Marginal Structural Models

So you want to compare two treatments–for instance Treatment A and Treatment B–in order to see which one has largest impact on health outcomes. Sure you could do a randomized controlled trial, but let’s say you don’t have the funding for that. You could use real world data to conduct just such an analysis. Let’s…

Causality: Granger Causality

Earlier this year, I reviewed one definition of causality: the Bradford Hill criteria. Now I move from a medical definition causality to one developed by an economist (in fact, an economist from my alma matter). Granger causality basically identifies a variable as causal if: (i) it occurs the outcome of interest and (ii) including past…

Do pharmaceuticals improve quality of life? A Bayesian answer to the question when there is missing data

Let’s say we are interested in determining whether a particular treatment improves quality of life. Common measures of quality of life include EQ-5D, SF-12, and SF-36, among others. However, a systematic review of 237 randomized controlled trials found that only 43% collected SF-12 or SF-36 measures. If you are measuring a treatment’s effect on quality…

Causality: Bradford Hill criteria

If you observe two things occuring, how can you know whether event A causes event B. For instance, consider the case of patients who use a given treatment and finding that they have better health outcomes. While this relationship could be causal in nature, it may not be. For instance, if only people with higher…

Bayesian Statistics

We all know that there are two types of statistics: frequentist and Bayesian.  Frequentist approaches treat parameters to be estimated as fixed quantities and the data we observe to come from a data generating process based on these quantities.  The Bayesian approach assumes that we don’t want to just estimate the parameters as fixed points…

Discrete choice experiments

How have discrete choice experiments changed over time? This is the question Soekhai et al. (2018) try to answer.  They conduct a systematic literature review covering 27 years of data.  Below I summarize some of their findings graphically. First, you see a trend of an increasing number of DCEs. We also see that whereas DCEs…

The problem with propensity score matching when using difference-in-difference

Difference-in-differences attempts to measure causal effects using changes in outcomes across different groups.  One of the key assumptions of differences-in-differences specification are that pre-period trends are similar across these groups.   But what happens if these pre-period trends do appear?  Can the use of propensity score matching solve the problem.  According to a paper by Daw…

Open-Source tools for economic modelling

QuantEcon is an interesting site from some high profile economists advocating for open-source tools for quantitative economic analysis.  The organization describes itself  on their website as follows: QuantEcon is a nonprofit organization dedicated to improving economic modeling by enhancing computational tools for economists.  Our activities include developing and facilitating the development of open source software…