TESTING EQUALITY OF CORRELATION COEFFICIENTS FOR PAIRED BINARY DATA FROM MULTIPLE GROUPS.

Slides:



Advertisements
Similar presentations
Outline National Assessment of Educational Progress (NAEP) Multivariate Design Problem Implications for analysis Example with similar structure in Biostatistics.
Advertisements

COMPUTER INTENSIVE AND RE-RANDOMIZATION TESTS IN CLINICAL TRIALS Thomas Hammerstrom, Ph.D. USFDA, Division of Biometrics The opinions expressed are those.
Lecture 11 (Chapter 9).
Simulation methods for calculating the conditional power in interim analysis: The case of an interim result opposite to the initial hypothesis in a life-threatening.
Lecture 3 Outline: Thurs, Sept 11 Chapters Probability model for 2-group randomized experiment Randomization test p-value Probability model for.
Outline input analysis input analyzer of ARENA parameter estimation
Departments of Medicine and Biostatistics
Chapter 6: Experiments in the Real World
Chapter 6 STA 200 Summer I Equal Treatment of All Subjects The underlying assumption of randomized comparative experiments is that all subjects.
Point and Confidence Interval Estimation of a Population Proportion, p
Stat 512 – Lecture 12 Two sample comparisons (Ch. 7) Experiments revisited.
Clustered or Multilevel Data
BIOST 536 Lecture 3 1 Lecture 3 – Overview of study designs Prospective/retrospective  Prospective cohort study: Subjects followed; data collection in.
Mixed models Various types of models and their relation
Cumulative Geographic Residual Test Example: Taiwan Petrochemical Study Andrea Cook.
BS704 Class 7 Hypothesis Testing Procedures
Testing Dose-Response with Multivariate Ordinal Data Bernhard Klingenberg Asst. Prof. of Statistics Williams College, MA Paper available at
Detecting Spatial Clustering in Matched Case-Control Studies Andrea Cook, MS Collaboration with: Dr. Yi Li December 2, 2004.
Sample Size Determination
Calculating sample size for a case-control study
Normal and Sampling Distributions A normal distribution is uniquely determined by its mean, , and variance,  2 The random variable Z = (X-  /  is.
Analysis of Complex Survey Data
Marshall University School of Medicine Department of Biochemistry and Microbiology BMS 617 Lecture 12: Multiple and Logistic Regression Marshall University.
Survival analysis Brian Healy, PhD. Previous classes Regression Regression –Linear regression –Multiple regression –Logistic regression.
Tuesday, September 10, 2013 Introduction to hypothesis testing.
Chapter 8 Introduction to Hypothesis Testing
Means Tests Hypothesis Testing Assumptions Testing (Normality)
 Mean: true average  Median: middle number once ranked  Mode: most repetitive  Range : difference between largest and smallest.
Chapter 1: Introduction to Statistics
Basics of ANOVA Why ANOVA Assumptions used in ANOVA Various forms of ANOVA Simple ANOVA tables Interpretation of values in the table Exercises.
Reading Scientific Papers Shimae Soheilipour
AP STATISTICS “Do Cell Phones Distract Drivers?”.
HSRP 734: Advanced Statistical Methods June 19, 2008.
Maximum Likelihood Estimator of Proportion Let {s 1,s 2,…,s n } be a set of independent outcomes from a Bernoulli experiment with unknown probability.
Chapter 5: Producing Data “An approximate answer to the right question is worth a good deal more than the exact answer to an approximate question.’ John.
Handling Attrition and Non- response in the 1970 British Cohort Study Tarek Mostafa Institute of Education – University of London.
Evidence-Based Medicine Presentation [Insert your name here] [Insert your designation here] [Insert your institutional affiliation here] Department of.
Modeling Cure Rates Using the Survival Distribution of the General Population Wei Hou 1, Keith Muller 1, Michael Milano 2, Paul Okunieff 1, Myron Chang.
Contingency tables Brian Healy, PhD. Types of analysis-independent samples OutcomeExplanatoryAnalysis ContinuousDichotomous t-test, Wilcoxon test ContinuousCategorical.
통계적 추론 (Statistical Inference) 삼성생명과학연구소 통계지원팀 김선우 1.
How to Read Scientific Journal Articles
Bayesian Multivariate Logistic Regression by Sean O’Brien and David Dunson (Biometrics, 2004 ) Presented by Lihan He ECE, Duke University May 16, 2008.
Ledolter & Hogg: Applied Statistics Section 6.2: Other Inferences in One-Factor Experiments (ANOVA, continued) 1.
Single-Factor Studies KNNL – Chapter 16. Single-Factor Models Independent Variable can be qualitative or quantitative If Quantitative, we typically assume.
Categorical Independent Variables STA302 Fall 2013.
1 Multivariable Modeling. 2 nAdjustment by statistical model for the relationships of predictors to the outcome. nRepresents the frequency or magnitude.
Unit 1 Sections 1-1 & : Introduction What is Statistics?  Statistics – the science of conducting studies to collect, organize, summarize, analyze,
Simulation Study for Longitudinal Data with Nonignorable Missing Data Rong Liu, PhD Candidate Dr. Ramakrishnan, Advisor Department of Biostatistics Virginia.
FIXED AND RANDOM EFFECTS IN HLM. Fixed effects produce constant impact on DV. Random effects produce variable impact on DV. F IXED VS RANDOM EFFECTS.
1 EFFICACY OF SHORT COURSE AMOXICILLIN FOR NON-SEVERE PNEUMONIA IN CHILDREN (Hazir T*, Latif E*, Qazi S** AND MASCOT Study Group) *Children’s Hospital,
XIAO WU DATA ANALYSIS & BASIC STATISTICS.
Compliance Original Study Design Randomised Surgical care Medical care.
Homogeneity test for correlated data in ophthalmologic studies Chang-Xing Ma University at Buffalo 1.
SECTION 2 BINARY OPERATIONS Definition: A binary operation  on a set S is a function mapping S X S into S. For each (a, b)  S X S, we will denote the.
How to do Power & Sample Size Calculations Part 1 **************** GCRC Research-Skills Workshop October 18, 2007 William D. Dupont Department of Biostatistics.
Association tests. Basics of association testing Consider the evolutionary history of individuals proximal to the disease carrying mutation.
1 Chapter 11 Understanding Randomness. 2 Why Random? What is it about chance outcomes being random that makes random selection seem fair? Two things:
Statistics Correlation and regression. 2 Introduction Some methods involve one variable is Treatment A as effective in relieving arthritic pain as Treatment.
Logistic Regression For a binary response variable: 1=Yes, 0=No This slide show is a free open source document. See the last slide for copyright information.
1 Study Design Imre Janszky Faculty of Medicine, ISM NTNU.
1.3 Experimental Design. What is the goal of every statistical Study?  Collect data  Use data to make a decision If the process to collect data is flawed,
Marshall University School of Medicine Department of Biochemistry and Microbiology BMS 617 Lecture 13: Multiple, Logistic and Proportional Hazards Regression.
How to read a paper D. Singh-Ranger.
Statistical Analysis of the Randomized Block Design
بسم الله الرحمن الرحیم.
SA3202 Statistical Methods for Social Sciences
Advanced Placement Statistics
Monitoring rare events during an ongoing clinical trial
Introduction to Statistics
Probability.
Presentation transcript:

