R

Well, maybe you haven’t, but this seems to come up all the time. An investigator wants to assess the effect of an intervention on a outcome. Study participants are randomized either to receive the intervention (could be a new drug, new protocol, behavioral intervention, whatever) or treatment as usual. For each participant, the outcome measure is recorded at baseline - this is the pre in pre/post analysis. The intervention is delivered (or not, in the case of the control group), some time passes, and the outcome is measured a second time. This is our post. The question is, how should we analyze this study to draw conclusions about the intervention’s effect on the outcome?

I’m contemplating the idea of teaching a course on simulation next fall, so I have been exploring various topics that I might include. (If anyone has great ideas either because you have taught such a course or taken one, definitely drop me a note.) Monte Carlo (MC) simulation is an obvious one. I like the idea of talking about importance sampling, because it sheds light on the idea that not all MC simulations are created equally. I thought I’d do a brief post to share some code I put together that demonstrates MC simulation generally, and shows how importance sampling can be an improvement.

My dissertation work (which I only recently completed - in 2012 - even though I am not exactly young, a whole story on its own) focused on inverse probability weighting methods to estimate a causal cost-effectiveness model. I don’t really do any cost-effectiveness analysis (CEA) anymore, but it came up very recently when some folks in the Netherlands contacted me about using simstudy to generate correlated (and clustered) data to compare different approaches to estimating cost-effectiveness. As part of this effort, I developed two more functions in simstudy that allow users to generate correlated data drawn from different types of distributions. Earlier I had created the CorGen functions to generate multivariate data from a single distribution – e.g. multivariate gamma. Now, with the new CorFlex functions (genCorFlex and addCorFlex), users can mix and match distributions. The new version of simstudy is not yet up on CRAN, but is available for download from my github site. If you use RStudio, you can install using devtools::install.github("kgoldfeld/simstudy"). [Update: simstudy version 0.1.8 is now available on CRAN.]

I am going to cut right to the chase, since this is the third of three posts related to confounding and weighting, and it’s kind of a long one. (If you want to catch up, the first two are here and here.) My aim with these three posts is to provide a basic explanation of the marginal structural model (MSM) and how we should interpret the estimates. This is obviously a very rich topic with a vast literature, so if you remain interested in the topic, I recommend checking out this (as of yet unpublished) text book by Hernán & Robins for starters.

Towards the end of Part 1 of this short series on confounding, IPW, and (hopefully) marginal structural models, I talked a little bit about the fact that inverse probability weighting (IPW) can provide unbiased estimates of marginal causal effects in the context of confounding just as more traditional regression models like OLS can. I used an example based on a normally distributed outcome. Now, that example wasn’t super interesting, because in the case of a linear model with homogeneous treatment effects (i.e. no interaction), the marginal causal effect is the same as the conditional effect (that is, conditional on the confounders.) There was no real reason to use IPW in that example - I just wanted to illustrate that the estimates looked reasonable.

Way back when I was studying algebra and wrestling with one word problem after another (I think now they call them story problems), I complained to my father. He laughed and told me to get used to it. “Life is one big word problem,” is how he put it. Well, maybe one could say any statistical analysis is really just some form of multilevel data analysis, whether we treat it that way or not.

When we are trying to assess the effect of an exposure or intervention on an outcome, confounding is an ever-present threat to our ability to draw the proper conclusions. My goal (starting here and continuing in upcoming posts) is to think a bit about how to characterize confounding in a way that makes it possible to literally see why improperly estimating intervention effects might lead to bias.

I just updated simstudy to version 0.1.7. It is available on CRAN.

To mark the occasion, I wanted to highlight a new function, genOrdCat, which puts into practice some code that I presented a little while back as part of a discussion of ordinal logistic regression. The new function was motivated by a reader/researcher who came across my blog while wrestling with a simulation study. After a little back and forth about how to generate ordinal categorical data, I ended up with a function that might be useful. Here’s a little example that uses the likert package, which makes plotting Likert-type easy and attractive.

Here’s the scenario: we have an intervention that we think will improve outcomes for a particular population. Furthermore, there are two sub-groups (let’s say defined by which of two medical conditions each person in the population has) and we are interested in knowing if the intervention effect is different for each sub-group.

And here’s the question: what is the ideal way to set up a study so that we can assess (1) the intervention effects on the group as a whole, but also (2) the sub-group specific intervention effects?

I just released a new iteration of simstudy (version 0.1.6), which fixes a bug or two and adds several spline related routines (available on CRAN). The previous post focused on using spline curves to generate data, so I won’t repeat myself here. And, apropos of nothing really - I thought I’d take the opportunity to do a simple simulation to briefly explore the likelihood function. It turns out if we generate lots of them, it can be pretty, and maybe provide a little insight.