Skip to main content
58 votes
Accepted

Why is Average Treatment Effect different from Average Treatment effect on the Treated?

The Average Treatment Effect (ATE) and the Average Treatment Effect on Treated (ATT) are commonly defined across the different groups of individuals. In addition, ATE and ATT are often different ...
usεr11852's user avatar
  • 44.8k
51 votes
Accepted

Propensity score matching - What is the problem?

It's true that there are not only other ways of performing matching but also ways of adjusting for confounding using just the treatment and potential confounders (e.g., weighting, with or without ...
Noah's user avatar
  • 34.6k
29 votes

Is Propensity Score Matching a "MUST" for Scientific Studies?

Propensity score methods are one type of method used to adjust for confounding. There are several other methods that rely on different assumptions. Some of the most popular include difference-in-...
Noah's user avatar
  • 34.6k
21 votes
Accepted

What are the pros and cons of using mahalanobis distance instead of propensity scores in matching

Mahalanobis distance matching (MDM) and propensity score matching (PSM) are methods of doing the same thing, which is to find a subset of control units similar to treated units to arrive at a balanced ...
Noah's user avatar
  • 34.6k
18 votes
Accepted

matched pairs in Python (Propensity score matching)

The easiest way I've found is to use NearestNeighbors from sklearn: ...
volodymyr's user avatar
  • 389
17 votes

Why does propensity score matching work for causal inference?

I'll try to give you an intuitive understanding with minimal emphasis on the mathematics. The main problem with observational data and analyses that stem from it is confounding. Confounding occurs ...
StatsStudent's user avatar
  • 11.5k
17 votes
Accepted

Should I use a machine learning model to calculate propensity score?

There are two approaches for modeling propensity scores. One is to try to approximate the treatment assignment process as closely as possible, and the other is to obtain propensity scores that yield ...
Noah's user avatar
  • 34.6k
16 votes
Accepted

What are the use cases for Propensity Score Matching?

You need to distinguish between uses of propensity scores for matching of cases versus for more general adjustments. The discussion on this page suggests that there isn't much of a use case for ...
EdM's user avatar
  • 94.6k
14 votes
Accepted

Intuitive explanation for inverse probability of treatment weights (IPTWs) in propensity score weighting?

The propensity score $p(x_i)$ calculated is the probability of subject $i$ to receive a treatment given the information in $X$. The IPTW procedure tries to make counter-factual inference more ...
usεr11852's user avatar
  • 44.8k
14 votes

Propensity score matching - What is the problem?

@Noah's answer is superb and qualifies as a mini review article. To me, the severe problems with PS matching are topped off by (1) it does not represent reproducible research in that the choice of ...
Frank Harrell's user avatar
14 votes
Accepted

Do I need to adjust OLS standard errors after matching?

Following up on Dimitriy's comment, which I agree with. There are (at least) three sources of uncertainty when performing a propensity score matching analysis: 1) the estimation of the PS, 2) the ...
Noah's user avatar
  • 34.6k
13 votes

Why is Average Treatment Effect different from Average Treatment effect on the Treated?

ATE is the average treatment effect, and ATT is the average treatment effect on the treated. The ATT is the effect of the treatment actually applied. Medical studies typically use the ATT as the ...
Yao Zhao's user avatar
  • 277
13 votes
Accepted

Why is Propensity Score Matching better than just Matching?

The procedure you described is not propensity score matching but rather propensity score subclassification. In propensity score matching, pairs of units are selected based on the difference between ...
Noah's user avatar
  • 34.6k
13 votes

What are the use cases for Propensity Score Matching?

Propensity score (PS) analysis has many problems in general, and matching is especially problematic. I prefer covariate adjustment for a spline function of the logit of PS if you need propensity ...
Frank Harrell's user avatar
12 votes

Why is Propensity Score Matching better than just Matching?

