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

learn more… | top users | synonyms

0
votes
0answers
9 views

Propensity score matching - Force full match on specific categorical variable

I'm trying to perform propensity score matching using R MatchIt pacakage, and I have a question: I have tried the nearest neigbor method, and I understand that it tries to find the nearest match, in ...
1
vote
1answer
13 views

Categorical variable as control variable in MatchIt

I'm kind of new to R and trying to run propensity score matching using the MatchIt module. Some of my control variables are continous but some of them are categorical. For example, I have a "currency" ...
0
votes
0answers
9 views

Retrospective randomised study design

I would like to measure the impact of having/not having intervention (counseling) on lifetime cost of care. Patients all enter the ED, and some may be referred for counseling. In some cases, patients ...
0
votes
0answers
16 views

Propensity score - how to deal with panel data?

I am researching mergers and acquisitions. The overlying question is the following: Do companies acquiring targets in a merger wave (i.e. a period of time where abnormally many acqusitions take place) ...
0
votes
0answers
15 views

Test for Conditional Normality?

On page 357 of this article, it states: We assume that the treatment (or its transformation) has a normal distribution conditional on the covariates. How would I go about determining if a ...
0
votes
0answers
14 views

Treament By Covariate Interactions with Propensity Score Weighting

I am trying to estimate the causal effect of a treatment on an outcome using propensity score weighting. I estimated the propensity scores and verified covariate balance with a number of covariates, ...
0
votes
0answers
25 views

Propensity score matching in a longitudinal setting

I am using Stata 13 to investigate a local programm aimed at reducing obesity amoung teenagers and adolescents in a school. I have a balanced panel over twelve years and a couple of covariates (like ...
0
votes
0answers
8 views

A good way to estimate propensity score for IPTW (without linear dependence)?

Are there consistent estimates for 1/e(X), where e(X) is the propensity score, when no linearity assumptions on the dependence of e(X) on X are made?
0
votes
0answers
9 views

How to estimate discontinuous propensity score?

Are there any methods to estimate propensity score if its dependence on covariates is discontinuous? For instance, if there is a discontinuity on some hyperplane which is not known?
0
votes
0answers
29 views

DiD Matching with Time-Varying Treatment and Repeated Cross Sectional Data

I am conducting research on the effect of modularizationg (dividing courses in modules) on early school leaving (dummy variable where 1 = left school prematurely). I would like to match my treatment ...
1
vote
1answer
24 views

Is a comparison of patients between 2 clinics using propensity score matching a matched case control study?

I'm helping my boss design a study that will look at the effects of a clinic level intervention on a patient level outcome. I would like to look at the effect of our intervention on one clinic ...
0
votes
0answers
15 views

hlsens and match/genmatch giving very different results

I'm doing some propensity modelling in R using these functions: ...
1
vote
0answers
30 views

Optimal matching with caliper in MatchIt package in R

I am using the package MatchIt in R to perform propensity score matching. The command is ...
1
vote
2answers
49 views

Maximal logit distance for propensity score matching

I use propensity score matching (PSM) with logit regression distance. What maximal propensity score (ps) distance in each pair of the treatment and control individuals can be allowed? What maximal ...
0
votes
0answers
8 views

Models and features used to estimate the propensity score in financial services (Banking)?

I'm trying to figure out how to compute the probability of a bank customer converting after sending him an offer. After a lot of research i found that propensity scores is what i am looking for. This ...
1
vote
0answers
16 views

Propensity score matching linearity assumption

One of the advantage that i have herd talked about propensity score matching, vs. a regression, is that propensity-score matching doesn't rely on linearity assumptions. This seems incorrect on the ...
6
votes
1answer
132 views

The difference between average and marginal treatment effect

I have been reading some papers, and I am unclear about the specific definitions of Average Treatment Effect (ATE), and Marginal Treatment Effect (MTE). Are they the same? According to Austin... ...
0
votes
0answers
16 views

propensity match advice

I need some advice on how to tackle this problem. I have two groups (treatment n=30 and no-treatment 400). I want to match the treatment group patients to the other group based on comorbidities and ...
2
votes
1answer
26 views

Including already balanced confounders in propensity score model

I have a dataset that I want to run propensity score analysis on. Using package TWANG in R, I plan to compute the propensity score and use it as IPTW. The variables that I put into the model are those ...
0
votes
0answers
10 views

Obtaining matched data from original data using match.data command in MATCHIT package

I am using matchit package. For getting the matched data set, match.data command is used.But it is not excluding the unmatched and discarded cases. Please can anybody guide me regarding this.
0
votes
0answers
22 views

Interpretation of ATE for IPTW propensity score analysis

I understand how we interpret the average treatment effect (ATE) when we use propensity score matching. We match on propensity score, and then subtract away the groups to get the average treatment ...
0
votes
0answers
36 views

Pre and Post matching glm syntax in R

I am trying to compare the effect of breastfeeding on child outcomes using PSM in R. Breastfeeding is my treatment whereby mothers who breastfed are coded as 1(treatment) and those who don't as ...
1
vote
0answers
48 views

Optimal Bandwidth Selection for Propensity Score Matching in Stata

currently I am performing a DID ATT estimation with propensity score matching and I want to present estimates for NN-matching with 1 and 2 neighbors as well as kernel(gaussian)-matching with an ...
2
votes
2answers
49 views

