↓ Skip to main content

Double-adjustment in propensity score matching analysis: choosing a threshold for considering residual imbalance

Overview of attention for article published in BMC Medical Research Methodology, April 2017

About this Attention Score

  • In the top 5% of all research outputs scored by Altmetric
  • High Attention Score compared to outputs of the same age (93rd percentile)
  • High Attention Score compared to outputs of the same age and source (87th percentile)

Mentioned by

news
1 news outlet
policy
3 policy sources
twitter
10 X users
patent
1 patent
q&a
2 Q&A threads

Readers on

mendeley
216 Mendeley
You are seeing a free-to-access but limited selection of the activity Altmetric has collected about this research output. Click here to find out more.
Article details
Title
Double-adjustment in propensity score matching analysis: choosing a threshold for considering residual imbalance
Published in
BMC Medical Research Methodology, April 2017
DOI 10.1186/s12874-017-0338-0
Pubmed ID
Authors
Abstract

Double-adjustment can be used to remove confounding if imbalance exists after propensity score (PS) matching. However, it is not always possible to include all covariates in adjustment. We aimed to find the optimal imbalance threshold for entering covariates into regression. We conducted a series of Monte Carlo simulations on virtual populations of 5,000 subjects. We performed PS 1:1 nearest-neighbor matching on each sample. We calculated standardized mean differences across groups to detect any remaining imbalance in the matched samples. We examined 25 thresholds (from 0.01 to 0.25, stepwise 0.01) for considering residual imbalance. The treatment effect was estimated using logistic regression that contained only those covariates considered to be unbalanced by these thresholds. We showed that regression adjustment could dramatically remove residual confounding bias when it included all of the covariates with a standardized difference greater than 0.10. The additional benefit was negligible when we also adjusted for covariates with less imbalance. We found that the mean squared error of the estimates was minimized under the same conditions. If covariate balance is not achieved, we recommend reiterating PS modeling until standardized differences below 0.10 are achieved on most covariates. In case of remaining imbalance, a double adjustment might be worth considering.

Login to access the Attention Digest and the Sentiment Analysis related to this output.

Timeline Attention over time Attention Score history
Login to access the full charts related to this output.
Activity
Login to access the full charts related to this output.
X Demographics

X Demographics

The data shown below were collected from the profiles of 10 X users who shared this research output. Click here to find out more about how the information was compiled.
Mendeley demographics

Mendeley demographics

The data shown below were compiled from readership statistics for 216 Mendeley readers of this research output. Click here to see the associated Mendeley record.
Login to view Mendeley reader trends over time.

Geographical breakdown

Geographical breakdown
Country Count As %
Chile 1 <1%
Unknown 215 100%

Demographic breakdown

Readers by professional status
Readers by professional status Count As %
Student > Ph. D. Student 37 17%
Researcher 37 17%
Student > Master 18 8%
Other 14 6%
Student > Doctoral Student 11 5%
Other 37 17%
Unknown 62 29%
Readers by discipline
Readers by discipline Count As %
Medicine and Dentistry 61 28%
Economics, Econometrics and Finance 13 6%
Social Sciences 12 6%
Agricultural and Biological Sciences 9 4%
Mathematics 7 3%
Other 37 17%
Unknown 77 36%
Attention Score in Context

Attention Score in Context

This research output has an Altmetric Attention Score of 32. This is our high-level measure of the quality and quantity of online attention that it has received. This Attention Score, as well as the ranking and number of research outputs shown below, was calculated when the research output was last mentioned on 24 April 2025.
All research outputs
#1,477,530
of 31,660,612 outputs
Outputs from BMC Medical Research Methodology
#139
of 2,671 outputs
Outputs of similar age
#22,441
of 343,294 outputs
Outputs of similar age from BMC Medical Research Methodology
#5
of 39 outputs
Altmetric has tracked 31,660,612 research outputs across all sources so far. Compared to these this one has done particularly well and is in the 95th percentile: it's in the top 5% of all research outputs ever tracked by Altmetric.
So far Altmetric has tracked 2,671 research outputs from this source. They typically receive more attention than average, with a mean Attention Score of 9.7. This one has done particularly well, scoring higher than 94% of its peers.
Older research outputs will score higher simply because they've had more time to accumulate mentions. To account for age we can compare this Altmetric Attention Score to the 343,294 tracked outputs that were published within six weeks on either side of this one in any source. This one has done particularly well, scoring higher than 93% of its contemporaries.
We're also able to compare this research output to 39 others from the same source and published within six weeks on either side of this one. This one has done well, scoring higher than 87% of its contemporaries.