TESTING EQUALITY OF CORRELATION COEFFICIENTS FOR PAIRED BINARY DATA FROM MULTIPLE GROUPS

Outline Background Testing Methods Simulation Study Real Work Example Conclusion

Background

Introduction In clinical trials studying diseases at paired body parts, each person contributes two measurements to the study. Outcomes from the same patient can be highly correlated. Taking eyes as an example, for a single patient, the probability that one eye has disease often increases given the knowledge that the other one does. One of the models to deal with these binary correlated data is the equal correlation coefficients model. Before using this model, here we need to test if the correlation coefficients in each groups are actually equal.

Two Possible Method Rosner’s model Assume that for a single patient, the conditional probability of one eye having disease given disease response at the other eye is R times the unconditional probability. where Z ijk =1 if the kth eye of jth individual in the ith group has a response at the end of the study, and 0 otherwise. Where constant R is the same in each of the g groups. Donner’s model Assumes that the g groups share a common intra-class correlation coefficient. Basically focus on this model in this paper.

Binary correlated data structure

Testing Method

Method(Equal correlation coefficients model)

Log Likelihood Function

Likelihood Ratio Test

Wald-type test

Score test

Simulation Study

g g 2 4 8

Real Work Examples

Example1:218 outpatients, aged from 20 to 29 with retinitis pigmentosa (RP),were assigned into 4 genetic type groups. Table of the data(number of effected eyes for persons in each genetic type group) Table of result(Statistic values and p-values of different test statistics)

Example2:the extend and causes of blindness and visual impairment (VI). Table of the data prevalence of VI by age groups in the sample population. Table of result(Statistic values and p-values of different test statistics)

Example3:the MRSS case-control clinical trial which enrolled 168 patients with diffuse scleroderma. Patients are randomly given oral native collagen or placebo, and compare the MRSS(modified Rodnan Skin Scores) in treatment group and control group.

Conclusion

Introduce three test statistics for testing the equality of correlation coefficients in paired binary data with different groups. Score test is recommended in practical use. Since simulation study showed that the Score test has not only robust empirical type I error for various number of groups and sample sizes, but also satisfactory power. With these asymptotic methods studied in this work, we consider developing exact tests for small samples as interesting future work.

Thank you!