Questions tagged [matching]

Matching refers to a process in experimental design in which observations are sampled in a systematic, non-random fashion to be analyzed more efficiently with special statistical methods.

Filter by
Sorted by
Tagged with
0 votes
0 answers
15 views

MatchIt in R option for euclidean distance matching [closed]

I read in MatchIt that there is option to specify "euclidean" for distance: https://cran.r-project.org/web/packages/MatchIt/MatchIt.pdf. However when I put distance = "euclidean" ...
user avatar
1 vote
0 answers
15 views

Common Trend Assumption in Difference-in-differences

I'm running a DiD analysis on whether the introduction of a spinoff NFT (non-fungible token) collection affects the prices of the parent NFT collection. First thing that I did is to visually test ...
user avatar
1 vote
1 answer
28 views

Stata teffects ATET

How does stata estimates ATET (Average Treatment Effect on the Treated) using teffects psmatch. I understand the average treatment effect (ATE) is computed by taking the average of the difference ...
user avatar
  • 11
2 votes
1 answer
18 views

Limits to how many control and treatment subjects may be paired in propensity score matching?

I'm working on a difference-in-differences project where we're matching up to 5 control subjects to each treatment subject using a combination of techniques to estimate treatment effects (ATT): exact, ...
user avatar
  • 4,514
1 vote
1 answer
19 views

Balance diagnostics: Why not measure post-matching balance **within** matched treatment-control pairs?

I understand there are a number of techniques for evaluating post-matching balance at the covariate level: standardized mean difference (SMD), variance ratios, and empirical CDF statistics. Are there ...
user avatar
  • 4,514
1 vote
1 answer
22 views

How to perform fine balance matching in R for several covariates?

I want to use fine balance matching to balance the marginal distribution of some covariates, so that it will be less stringent than exact matching. Below are some options I found: The ...
user avatar
  • 475
0 votes
0 answers
33 views

Is propensity score matching out of favor? [duplicate]

I came across this post, which was largely nonsensical, but a respondent suggested the original poster follow up with two articles: Ho, D. E., Imai, K., King, G., & Stuart, E. A. (2007). Matching ...
user avatar
  • 169
1 vote
0 answers
22 views

If I'm conducting a matched study with multiple levels (e.g., students within classrooms), what is the appropriate level to match on?

Let's say that I'm conducting a non-randomized matching evaluating of an educational intervention to determine its impact on student grades. While the students receive the intervention, the teachers ...
user avatar
  • 157
3 votes
1 answer
46 views

What is the positivity assumption required for matching and ATT estimand?

Does ATT estimand require a less stringent positivity assumption in matching? For example, if a small treated group is matched to a large control group, most of the control subjects will be discarded ...
user avatar
  • 475
1 vote
1 answer
49 views

Dependent t-test or something else when pre- and post-scores use different scales?

What would be the most appropriate statistic to use if one wanted to see whether an instructional treatment produced learning gains in a classroom in which all students were tested before and after ...
user avatar
  • 113
1 vote
0 answers
31 views

Choosing variables for propensity score matching

I'm working on a project dealing with transplants and comparing outcomes of first time (primary) transplants with re-transplants. I'm trying to decide which set of variables to include for propensity ...
user avatar
  • 11
3 votes
0 answers
38 views

Matching on pre-treatment outcome $z$-score in diff-in-diff analysis to avoid regression toward the mean bias in $ATT$ estimates?

There have been many articles (e.g., Chabé-Ferret (2017), Daw & Hatfield (2018), Zeldow & Hatfield (2021)) discussing the perils of matching on pre-treatment outcomes (such as patient's ...
user avatar
  • 4,514
1 vote
0 answers
49 views

How to interpret covariate balance table for binary variables in inverse probability treatment weighting

A quick question on how to interpret balance measures in a IPTW analysis. Here is an example code from the cobalt package: ...
user avatar
1 vote
0 answers
21 views

Matching weights

I am planning to apply propensity score matching with exact marching on two categorical variables and balancing on the rest of my covariates. Are the weights obtained from the matchit function related ...
user avatar
2 votes
1 answer
43 views

How does coarsened exact matching method in R package MatchIt determine the cutpoints for matching?

It is unclear to me how the cutpoints are determined after we selected the number of cutpoints for each covariate. What is the default "sturges" option? ...
user avatar
  • 475
0 votes
2 answers
35 views

STATA - Mean differences between treated and control groups after matching

Relevant Files: https://www.dropbox.com/sh/0jnj3txf4stb2q8/AAD58COnAUysul58qG2p5emwa?dl=0 ...
user avatar
0 votes
0 answers
33 views

Matching fixed control group to multiple time-varying treatment events so that each control is only used once/uniquely assigned

you have helped me tremendously over the past years and so far, I could find an answer to any the question I had! Thanks to anyone active in this community, I don't know what I would have done without ...
user avatar
  • 1
0 votes
0 answers
17 views

What are weights in coarsened exact matching? [duplicate]

I am using MatchIt in R to estimate the treatment effect on the treated (ATT) using Coarsened Exact Matching. Here's a replicable example of what I'm trying to do: <...
user avatar
0 votes
1 answer
37 views

How to do random matching within a certain propensity score range using MatchIt package in R

I have a large dataset containing about 20,000 individuals. Among them, there are about 200 people classified as disease group and the remaining 19,800 classified as normal controls. I want to do 1:1 ...
user avatar
  • 1
0 votes
0 answers
23 views

How to match Individuals from Origins to Locations using frequency distribution

Context I have a matching problem in which I try to match individuals $I$ from origins $O$ to destinations $D$. After assignment I then want to calculate some destination-level statistics (think e.g. ...
user avatar
0 votes
1 answer
26 views

Proper way to setup propensity matching

I'm involved in a study where we want to examine the effects of two different types of implant on a variety of health outcomes. We've collected a ton of data on about 200 patients who received either ...
user avatar
3 votes
1 answer
104 views

Nearest Neighbor Matching

This is probably a very basic question. But I spent a good part of 2 weeks trying to understand this (by reading textbooks, searching on internet, listening to lectures) but haven't gotten anywhere ...
user avatar
  • 31
0 votes
1 answer
45 views

Matching two distributions and subsampling

This should be a simple problem that I have no idea how to solve it. I have two datasets in R each with 3 columns (ID, Age and a response to a drug). I want to subsample both these datasets and build ...
user avatar
1 vote
1 answer
70 views

What is the ATE in the output of stata with psmatch2 or teffects psmatch

It has been known that we can not get ATE from MatchIt package with method = "nearest" in R because What is the ...
user avatar
  • 43
2 votes
1 answer
26 views

Prioritize variables in Matchit() R function [closed]

In the following matchit() example, I want to give more importance to (prioritize) matching Sales1 and ...
user avatar
0 votes
1 answer
165 views

Standardized mean difference of ATT, ATE, ATU in MatchIt in R

The MatchIt package manual says that: The standardized mean differences are computed both before and after matching or subclassification as the difference in treatment group means divided by a ...
user avatar
  • 43
0 votes
1 answer
47 views

Matching using R -- complex design with repeated controls

I am seeking help on using Matching with R on a particular data structure. I reproduce below the general idea how the data looks like. I have a "pool of control" units that I want to re-used ...
user avatar
  • 781
1 vote
1 answer
44 views

Propensity score match with exact matching on one variable

I would like to compare survival outcomes of two groups (control vs. treatment). Because of imbalances of baseline covariates, I used propensity score matching using nearest neighbor matching. After ...
user avatar
  • 129
0 votes
1 answer
44 views

Weights for estimating ATE (rather than ATT) in SAS %CEM macro for coarsened exact matching?

I'm running Gary King's %CEM SAS macro (available here) for coarsened exact matching (CEM) for a project at work. The macro works fine for estimating the Average Treatment Effect on the Treated (ATT) ...
user avatar
  • 4,514
1 vote
0 answers
29 views

How can I understand ATT estimator for matching discrepancies in Causal Inference Mixtape?

While studying 'Causal Inference: Mixtape' by myself, something I didn't know happened. link: https://mixtape.scunning.com/matching-and-subclassification.html#bias-correction $\begin{align} \...
user avatar
1 vote
1 answer
115 views

Interpreting regression coefficients for covariates after matching

I am new to the fascinating world of matching and propensity scoring. It is highly likely that I will be using some (or more) matching method(s) for my forthcoming project, probably with the R package ...
user avatar
  • 13
11 votes
2 answers
2k views

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

Recently, I have been reading about Propensity Score Matching : If I have understood this correctly, Propensity Score Matching is used to construct control/treatment groups in scientific studies, in ...
user avatar
  • 5,754
2 votes
1 answer
49 views

Feature Selection and Propensity Score Matching

After reading the section on variable selection in OHDSI for population-level estimation effects, I set out to add additional covariates to my process. As suggested, I began looking at implementing ...
user avatar
  • 35
0 votes
1 answer
55 views

Estimate effects after exact matching

I am working on a project, and I have to use matching. I decided to go to exact matching, and surprisingly I did not lose too many observations. But I have a dilemma about how to conduct the analysis ...
user avatar
  • 1
1 vote
1 answer
42 views

Replicating Simulation Study of Gary King in R

In this article, the authors describes the following simulation study of Propensity Score Matching, For each of two covariates, we randomly and independently draw ...
user avatar
  • 113
4 votes
1 answer
80 views

Is propensity score matching worse than other matching methods? [duplicate]

Gary King explained why he thought propensity score matching should not be used for matching. See Paper and the Video Lecture. After all these years, have the academics/practitioners reached consensus ...
user avatar
2 votes
0 answers
35 views

How to accommodate endogeneity after matching?

I am working on a field experiment where assignment to treatment vs. comparison was random, but participation uptake was not. The design is pre-post, and attrition is certainly not MCAR. This is a ...
user avatar
0 votes
1 answer
16 views

Matching across groups on R to control the influence of confounders

I have a cohort of individuals whose exact glucose measurements I have. I want to look at the influence of a variable (which I can call Var1) on the variation of glucose in this group. However, i don'...
user avatar
  • 1
4 votes
2 answers
227 views

Understanding Propensity Score Matching

I am trying to better understand the motivations and the applications behind Propensity Score Matching. I read the following that explains the motivations behind Propensity Score Matching: Suppose ...
user avatar
  • 5,754
1 vote
0 answers
36 views

How to calculate propensity scores for multiple treatments with different predictors?

I use propensity score matching with one control condition $d\in\{0\}$ and multiple treatment conditions $d\in\{A, B, AB\}$, where $AB$ denotes the combination of (relatively unrelated) treatments $A$ ...
user avatar
  • 566
0 votes
1 answer
155 views

Why Multivariate L1 Distance from Coarsened Exact Matching (CEM) is high compared to Univariate Imbalance for each matching covariate?

I was looking at a paper link here by Blackwell et al. (2010) on CEM in Stata. In one example using an example data set, the authors ran CEM using the matching covariates such as age, education, black,...
user avatar
  • 141
0 votes
0 answers
19 views

How to weigh data points to match multiple dimensions?

I am trying to match the results of one survey to another. I would like sex and age to match, so first, I weigh each datapoint to match the distribution of male/female. However, when trying to weigh ...
user avatar
0 votes
1 answer
44 views

Matching and DiD - understanding of the control group

Im trying to understand the methodology of matching and how to matches are used in this article. Specifically, are treated firms compared the WHOLE group of matched firms (ie all firms that got ...
user avatar
1 vote
0 answers
34 views

Add Age/sex as covariates when the groups are already Age- and Sex-matched? [duplicate]

Context: I am working on a longitudinal study that aim to analyse a response variable in Alzheimer's disease population and determine the differences between 4 groups of the AD population I want to ...
user avatar
  • 457
0 votes
0 answers
28 views

Running a logistic model on matched exposed and unexposed groups (matched variable still significant)

I have the following group that was created based on an exposure: Exposed group: ...
user avatar
4 votes
1 answer
84 views

Why does propensity score matching fail to estimate the true causal effect when OLS works?

Consider the following model (DAG), where D is the treatment (exposure) and Y1 is the outcome. To estimate the causal effect of <...
user avatar
  • 781
1 vote
0 answers
19 views

Matched Pairs, GEE Models, and Other Regression Models

I am presenting the following hypothetical example in which the variables may or may not make sense clinically. A study has 100 matched pairs. A matched pair, in the study’s context, is defined as a ...
user avatar
0 votes
0 answers
21 views

Choosing right value for caliper [duplicate]

I was doing matching using the nearest matching but got stuck with the caliper value. I am not sure which calliper value to choose as many of the tutorials to use 0.1. Suppose, I choose caliper ...
user avatar
3 votes
1 answer
106 views

What is the expected number of correct matches that the medium will make (by chance)?

In a test of ‘psychometry’ the car keys and wrist watches of 5 people are given to a medium. The medium then attempts to match the wrist watch with the car key of each person. What is the expected ...
user avatar
0 votes
1 answer
32 views

Matchit - Distance between 2 Propensity scores for findings specific pairs

helo I'm trying to find "spare" controls in case of drop-out in my primary control. I took my primary control sample (n=29), and ran Optimal match for find secondary match sample (N=350 ...
user avatar
  • 1

1
2 3 4 5
9