Medical statistics and Data Science: Epidemiology

Quantitative Bais Aanlysis in Epidemiology

This has not been finished, we are still working on it.

Background

underdevelopment

Install Stata commands

  • biasepi
    • Second verion of Stata-package biasepi is ready. It includs three Stata commands (biascon, biasmis, and biasselect) to perform simple bias analysis, multidimensional bias analysis, multiple bias modelinging in epidemiological data. Combining the existing Stata commands, the package is capable to perform probabilitic bias analysis. Type and run "ssc describe biasepi" in the Stata command window. You should be able to view and download the commands.

      Be aware: you may have to remove the older version, if so, the following may help.

      • PC: Go to C driver → ado → plus → b, remove biasepi, biasselect, biascon, biasmis
      • Mac: Go to Folder → Library → Application support → Stata → Plus → b, remove biasepi, biasselect, biascon, biasmis

  • episens
    • In the Stata command window, type "search episens", you should be able find the information on command "episens" by Nicola Orsini et al.4

Selection bias

  • Single bias analysis
  • Multiple bias analysis
  • Probalistic bias analysis

Unmeasured and Unknown Confounders

  • Single bias analysis
  • Multiple bias analysis
  • Probalistic bias analysis

Misclassification

  • Single bias analysis
  • Multiple bias analysis
  • Probalistic bias analysis

References

  1. Lash TL, Fox MP, MacLehose RF, Maldonado G, McCandless LC, Greenland S. Good practices for quantitative bias analysis. Int J Epidemiol. 2014 Link
  2. Fox MP, Lash TL. On the Need for Quantitative Bias Analysis in the Peer-Review Process. Am J Epidemiol. 2017 Link
  3. Lash TL, Fox MP, and Fink AK. Applying Quantitative Bias Analysis to Epidemiologic Data Link
  4. Orsini N, Bellocco R, Bottai M, Wolk A, and Greenland S. A tool for deterministic and probabilistic sensitivity analysis of epidemiologic studies Link