CLIO Learning Modules
Study DesignSelectionSample SizeData Collection and AnalysisHuman Subjects

Ascertaining Exposure
Ascertaining Outcome
Intention-to-treat vs. per-protocol analysis of RCT data
Recall bias
Interviewer bias
Differential Misclassification Bias
Univariate Analysis
Multivariate Analysis
Subgroup Analysis
Data Collection and Analysis
At the end of this section, you should be able to:
  • Define all variables to be collected.
  • Identify ascertainment procedures (interview, charts, diagnostic test, therapeutic intervention).
  • Apply defensive strategies to control or study confounding.
  • Identify methods to deal with classification bias (multivariable analysis?).
  • Identify the main analytic question and secondary questions.
  • Select the statistical test associated with each.
  • Report the power associated with analysis of main question.
  • Optional: generate table shells.

June 4, 2004 v0.20
Copyright © 2004 Stanford School of Medicine