Statistical models for vaccines using. propensity score. Aksel Jensen 1,2. What is a. propensity. score? Why use a. propensity. score?

Similar documents
Big data size isn t enough! Irene Petersen, PhD Primary Care & Population Health

How to choose an analysis to handle missing data in longitudinal observational studies

Imputation Methods to Deal with Missing Values when Data Mining Trauma Injury Data

Overview. Longitudinal Data Variation and Correlation Different Approaches. Linear Mixed Models Generalized Linear Mixed Models

Basic Statistics and Data Analysis for Health Researchers from Foreign Countries

The Cross-Sectional Study:

Title: Proton Pump Inhibitors and the risk of pneumonia: a comparison of cohort and self-controlled case series designs

Many research questions in epidemiology are concerned. Estimation of Direct Causal Effects ORIGINAL ARTICLE

SAS and R calculations for cause specific hazard ratios in a competing risks analysis with time dependent covariates

Handling missing data in Stata a whirlwind tour

Chapter 3. Sampling. Sampling Methods

Age at First Measles-Mumps. Mumps-Rubella Vaccination in Children with Autism and School-Matched Control Subjects. Frank DeStefano, MD, MPH

Dealing with Missing Data

Analysis of Longitudinal Data for Inference and Prediction. Patrick J. Heagerty PhD Department of Biostatistics University of Washington

Two Tools for the Analysis of Longitudinal Data: Motivations, Applications and Issues

Estimating causal effects of public health education campaigns using propensity score methodology *

Implementing Propensity Score Matching Estimators with STATA

Maternal Employment and Child Development: A Fresh Look Using Newer Methods

Randomized trials versus observational studies

The Harvard MPH in Epidemiology Online/On-Campus/In the Field. Two-Year, Part-Time Program. Sample Curriculum Guide

With Big Data Comes Big Responsibility

AN INTRODUCTION TO MATCHING METHODS FOR CAUSAL INFERENCE

COMMON METHODOLOGICAL ISSUES FOR CER IN BIG DATA

Impact of Community-Based Rehabilitation (CBR) programs in Mandya district (Karnataka, India)

14.74 Lecture 7: The effect of school buildings on schooling: A naturalexperiment

Programme du parcours Clinical Epidemiology UMR 1. Methods in therapeutic evaluation A Dechartres/A Flahault

Missing values in data analysis: Ignore or Impute?

A comparison of Academic Achievement in Independent and State Schools

Missing Data in Longitudinal Studies: To Impute or not to Impute? Robert Platt, PhD McGill University

Missing Data: Part 1 What to Do? Carol B. Thompson Johns Hopkins Biostatistics Center SON Brown Bag 3/20/13

The Harvard MPH in Epidemiology Online/On-Campus/In the Field. Two-Year, Part-Time Program. Sample Curriculum Guide

Organizing Your Approach to a Data Analysis

Missing data and net survival analysis Bernard Rachet

Confounding in health research

Improving Experiments by Optimal Blocking: Minimizing the Maximum Within-block Distance

Impact of Critical Care Nursing on 30-day Mortality of Mechanically Ventilated Older Adults

Prospective, retrospective, and cross-sectional studies

Diabetes Care 29:15 19, 2006

Module 223 Major A: Concepts, methods and design in Epidemiology

Addition of vaccination against hepatitis B infection and change of the HPV vaccination programme

The Impact of Retail Payment Innovations on Cash Usage

Profit-sharing and the financial performance of firms: Evidence from Germany

SOLUTIONS TO BIOSTATISTICS PRACTICE PROBLEMS

Missing data in randomized controlled trials (RCTs) can

How To Find Out If A Local Market Price Is Lower Than A Local Price

Workshop on Impact Evaluation of Public Health Programs: Introduction. NIE-SAATHII-Berkeley

Epidemiologists typically seek to answer causal questions using statistical data:

Modelling spousal mortality dependence: evidence of heterogeneities and implications

Guide to Biostatistics

The Product Review Life Cycle A Brief Overview

Multiple Imputation for Missing Data: A Cautionary Tale

Placement Stability and Number of Children in a Foster Home. Mark F. Testa. Martin Nieto. Tamara L. Fuller

Many studies in social science that aim to BEST PRACTICES IN QUASI- EXPERIMENTAL DESIGNS. Matching Methods for Causal Inference ELIZABETH A.

Methods for Meta-analysis in Medical Research

The PCORI Methodology Report. Appendix A: Methodology Standards

Basic Study Designs in Analytical Epidemiology For Observational Studies

Chapter 4. Study Designs

Overview of study designs

Applied Missing Data Analysis in the Health Sciences. Statistics in Practice

INVESTIGATIONS. Page 1

Using Monitoring and Evaluation to Improve Public Policy

BIG DATA: CONVENTIONAL METHODS MEET UNCONVENTIONAL DATA

A Comparison of Propensity Score and Linear Regression Analysis of Complex Survey Data

Introduction to Fixed Effects Methods

ESSAYS IN CHILDREN S ACCESS TO HEALTH CARE. Sean Michael Orzol

A course on Longitudinal data analysis : what did we learn? COMPASS 11/03/2011

Cohort Studies. Sukon Kanchanaraksa, PhD Johns Hopkins University

TUTORIAL on ICH E9 and Other Statistical Regulatory Guidance. Session 1: ICH E9 and E10. PSI Conference, May 2011

PREDICTIVE ANALYTICS: PROVIDING NOVEL APPROACHES TO ENHANCE OUTCOMES RESEARCH LEVERAGING BIG AND COMPLEX DATA

Clinical Study Design and Methods Terminology

Basic of Epidemiology in Ophthalmology Rajiv Khandekar. Presented in the 2nd Series of the MEACO Live Scientific Lectures 11 August 2014 Riyadh, KSA

Financial Aid and Student Retention ***** Gauging Causality in Discrete Choice Propensity Score Matching Models

Prospective Life Tables

Machine Learning Methods for Causal Effects. Susan Athey, Stanford University Guido Imbens, Stanford University

Bias of the regression estimator for experiments using clustered random assignment

Childhood Diseases and potential risks during pregnancy: (All information available on the March of Dimes Web Site.)

