Term: Inverse Probability Treatment Weighting (IPTW)

Printer friendly

Glossary Definition

Last Updated: 2015-10-13

Definition:

Inverse Probability Treatment Weighting (IPTW) is a statistical method used to create groups that are otherwise similar when examining the effect of a treatment or exposure.  In contrast to matching treated and untreated individuals on a select group of confounders, the IPTW approach uses the entire cohort and can address a very large number of confounding variables.  Each individual in the cohort is assigned a weight based on the likelihood that they would be exposed to the treatment effect under investigation. Applying this weight when conducting statistical tests or regression models reduces or removes the impact of confounders.

For more inforamtion on the IPTW statistical method, please read the section titled Developing the Comparison Group in the deliverable Long-Term Outcomes Of Manitoba's Insight Mentoring Program: A Comparative Statistical Analysis by Ruth et al. (2015).

Related terms 

• Propensity Scores

References 

• Ruth C, Brownell M, Isbister J, MacWilliam L, Gammon H, Singal D, Soodeen R, McGowan K, Kulbaba C, Boriskewich E. Long-Term Outcomes Of Manitoba's Insight Mentoring Program: A Comparative Statistical Analysis . Winnipeg, MB: Manitoba Centre for Health Policy, 2015. [Report] [Summary] [Additional Materials] (View)