Retrospective Comparison of SADI-S Versus RYGB in Chinese with Diabetes and BMI< 35kg/m2: a Propensity Score Adjustment Analysis

This paper investigates different approaches for causal estimation under multiple concurrent medications. Our parameter of interest is the marginal mean counterfactual outcome under different combinations of medications. We explore parametric and non-parametric methods to estimate the generalized propensity score. We then apply three causal estimation approaches (inverse probability of treatment weighting, propensity score adjustment, and targeted maximum likelihood estimation) to estimate the causal parameter of interest. Focusing on the estimation of the expected outcome under the most prevalent regimens, we compare the results obtained using these methods in a simulation study with four potentially concurrent medications. We perform a second simulation study in which some combinations of medications may occur rarely or not occur at all in the dataset. Finally, we apply the methods explored to contrast the probability of patient treatment success for the most prevalent regimens of antimicrobial agents for patients with multidrug-resistant pulmonary tuberculosis.

Download Full-text

Propensity score adjustment using machine learning classification algorithms to control selection bias in online surveys

PLoS ONE ◽

10.1371/journal.pone.0231500 ◽

2020 ◽

Vol 15 (4) ◽

pp. e0231500 ◽

Cited By ~ 3

Author(s):

Ramón Ferri-García ◽

María del Mar Rueda

Keyword(s):

Machine Learning ◽

Propensity Score ◽

Selection Bias ◽

Classification Algorithms ◽

Online Surveys ◽

Machine Learning Classification ◽

Control Selection ◽

Propensity Score Adjustment

Download Full-text

Propensity Score Adjustment Methods

Propensity Score Methods and Applications ◽

10.4135/9781071814253.n3 ◽

2019 ◽

pp. 39-64

Keyword(s):

Propensity Score ◽

Propensity Score Adjustment

Download Full-text

Propensity score adjustment with several follow-ups

Biometrika ◽

10.1093/biomet/asu003 ◽

2014 ◽

Vol 101 (2) ◽

pp. 439-448 ◽

Cited By ~ 5

Author(s):

J. K. Kim ◽

J. Im

Keyword(s):

Propensity Score ◽

Propensity Score Adjustment

Download Full-text

A propensity score adjustment method for regression models with nonignorable missing covariates

Computational Statistics & Data Analysis ◽

10.1016/j.csda.2015.07.017 ◽

2016 ◽

Vol 94 ◽

pp. 98-119 ◽

Cited By ~ 11

Author(s):

Depeng Jiang ◽

Puying Zhao ◽

Niansheng Tang

Keyword(s):

Propensity Score ◽

Regression Models ◽

Missing Covariates ◽

Adjustment Method ◽

Nonignorable Missing ◽

Propensity Score Adjustment

Download Full-text

Inference from Non-Probability Surveys with Statistical Matching and Propensity Score Adjustment Using Modern Prediction Techniques

Mathematics ◽

10.3390/math8060879 ◽

2020 ◽

Vol 8 (6) ◽

pp. 879 ◽

Cited By ~ 1

Author(s):

Luis Castro-Martín ◽

Maria del Mar Rueda ◽

Ramón Ferri-García

Keyword(s):

Propensity Score ◽

Linear Models ◽

Prediction Models ◽

Selection Procedure ◽

Bias Reduction ◽

Online Surveys ◽

K Nearest Neighbors ◽

Weighted Estimates ◽

Statistical Matching ◽

Propensity Score Adjustment

Online surveys are increasingly common in social and health studies, as they provide fast and inexpensive results in comparison to traditional ones. However, these surveys often work with biased samples, as the data collection is often non-probabilistic because of the lack of internet coverage in certain population groups and the self-selection procedure that many online surveys rely on. Some procedures have been proposed to mitigate the bias, such as propensity score adjustment (PSA) and statistical matching. In PSA, propensity to participate in a nonprobability survey is estimated using a probability reference survey, and then used to obtain weighted estimates. In statistical matching, the nonprobability sample is used to train models to predict the values of the target variable, and the predictions of the models for the probability sample can be used to estimate population values. In this study, both methods are compared using three datasets to simulate pseudopopulations from which nonprobability and probability samples are drawn and used to estimate population parameters. In addition, the study compares the use of linear models and Machine Learning prediction algorithms in propensity estimation in PSA and predictive modeling in Statistical Matching. The results show that statistical matching outperforms PSA in terms of bias reduction and Root Mean Square Error (RMSE), and that simpler prediction models, such as linear and k-Nearest Neighbors, provide better outcomes than bagging algorithms.

Download Full-text

A sex-specific propensity-adjusted analysis of colonic adenoma detection rates in a screening cohort

Scientific Reports ◽

10.1038/s41598-021-97163-0 ◽

2021 ◽

Vol 11 (1) ◽

Cited By ~ 1

Author(s):

Sarah Wernly ◽

Bernhard Wernly ◽

Georg Semmler ◽

Sebastian Bachmayer ◽

David Niederseer ◽

...