Effects of Corporate Diversification Revisited: New Evidence from the Property-Liability Insurance industry

6/15/2005 7:54 PM. Affirmative Action s Affirmative Actions: A Reply to Sander

Statistical Rules of Thumb

Some aspects of propensity score-based estimators for causal inference

How to set the main menu of STATA to default factory settings standards

Big data in health research Professor Tony Blakely

Effect of Pretransplant Serum Creatinine on the Survival Benefit of Liver Transplantation

COMMITTEE FOR VETERINARY MEDICINAL PRODUCTS GUIDELINE FOR THE CONDUCT OF POST-MARKETING SURVEILLANCE STUDIES OF VETERINARY MEDICINAL PRODUCTS

Deutsches Institut für Ernährungsforschung Potsdam-Rehbrücke. DAG program (v0.21)

Standard Comparison Protocols at NICU, Regional and National levels.

Safety & Effectiveness of Drug Therapies for Type 2 Diabetes: Are pharmacoepi studies part of the problem, or part of the solution?

Module 7 Expanded Programme of Immunization (EPI)

STATISTICAL ANALYSIS OF SAFETY DATA IN LONG-TERM CLINICAL TRIALS

Snap shot. Cross-sectional surveys. FETP India

What do we mean by cause in public health?

RATIOS, PROPORTIONS, PERCENTAGES, AND RATES

Large Danish birth cohorts -- what have we learned?

Educational Epidemiology: Applying a Public Health Perspective to Issues and Challenges in Education

Chemicals and childhood leukemia

HOW LABOR MARKETS AND WELFARE POLICIES SHAPE HEALTH ACROSS THE LIFE COURSE:

Skilled Nursing Facility Rehabilitation and Discharge to Home After Stroke

Which flu vaccine should you or your child

AVOIDING BIAS AND RANDOM ERROR IN DATA ANALYSIS

March ABSTRACT

Transcription:

1 / 10 1 CVIVA, Research Center For Vitamins & Vaccines, Statens Serum Institut. 2 Department of Biostatistics, University of Copenhagen.

2 / 10 Outline How can a be used? What are the challenges in the current Ph.D project?

3 / 10 What do we want to model? We want to compare intensities - possibly time-dependent. not vac (0) α 02 (t) α 01 (t) dead (2) vac (1) α 12 (t)

4 / 10 A is a probability. Examples: 1. The probability of recieving a treatment. 2. The probablity of having recieved measles vaccine at 12 month of age. 3. The probablity of having recieved measles vaccine at age t (time-dependent -). Often the will depend on covariates e.g., sex, birth weight, homebirth, mothers age at birth, etc.

5 / 10 1/3 Observational studies and randomized studies typically, does not estimate the same parameter. Observational studies (regression analysis) estimate conditional effects: Given all others covariates equal what is the effect of being vaccinated (effects assumed equal for all subgroups). Randomized studies estimate causal effects: Compare outcome in two equal populations which only differ on vaccination status (effects possibly different in subgroups).

6 / 10 2/3 Using - techniques in analysis of observational data one can mimic a randomized study. Mimic means: We estimate the same parameter (the average causal effect) as in a randomized study. Note: Propensity analysis can not mimic balance of unmeasured confounders.

7 / 10 3/3 Other advantages of approach compared to ordinary regression analysis: 1. If outcome is rare (e.g. death) and treatment common (e.g. vaccination) a much richer model is allowed. 2. In general the model is more robust to misspecification. 3. Easier to detect non-comparable subjects or subgroups (they have a close to 0 or 1). Note: an ordinary regression potentially involves a lot of extrapolation.

8 / 10 In general 4 different methods: 1. Stratification on. 2. Match (1:1) exposed to unexposed based on. 3. Create pseudo population based on weighting by the inverse of the. 4. Include the as a covariate in a regression model. All 4 have been thoroughly studied in simple setups (time-invariant s) and are more or less interpretable.

9 / 10 Ongoing research Some themes in the current Ph.D project: 1. How to build an appropriate time-dependent - for vaccination status. 2. How to use this -. Matching? Create pseudo-population? 3. How to build models which can include and handle different vaccination-histories. (multistate models) 4. How to handle survival-bias (caused by missing vaccination cards) without throwing away information (landmark approach). death 1. visit 2. visit

10 / 10 References Rosenbaum P.R., Rubin D.B. The central role of the in observational studies for causal effects. Biometrika, 70(1):41 55, 1983. Williamson E., Morley R., Lucas A., and Carpenter J. Propensity s: From nave enthusiasm to intuitive understanding. Methods in Medical Research, 21(3):273 293, 2012. D Agostino R.B. Propensity methods for bias reduction in the comparison of a treatment to a non-randomized control group. Statistics in Medicine, 17(19):2265 2281, 1998.