Let's step back and think more broadly about how you could match given some data X. Exact or Cell Matching This is hard to do with continuous Xs. You could try rounding/discretizing each variable, but ...
dimitriy's user avatar
  • 36.7k
12 votes

Is Propensity Score Matching a "MUST" for Scientific Studies?

As Alexis pointed out, propensity score matching (PSM) is one of many tools we have in causal inference. Another one is Inverse Probability Weighted Estimator (IPWE). You can also use causal discovery ...
mribeirodantas's user avatar
11 votes

Is it possible to use propensity score matching (or something similar) to create a control group if you do not yet have outcome data?

Not only can you do that, this this one of the main motivations for using matching methods (such as PSM) over other methods. You can perform the matching to select a subset of individuals that you ...
Noah's user avatar
  • 34.6k
10 votes

Why does propensity score matching work for causal inference?

In a strict sense, propensity score adjustment has no more to do with causal inference than regression modeling does. The only real difference with propensity scores is that they make it easier to ...
Frank Harrell's user avatar
10 votes

Difference between marginal and conditional treatment effect? Relating to regression vs. propensity score methods

What do marginal and conditional relate to? Assuming the treatment effects are accurately estimated, the conditional treatment effect relates to the estimated effect on an individual whereas the ...
John G's user avatar
  • 101
10 votes

Difference between covariates and treatment confounders in propensity score matching

The definition of a confounder is somewhat complicated, but VanderWeele & Shpitser (2013) decided A pre-exposure covariate C is a confounder for the effect of A on Y if it is a member of some ...
Noah's user avatar
  • 34.6k
10 votes
Accepted

Matching with Multiple Treatments

I recommend taking a look at Lopez & Gutman (2017), who clearly describe the issues at hand and the methods used to solve them. Based on your description, it sounds like you want the average ...
Noah's user avatar
  • 34.6k
10 votes
Accepted

Why do stabilized IPW weights give the same estimates and SEs as unstabilized weights?

This is because the marginal structural models you're fitting (objects fitw and fitsw) are so-called saturated models. For ...
johansteen's user avatar
10 votes
Accepted

Propensity score matching vs non-parametric regression

This is a great question and one for which there is no single answer, so I won't attempt to give one to be comprehensive. I'll mention a few topics that might satisfy some of your curiosity and point ...
Noah's user avatar
  • 34.6k
9 votes
Accepted

multiple imputation and propensity scores

My understanding is that you should generate individual propensity score models for each data set, then match, then estimate outcomes, then combine the estimates into one. 1) ...
Noah's user avatar
  • 34.6k
9 votes
Accepted

Calculate single absolute standardized difference across levels of a categorical treatment variable cobalt::bal.tab

Author of cobalt here. What the reviewer is requesting doesn't really make a lot of sense. The bias in an effect estimate is a function of the mean difference of ...
Noah's user avatar
  • 34.6k
9 votes
Accepted

How can I use Propensity Scores to adjust for survey non-response bias?

The answer to this depends on whether you have a probability sample versus a nonprobability sample, where a probability sample refers to a sample selected using random sampling from the population. If ...
bschneidr's user avatar
  • 452
8 votes
Accepted

Analysis strategy for rare outcome with matching

Removing good data from an analysis is scientifically suspect in my humble opinion, and naive matching methods are inefficient. It may be very easy to adjust for patient characteristics using ...
Frank Harrell's user avatar
8 votes

How can we justify using "with replacement" in propensity score matching

Matching without replacement can yield very bad matches if the number of comparison observations comparable to the treated observations is small. It keeps variance low at the cost of potential bias. ...
dimitriy's user avatar
  • 36.7k
8 votes
Accepted

Adjusting the model by propensity scores after propensity score matching

This is definitely possible, and its effectiveness is described in Austin (2017). In general, there is little utility to doing this. If the matching was good, the propensity score distributions should ...
Noah's user avatar
  • 34.6k

Only top scored, non community-wiki answers of a minimum length are eligible