Cost savings–a bleg

My small brain is turned in knots on the seemingly simple question laid out below.

Say I have a clinical trial where the intervention is stopping the drug, and there are no mortality differences between treatment and control groups, and I want to estimate the cost savings of stopping the drug, based on the assumption that it is a good thing to do since it didn’t reduce mortality.

  • Option 1. cost savings are defined after randomization as: incurred costs of the continued group (assume +$10) + the avoided costs of the discontinue group (assume -$10). Savings = $20/person
  • Option 2. cost savings are defined after randomization as: the avoided costs of the discontinued group alone (assume =$10). Savings = $10/person

Option 1 highlights the counterfactual of continued use of the drug, and shows what could be achieved if you managed to get lots of folks to follow the results of the trial (I think). Option 2 is more conservative and only focuses on reduced costs/person who stops.

Which is correct?

About Don Taylor
Professor of Public Policy at Duke University (with appointments in Business, Nursing, Community and Family Medicine, and the Duke Clinical Research Institute). I am one of the founding faculty of the Margolis Center for Health Policy, and currently serve as Chair of Duke's University Priorities Committee (UPC). My research focuses on improving care for persons who are dying, and I am co-PI of a CMMI award in Community Based Palliative Care. I teach both undergrads and grad students at Duke. On twitter @donaldhtaylorjr

2 Responses to Cost savings–a bleg

  1. Ross McKinney, Jr MD says:

    The way to solve it. What would it cost if everyone continues the drug? 10 people x $10 = 100.
    What happens if everyone can stop? 10 people x $0 = $0.
    The savings is thus $100 for 10 people, or $10 per person.

  2. Glenn Cassidy says:

    I agree with Dr. McKinney. Likewise, any attendant changes in care (monitoring, treatment for side effects, etc.) should be normalized to the entire sample, since this study will be used to generalize to all potential users of the drug.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s

%d bloggers like this: