Questions tagged [propensity-scores]

The probability of receiving a treatment given a set of observed covariates.

147 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
8
votes
0answers
547 views

Propensity Score Matching – How do the mechanics lead to a different result than unmatched?

The gist of propensity score matching, as I understand it, is as follows: You want to estimate the average treatment effect (ATE) of a treatment on some outcome. However, if you simply calculate the ...
5
votes
0answers
107 views

Derivation of a doubly robust estimator with clever covariate and inverse probability weighting

With notation: outcome $Y$, (binary) treatment $A$, and covariates $L$. In Hernan and Robins (2020) causal inference textbook: To obtain a doubly robust estimate of the average causal effect, first ...
5
votes
0answers
860 views

Propensity score matching: using alternative methods to create a distance measure

I would like to use a greedy nearest neighbour method to do propensity score matching. Though I've little experience here, it seems that the distance measure used is generally a propensity score ...
5
votes
0answers
522 views

Predicting response propensity in a rolling data collection

I'm working with a survey that uses a rolling data collection format (i.e., there are multiple waves of sampling and initial contacts). I'm trying to develop a model to predict how likely a sample ...
4
votes
0answers
224 views

Propensity matching and analysis of resultant data on a data set with repeated measures

We have extracted retrospective case-level data collected over several years. We are using the administration of rescue antiemetic in the postanesthesia care unit as a proxy for postoperative nausea ...
4
votes
1answer
125 views

Are model diagnostics necessary for linear model run on matched data?

On https://cran.r-project.org/web/packages/cem/vignettes/cem.pdf, it mentions that "Using the output from cem, we can estimate SATT via the att function. The simplest approach requires a weighted ...
4
votes
0answers
178 views

Analyzing the effects of different scholarships among university students

We have a data set that has data on university students, including their socio-demographic characteristics (sex, first language, ethnicity, residency etc.), GPA and CGPA in each semester (note that ...
4
votes
1answer
816 views

Inverse probability weighting (IPW): standard errors after weighting observations

When using propensity scores for inverse probability weighting (IPW) the standard errors for the parameters in the regression model may be affected. I have seen several examples of people using ...
4
votes
0answers
5k views

Propensity Score Matching in R with Multiple Treatments

I commonly estimate Average effect of Treatment on the Treated (ATT) via Propensity Score Matching for a particular business use case. I'm currently using R, where ...
4
votes
0answers
2k views

Propensity score and Cox regression

I have a retrospective dataset of patients treated with a certain drug (treatment, $n=46$) or with placebo (control $n=96$). The stored variables are age, sex, stage of disease. I want to assess the ...
3
votes
0answers
51 views

Extending external validation diagnostics to experiments with continuous treatment

Does the external validation diagnostic methods discussed in Stuart et al. (2011) (i.e., inverse propensity score weighted regressions) also apply to the experimental setting in which the treatment is ...
3
votes
0answers
34 views

Adjusting for non-response bias in a survey

Say I have a target population of 10,000 for a survey, and only 2,000 respond, because they likely feel strongly about the survey topic (either happy or angry). I have clear, abundant non-response ...
3
votes
0answers
31 views

Transfer Learning in domains other than Image processing and NLP

Can Transfer Learning be applied in domains other than Image processing or NLP? I am trying to apply it on clickstream data (for propensity modeling). Any reference would be greatly appreciated.
3
votes
0answers
578 views

Paired tests for one-to-many matched observations

I have a propensity score matched data after 1-to-2 matching. Each treatment case is matched to one or two control cases. May I use paired tests to compare the outcomes? The discussion https://www....
3
votes
0answers
475 views

Propensity score matching for "large" datasets - smarter solution than nearest neighbour?

The following question has some programming / software package as well as some numerical aspects, but I would consider it a statistical question at heart - I hope you agree. I am trying to do 1:1 ...
3
votes
0answers
687 views

Heterogeneous Treatment Effects - How to test differences in the ATE?

I want to conduct a simple propensity score estimation where the treatment $D_i$ is a binary variable ($D_i=1$ individual $i$ participates in the labor market program, zero otherwise). I estimate the ...
2
votes
0answers
17 views

Should inverse probability weighting be used in two-way fixed-effects panel regression?

Let's assume a (balanced) panel data set with two measurement points $t_0$ and $t_1$, where $t_0$ may be considered as the baseline. Some of the ID's are treated at $t_1$, i.e. $D=1$, the assignment ...
2
votes
0answers
23 views

How do I properly run a propensity correction for a fixed-effects model in Stata?

I have a fixed effects regression with a highly unbalanced panel. I am recording the outcome for each day a person participates over the course of a fifteen year time frame. Individuals can enter or ...
2
votes
0answers
18 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 ...
2
votes
0answers
60 views

What can I do to get better overlap in propensity score distributions?

I would like to verify the positivity assumption to identify causal effects from observational data. My exposure prevalence is about 6%. When I included several potential confounders in my exposure ...
2
votes
0answers
32 views

Difference-in-differences model with a matched control group

I need to run a difference-in-differences (DiD) model, but I'm not sure how to construct a formula for this. The problem is that the timing of events affecting the treatment group is not uniform, like ...
2
votes
0answers
28 views

Is it necessary to match groups before running random forest?

I' m doing a survival analysis using machine learning with random forest method. There are two groups for comparison. But two groups are so unmatched in baseline characteristics. I performed ...
2
votes
0answers
34 views

Preprocessing on propensity score matched data

I did preprocessing, then propensity score matching using logistic regression, and then fit a glm to the response variable of interest. However, the odds ratio obtained was 0.0008 (while it should be ...
2
votes
0answers
160 views

Standard errors propensity score matching

I am currently working on a causal inference project via several panel regression specifications, and one of the methods I'm using to obtain more robust results is propensity score matching (PSM). For ...
2
votes
1answer
106 views

Difference in difference with similar units over 2 periods of time

I have ESG (Environmental, Social & Governance) scores for 20 companies over a period of 10 years. In the fifth year a policy was introduced and I want to estimate the impact/effect of the policy ...
2
votes
0answers
77 views

Propensity score matching - time variant treatment

I have a question about propensity score matching for a panel data file. The aim of my study is to understand the impact of having the first child on the wage of women. My data goes from 2001 to 2018. ...
2
votes
1answer
79 views

Matching biometrics with NHANES

Good morning everyone, I'm trying to figure out how to do some matching with NHANES datasets. Basically, I have a separate population of participants in a weight loss program, for which we do not ...
2
votes
0answers
36 views

Propensity score variable selection

In articles about propensity score it says you should select variables associated with treatment and outcome as covariates to calculate the propensity score. What I haven't found explained anywhere ...
2
votes
0answers
463 views

Kernel Matching

I wish to estimate a treatment effect using Kernel Matching, but I'm confused about the process. From a high level, Is A or B correct? Or are both considered Kernel matching? A (1) Estimate ...
2
votes
1answer
442 views

Variance of ATE (Average Treatment Effect) from log-linked gamma model

I have matched my sample using propensity score matching such that each individual has an estimated propensity score of being assigned to a treatment group. Let $T_i$={0,1} be the actual treatment ...
2
votes
0answers
77 views

Difference-in-Difference with multiple regression vs. matching combined with Difference in Difference

I want to use a Difference-in-Difference approach. In order to make sure treatment and control group are similar, I want to use a propensity score matching before the DiD approach. What I do is to ...
2
votes
0answers
361 views

Cox Regression in Propensity Score Matched cohort after multiple imputation

I have a follow-up question on the question of this thread: Manipulating data for propensity score matching following multiple imputation with mice package In aforementioned topic we can see the ...
2
votes
0answers
957 views