Model Selection in Propensity Score Matching

I am trying to fit a logistic model to create propensity scores. Looking though the literature, there appears to be some disagreement on which covariates to include when designing such a model. Some ...
1
vote
0answers
44 views

Propensity Score Matching with few treated observations

Consider the situation in which one has 3000 untreated observations and 30 treated observations, that is, a ratio of 1/100 between treated and untread. In this situation, I believe the logistical or ...
0
votes
1answer
29 views

Validating a predictive model after using propensity score weights

I have observational data with a "treatment" and I want to use propensity scores to weight the samples. A predictive model will be built (including the case weights). I will want to include the ...
4
votes
0answers
153 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 ...
1
vote
0answers
27 views

Methods of Treatment Effect Heterogeneity Estimation (Observation Data)

Given observational data, where a "treatment" is chosen by the unit of observation or not, are there any standard methods of ascertaining not just if the treatment has effect overall (ATT), but ...
0
votes
0answers
72 views

matching one-to-many vs one-to-one?

When doing propensity score matching, how do you decide whether to do one-to-many or one-to-one matching? This paper says: "Increasing the matching ratio is thought to improve precision but may come ...
1
vote
1answer
66 views

Using Matching to Conduct a Sub Group Analysis

[Moved from stack overflow) While I have done a good amount of reading regarding the usage of PSM, I am still struggling a bit to see if it can be used in my application. I am trying to analyze the ...
0
votes
1answer
36 views

Standards for reporting propensity score matching

When publishing articles, there are international recommendations for reporting modeling such as the TRIPOD Statement (Transparent reporting of a multivariable prediction model for individual ...
1
vote
0answers
71 views

Conditional logistic regression or GEE in PS matched study

My situation: In a cohort study, I'm trying to find the correlation between outcome & Tx (Arm A vs Arm B). However, baseline covariates are unbalance between different treatment groups. Hence, ...
0
votes
0answers
66 views

Instrumental variable analysis after (propensity) matching

I am trying to replicate the methods used in this paper by Paul Rosenbaum and colleagues (Near-Far matching). I have been studying the methods in the referenced papers by Michael Baoicchi. My work ...
0
votes
1answer
51 views

Propensity score stratification: standard errors and p-values

While there are many tutorials on how to perform propensity score stratification, I was unable to find any example that showed the calculation of standard errors and p-values for the final estimate. ...
1
vote
1answer
39 views

Challenging Propensity Score/Causal Inference Problem

I am reaching out to the Cross-Validated statistical community seeking suggestions on a challenging problem on which I'm working. I've been asked to look into a problem related to electronic ...
1
vote
0answers
46 views

Propensity Score Matching with pooling of panel data

I want to conduct a Propensity Score Matching with a Diff in Diff strategy (or please suggest if there are any other approach/s I should be following) to assess the causal impact of ventures changing ...
0
votes
0answers
15 views

Is there better method to model this scenario of finding most suitable people for campaign?

I have a scenario like this: There is a population which is divided into members/non-members for one particular credit card. Based on studying the characteristics of members, we need to identify the ...
0
votes
0answers
36 views

Control for regression to the mean effects when comparing propensity score matched observations?

I'm working on a project where I'm comparing the % change in total annual health care expenditures among patients who did or did not participate in a cost reduction intervention program. We're ...
1
vote
0answers
97 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 ...
0
votes
0answers
55 views

matching methods when treated group is much larger than untreated group

I have a treatment group with Nt = 2000 and an untreated group with Nu=500. I want to perform propensity score matching/weighting (PSM). It seems like the common matching methods have serious flaws ...
1
vote
0answers
46 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 ...
0
votes
0answers
56 views

Propensity score methods versus GLM for cost comparisons between treatment groups

I'm working with a client that wants cost differences between two treatment groups. They have little background knowledge but have seen in the literature folks doing GLM gamma/log-link, etc. and are ...
0
votes
0answers
15 views

Quasi-experiment with naturally assembled collectives (classrooms): Propensity score matching or not?

I am planning on running a quasi-experiment (pre-test post-test non-equivalent groups design) that involves two treatment groups that are subjected to different treatments (X+ & X-) and one ...
1
vote
2answers
78 views

Propensity Score Matching

What is the right approach when there is a variable that does not affect participation but effects the outcome measure? I have data set of the health outcome of a treatment and control group. I have ...
0
votes
0answers
33 views

Propensity Score Matching and significance of estimators in logit regression

If I run a logistic regression to calculate a propensity score (i.e. the dependent variable is 0= do not participate in the treatment; 1= do participate) and therefore I want to see the probability a ...
1
vote
1answer
28 views

What type of matching should I use?

I am conducting a retrospective cohort analysis looking at major psych diagnosis (exposure) on outcomes following traumatic injury using a large registry. n exposed = 36,000 ; n unexposed = 3.5 ...
1
vote
0answers
38 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. http://stats.stackexchange.com/a/8610/78057 However, my ...
2
votes
0answers
116 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 ...
0
votes
1answer
96 views

Inverse probability weighting in logistic models - large weights irrelevant when using additional covariates?

I am using propensity scores for IPW in a logistic GLM in R. Two of the propensities are quite small and thus the resulting weights are quite large - much larger than all the others. I expected these ...
4
votes
1answer
165 views

Post propensity score matching analysis

I want to look into the causal effects of an education program on a binary employment outcome (positive vs negative). I have two groups of students- one that took the education program (the treatment ...