The problem with instrumental variables

When using real-world data, researchers must always deal with a key issue: selection bias.  To get around this bias, many health care researchers use an instrumental variable that can predict the explanatory variable of interest (e.g., receipt of a specific treatment) but is not correlated with patient outcomes (e.g., mortality). A commonly used IV is…

DA Henderson, RIP

The man, Donal Ainslie (DA) Anderson, whole help eliminate smallpox died on August 19.  The Economist has an obituary to the man. This crowd of helpers, which delighted him, meant that no Nobel prize could be given for wiping out smallpox. If it had been, he might have shared it with William Foege, who first devised…

How to prevent another EpiPen controversy

Dana Goldman–my colleague at PHE and a professor at USC–offers three suggestions on how to prevent generic products from increasing their prices drastically as occurred in the EpiPen saga.  In Stat News, he makes three recommendations: First, Congress should mandate that the Federal Trade Commission report on the availability of all such drugs and devices…

Will payers pay for new healthcare technologies

Wearables, digital medicine and ‘beyond-the-pill’ are the latest healthcare craze.  New technologies–particular those combined with patients mobile phones–offer the promise of improving patient health.  One question is will insurance companies, the government and other payers actually reimburse for these technologies.  According to a recent FiercePharma article, the answer is yes…if there is evidence. Payers say they’re willing…

The End of the Obamacare Exchanges

Princeton economist Uwe Reinhardt things so.  In an interview with Vox he states: The natural business model of a private commercial insurer is to price on health status and have the flexibility to raise prices year after year. What we’ve tried to do, instead, is do community rating [where insurers can’t price on how sick…

AA and selection bias

This video that discusses whether alcoholics anonymous actually improves the outcomes of alcoholics who attend the meeting.  More broadly, the video the AA treatment effect discussion serves as an example for expounding on some fundamental statistical issues such as selection bias, randomization, intention to treat, marginal effect, instrumental variables, and others.

Does adherence information affect physician decisions?

According to a recent study of patients with hypertension, the answer is yes. The study by Kronish et al. (2016) used a cluster randomized trial design made up of 24 providers and 100 patients.  Half of the providers were randomized to receive received a report summarizing electronically measured patient adherence to their blood pressure regimen as well as and recommended clinical to…

Another VBP fail?

Value-based purchasing is supposed to tie reimbursement to quality of care and costs.  Providers that are high quality and low cost are supposed to get higher reimbursement, those that are low quality and high cost the reverse.  The key question is: does this reimbursement approach work in practice? According to a recent study by Grabowski…