dose levels in Cancer Phase I Clinical Trials while controlling the probability of exceeding the maximum tolerated dose (view article)
Authors: A. Rogatko and J. Babb (application software and documentation)


 

Sections II and III: Biological Sequences Analysis.


This is an introductory series of lectures aimed at discussing the basic concepts of biological (nucleotides and amino acids) sequence analysis from a probabilistic modeling perspective. This knowledge will facilitate the understanding of contemporary and classic clinical applications of the underlying probabilistic concepts, including those illustrated in the selected readings (see references below).

The probability and statistics background will be derived from the notions and examples introduced in the Basic Module (Section I) of the Rotation, including probability distributions, entropy, inference, sampling and estimation of probability from counts.


Session 2.1 October 1: Sequence similarity, homology and alignment
Session 2.2 October 8: Scoring models for pairwise alignment
Session 2.3 October 15: Markov chains and hidden Markov models

Session 3.1 October 29: Pairwise alignemnt using HMM
Session 3.2 November 5: Phylogenetic trees
Session 3.3 November 12: Analysis and interpretation of microarray data
Invited guest lecture: Borko Jovanovic, PhD, Northwestern University

 

Suggested readings and links:

 Biological Sequences: Briefly Annotated Definitions and Concepts (Part I) (view article)
Author: Marlos Viana
Biological sequence analysis: Probabilistic models of protein and nucleic acids
Authors: Durbin, R., Eddy S., Krogh A., and Mitchison, G.
Cambridge U. Press, 1998
National Center for Biotechnolgy Information (NCBI)
User's Guide to Human 's Genome (Links)
Importance of purine and pyrimidine content of local nucleotide sequences (six bases long) for evolution of the human immunodeficiency virus type 1.(view article)
Author: H. Doi, Proc Natl Acad Sci U S A. 1991 Oct 15;88(20)

A piecewise-homogeneous Markov chain process of lung transplantation. (view abstract)
Authors: Sharples LD, Taylor GI, Faddy M.
J Epidemiol Biostat 2001;6(4):349-55

Hidden Markov models for the onset and progression of bronchiolitis
obliterans syndrome in lung transplant recipients.
(view abstract)
Authors: Jackson CH, Sharples LD.
Stat Med 2002 Jan 15;21(1):113-28
Profile hidden Markov models. (view article) (view abstract)
Author: Eddy SR.
Bioinformatics 1998;14(9):755-63
A Markov model for analysing cancer markers and disease states in survival studies.Biometrics. 1986 Dec;42(4):855-65. (view article) (view abstract)
Author: Richard Kay
Classification, subtype discovery, and prediction of outcome in pediatric acute lymphoblastic leukemia by gene expression profiling. (view abstract)
Authors: Yeoh EJ, Ross ME, Shurtleff SA, Williams WK, Patel D, Mahfouz R, Behm FG, Raimondi SC, Relling MV, Patel A, Cheng C, Campana D, Wilkins D, Zhou X, Li J, Liu H, Pui CH, Evans WE, Naeve C, Wong L, Downing JR.


Note:

The PDF files in the above links can be viewed with

 
   Last updated on August 23, 2004 1:28 PM
GCRC Home Contact GCRC Comment to GCRC