Generating frequency table and survival curve after multiple imputation

I'm using the MICE package to generate 10 imputed datasets. After that, I know I should perform analysis on each dataset (propensity score matching, Chi-square, and Cox-regression in my case) and ...
2
votes
0answers
670 views

Propensity Score Matching - Multiple observations in control group

I am quite new to propensity score matching and have the following issue in my data. I have two groups (Treatment vs control) this could be for eg. two types of loyalty program at a retail store. In ...
2
votes
0answers
119 views

Matching variables in matching diff-in-diff

In a matching diff-in-diff, which pre-treatment variables can be legitimately used in the matching procedure? I'm reading this paper, which uses propensity score matching to estimate the effect of ...
2
votes
0answers
49 views

How to improve structural bias correction using propensity scores

Given a control group and a treatment group, which are not equivalent (different distributions on a number of variables), I want to estimate the probability of an event given that the observation was ...
2
votes
0answers
30 views

What are the most adequate parameters for assessing bias in propensity scoring systems?

I am analyzing a very large dataset featuring scores in a sport. The only information I have is the scores of many athletes in various locations, which are organized in the following way: ...
2
votes
0answers
34 views

propensity score weighting in estimating population mean

I have a survey data like, it has three covariates, age, gender and marital status: ...
2
votes
0answers
966 views

Calculating average treatment effect for propensity score matching with MatchIt and Zelig packages in R

Using the lalonde dataset provided with the MatchIt package, I'm running the following R commands (from the subclassification ...
2
votes
0answers
956 views

Logistic regression methods after propensity score matching

I have multiple questions regarding the best way of estimating the odds ratios after I have calculated a propensity score. I am using a complex survey sample with single-stage design (sampling unit = ...
2
votes
0answers
2k views

Software that matches 6 groups by propensity score?

I have found MatchIt in R that does propensity score matching among 2 groups. But I have six groups that I'd like matched by age, gender, race, and a few other variables. They don't have to be ...
2
votes
0answers
322 views

Propensity score matching: gain or loss in degree of freedom?

I saw some argument in a thread that propensity score matching (PSM) has statistical advantage over OLS in terms of degree of freedom. https://stats.stackexchange.com/a/8610/78057 However, my ...
2
votes
0answers
922 views

propensity score matching and survival analysis

I am using the Matching R package to compute Average Treatment Effect within Propensity Score Matching (PSM). I have two groups: treatment and control. In ...
2
votes
0answers
2k views

Propensity score nearest neighbor matching with replacement and caliper

I am using the package MatchIt in R to perform propensity score matching. I have chosen to use nearest neighbor matching with a caliper of 0.2 and since in my case i have more cases than controls i ...
2
votes
0answers
128 views

Multilevel propensity score

I'm trying to analyze many treatments on outcome after propensity score 1:1 matching. My problem: I have 6 differents drugs and each patient can take or not each of these. If I build my propensity ...
2
votes
0answers
74 views

Statistical thought experiment (possibly Bayesian) about survey sampling and propensity scores

For some practical application I recently came about the following thought experiment. Can anybody help? Suppose we administer a survey A to measure a variable $Y$. The response probabilities may ...
1
vote
0answers
21 views

Using same control variables as in propensity score matching

I matched my treatment and control group in STATA, using propensity score matching. I also made sure that each treatment/control pair share the same industry and year ( it's a panel data). If I'm now ...
1
vote
0answers
27 views

What is the prediction model to predict the probability?

In a paper, Dasgupta, 2019 used Difference-in-Difference approach to see whether anticollusion laws implemented by different countries (staggered implementation) affect firms financial flexibility. ...
1
vote
0answers
23 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 $A$ ...
1
vote
0answers
43 views

How would one calculate the p-value from a doubly robust model

How would one calculate the p-value from a doubly robust model I could used the boot.pval r package and set the theta_null (The value of the parameter under the null hypothesis) 0, using student t-...