Unbiased Analysis of Today's Healthcare Issues

Archive for the 'Econometrics' Category

Trials in Health Policy

Scientists often use randomized controlled trials (RCT) to examine whether certain treatments have a causal effect on patient outcomes.  For social scientists, however, conducting an RCT is more difficult.  Nevertheless, there have been a number of health policy trials. In a recent NEJM paper, Newhouse and Normand (2017) review some of these trials.  A summary […]

Read the rest of this entry »

What can you learn from quality or cost outliers?

Many researchers have pointed to (positive) cost or quality outliers and made the claims that if only all physicians, or hospitals, or regions could be like these high quality or low cost providers/regions, then the health care system would be much more efficient.  Research teams such as the Dartmouth Atlas are famous for finding these conclusions.  […]

Read the rest of this entry »

Does the hedonic treadmill work in reverse?

The hedonic treadmill is a concept that people acclimate to changes in their life and improvements in quality of life. For instance, people who buy a new car have a brief short-term burst of happiness, but after people acclimate to having the car, their quality of life returns to the previous level. This concept can be […]

Read the rest of this entry »

Measuring the effect of multiple comorbidities on health care costs: Q&A Style

Q: What is the effect of the number of patient comorbidities on health care spending? A: This is a simple analysis to do. One could just run a regression with cost as the dependent variable and the number of comorbidities as an independent.   Q: What if the effect of the number of comorbitiides is […]

Read the rest of this entry »

“You can’t fix by analysis what you bungled by design”

This is a quote from Light, Singer, and Willet (1990) and is mentioned on a recent commentary by Stephen B. Soumerai  and Ross Koppel in Health Services Research. The commentary focuses on the use of instrumental variables when conducting health care effectiveness reserach.  They define instrumental variables concisely as: An instrumental variable (IV) is a variable, generally found in […]

Read the rest of this entry »

Stratified Covariate Balancing

When selection bias is an issue, many researchers use propensity score matching to insure that observable differences in patient characteristics are balanced between individuals who receive a given treatment and those who do not.  If unobservable characteristics are correlated with observable characteristics, propensity score matching generally works well. Cases where propensity score matching does not work well include […]

Read the rest of this entry »

What is a Pseudo R-squared?

When running an ordinary least squares (OLS) regression, one common metric to assess model fit is the R-squared (R2). The R2 metric can is calculated as follows. R2 = 1 – [Σi(yi-ŷi)2]/[Σi(yi-ȳ)2] The dependent variable is y, the predicted value from the OLS regression is ŷ, and the average value of y across all observations […]

Read the rest of this entry »

Optimal Matching Techniques

In randomized controlled trials, participants are randomized to different groups where each group receives a unique intervention (or control). This process insures that any differences in the outcomes of interest are due entirely to the interventions under investigation.   While RCTs are useful, they are expensive to run, are highly controlled and suffer from their own […]

Read the rest of this entry »

Berkson’s paradox

Berkson’s paradox happens when given two independent events, if you only consider outcomes where at least one occurs, then they become negatively dependent.  More technically, this paradox occurs when there is ascertainment bias in a study design. Let me provide an example. Consider the case where patients can have diabetes or HIV.  Assume that patients have a positive probability of […]

Read the rest of this entry »

The problem with p-values

Interesting article in Aeon on why p-values may not be the best way to determine the probability we are observing a real effect in a study. Tests of statistical significance proceed by calculating the probability of making our observations (or the more extreme ones) if there were no real effect. This isn’t an assertion that […]

Read the rest of this entry »