Keyword(s):

Propensity Score ◽

Colorectal Adenoma ◽

Sensitivity Analyses ◽

Screening Colonoscopy ◽

Advanced Adenoma ◽

Age Group ◽

Detection Rates ◽

Group 3 ◽

Propensity Score Adjustment ◽

Group 1

AbstractThe prevalence of colorectal adenoma and advanced adenoma (AA) differs between sexes. Also, the optimal age for the first screening colonoscopy is under debate. We, therefore, performed a sex-specific and age-adjusted comparison of adenoma, AA and advanced neoplasia (AN) rates in a real-world screening cohort. In total, 2824 asymptomatic participants between 45- and 60-years undergoing screening colonoscopy at a single-centre in Austria were evaluated. 46% were females and mean age was 53 ± 4 years. A propensity score for being female was calculated, and adenoma, AA and AN detection rates evaluated using uni- and multivariable logistic regression. Sensitivity analyses for three age groups (group 1: 45 to 49 years, n = 521, 41% females, mean age 47 ± 1 years; group 2: 50 to 54 years, n = 1164, 47% females, mean age 52 ± 1 years; group 3: 55 to 60 years, n = 1139, 46% females, mean age 57 ± 2 years) were performed. The prevalence of any adenoma was lower in females (17% vs. 30%; OR 0.46, 95% CI 0.38–0.55; p < 0.001) and remained so after propensity score adjustment for baseline characteristics and lifestyle factors (aOR 0.52, 95% CI 0.41–0.66; p < 0.001). The same trend was seen for AA with a significantly lower prevalence in females (3% vs. 7%; OR 0.38, 95% CI 0.26–0.55; p < 0.001) that persisted after propensity score adjustment (aOR 0.54, 95% CI 0.34–0.86; p = 0.01). Also, all age-group sensitivity analyses showed lower adenoma, AA and AN rates in females. Similar numbers needed to screen to detect an adenoma, an AA or AN were found in female age group 3 and male age group 1. Colorectal adenoma, AA and AN were consistently lower in females even after propensity score adjustment and in all age-adjusted sensitivity analyses. Our study may add to the discussion of the optimal age for initial screening colonoscopy which may differ between the sexes.

Download Full-text

An evaluation of whether propensity score adjustment can remove the self-selection bias inherent to web panel surveys addressing sensitive health behaviours

BMC Medical Research Methodology ◽

10.1186/s12874-020-01134-4 ◽

2020 ◽

Vol 20 (1) ◽

Cited By ~ 1

Author(s):

Andrew Copas ◽

Sarah Burkill ◽

Fred Conrad ◽

Mick P. Couper ◽

Bob Erens

Keyword(s):

Propensity Score ◽

Sexual Behaviour ◽

Health Research ◽

Odds Ratio ◽

Market Research ◽

Health Behaviours ◽

Web Survey ◽

Panel Surveys ◽

Propensity Score Adjustment ◽

The Impact

Abstract Background In health research, population estimates are generally obtained from probability-based surveys. In market research surveys are frequently conducted from volunteer web panels. Propensity score adjustment (PSA) is often used at analysis to try to remove bias in the web survey, but empirical evidence of its effectiveness is mixed. We assess the ability of PSA to remove bias in the context of sensitive sexual health research and the potential of web panel surveys to replace or supplement probability surveys. Methods Four web panel surveys asked a subset of questions from the third British National Survey of Sexual Attitudes and Lifestyles (Natsal-3). Five propensity scores were generated for each web survey. The scores were developed from progressively larger sets of variables, beginning with demographic variables only and ending with demographic, sexual identity, lifestyle, attitudinal and sexual behaviour variables together. The surveys were weighted to match Natsal-3 based on propensity score quintiles. The performance of each survey and weighting was assessed by calculating the average ‘absolute’ odds ratio (inverse of the odds ratio if less than 1) across 22 pre-specified sexual behaviour outcomes of interest comparing the weighted web survey with Natsal-3. The average standard error across odds ratios was examined to assess the impact of weighting upon variance. Results Propensity weighting reduced bias relative to Natsal-3 as more variables were added for males, but had little effect for females, and variance increased for some surveys. Surveys with more biased estimates before propensity weighting showed greater reduction in bias from adjustment. Inconsistencies in performance were evident across surveys and outcomes. For most surveys and outcomes any reduction in bias was only partial and for some outcomes the bias increased. Conclusions Even after propensity weighting using a rich range of information, including some sexual behaviour variables, some bias remained and variance increased for some web surveys. Whilst our findings support the use of PSA for web panel surveys, the reduction in bias is likely to be partial and unpredictable, consistent with the findings from market research. Our results do not support the use of volunteer web panels to generate unbiased population health estimates.

Download Full-text