Category 3: Standards for Data Integrity and Rigorous Analyses

Learning Objectives

Cognitive: Compare the content of different types of secondary data to select data appropriate to study goals; Describe the characteristics of a well-validated exposure or outcome variable, including scales; Explain the key threats to validity of exposure and outcome variables in secondary data sets; State the purpose of control of confounding in secondary data analyses; Define internal and external validity of a study using secondary data.

Attitudinal: Appreciate the challenge of assessing the causal effects of exposures on outcomes from observational or experimental studies; Commit to protecting data from breaches of confidentiality and privacy; Recognize the importance of capturing the diverse sources of uncertainty in estimates of causal effects through sensitivity and other analyses. 

Skills: Draw a causal graph that represents the major observed variables, unobserved variables, and assumptions that constitute the proposed analysis; Select one or more data sets that meet the project’s needs; Develop an analytic plan to address the specific aims of the project; Choose validated exposure and outcome variables, when available; Prepare a satisfactory description of a plan for control of confounding; Prepare a plan to address potential bias and variance in effect estimates caused by unobserved variables—for example, using instrumental variables or sensitivity analyses; Formulate a thoughtful plan for subgroup analyses and/or sensitivity analyses as needed to address specific aims; Apply tools to assess a proposed study’s internal validity at the time of study design; Conduct analyses that are reproducible by others.

Learning Modules

This category contains the curriculum Introduction and nine main modules. Learn about the instructors for this curriculum.

• Introductory Lecture: Prepared and presented by Jodi Segal, MD, MPH
• Learning Modules: Prepared by Jodi Segal, MD, MPH, and Scott Zeger, PhD; Presented by Jodi Segal, MD, MPH

Module 1: Introduction
Watch | Listen | Handout

Module 2: Objectives and Objectives Illustration
Watch | Listen | Handout

Module 3: Initial Considerations regarding Data Integrity and Rigorous Analyses
Watch | Listen | Handout

Module 4: Thinking about Causality
Watch | Listen | Handout

Module 5a: Primary Data
Watch | Listen | Handout

Module 5b: Secondary Data
Watch | Listen | Handout

Module 6a: Imperfect Exposure Variables
Watch | Listen | Handout

Module 6b: Imperfect Outcome Variables
Watch | Listen | Handout

Module 6c: Attention to Scales and Instruments
Watch | Listen | Handout

Module 7a: Planning Analyses of Observational Data
Watch | Listen | Handout

Module 7b: Describing a Data Analysis Plan
Watch | Listen | Handout

Module 8a: Matching and Restriction
Watch | Listen | Handout

Module 8b: Standardization, Stratification, and Regression
Watch | Listen | Handout

Module 8c: Introduction to Propensity Scores
Watch | Listen | Handout

Module 9: Summary
Watch | Listen | Handout

Interview with Nancy Kass, ScD, Phoebe R. Berman Professor of Bioethics and Public Health in the Department of Health Policy and Management, Johns Hopkins Bloomberg School of Public Health, and Deputy Director for Public Health in the Berman Institute of Bioethics, on why the application of good methods is an ethical question
Listen

Category 3 Self-Assessment
View

Back to the Methodology Standards Academic Curriculum main page

Posted: February 2016