scholarly journals Piecewise propensity score analysis: A new method for conducting propensity score matching with polytomous ordinal independent variables.

2018 ◽  
Vol 6 (1) ◽  
pp. 14-20
Author(s):  
Robert Bodily ◽  
Ross Larsen ◽  
Russell T. Warne
Keyword(s):  
Propensity Score ◽  
Propensity Score Matching ◽  
Propensity Score Analysis ◽  
New Method ◽  
Independent Variables ◽  
Score Analysis

scholarly journals A Case Study About Why It Can Be Difficult To Test Whether Propensity Score Analysis Works in Field Experiments

2013 ◽  
Vol 3 (2) ◽  
pp. 1 ◽  
Author(s):  
William R. Shadish ◽  
Peter M. Steiner ◽  
Thomas D. Cook
Keyword(s):  
Experimental Data ◽  
Propensity Score ◽  
Propensity Score Matching ◽  
Field Experiments ◽  
Propensity Score Analysis ◽  
Randomized Experiment ◽  
Score Analysis ◽  
Quasi Experimental ◽  
Do So

Peikes, Moreno and Orzol (2008) sensibly caution researchers that propensity score analysis may not lead to valid causal inference in field applications. But at the same time, they made the far stronger claim to have performed an ideal test of whether propensity score matching in quasi-experimental data is capable of approximating the results of a randomized experiment in their dataset, and that this ideal test showed that such matching could not do so. In this article we show that their study does not support that conclusion because it failed to meet a number of basic criteria for an ideal test. By implication, many other purported tests of the effectiveness of propensity score analysis probably also fail to meet these criteria, and are therefore questionable contributions to the literature on the effects of propensity score analysis. DOI:10.2458/azu_jmmss_v3i2_shadish

scholarly journals Silicone oil versus gas tamponade for primary rhegmatogenous retinal detachment treated successfully with a propensity score analysis: Japan Retinal Detachment Registry

2021 ◽  
pp. bjophthalmol-2021-319876
Author(s):  
Ryoh Funatsu ◽  
Hiroto Terasaki ◽  
Chihaya Koriyama ◽  
Toshifumi Yamashita ◽  
Hideki Shiihara ◽  
...  
Keyword(s):  
Retinal Detachment ◽  
Propensity Score ◽  
Propensity Score Matching ◽  
Rhegmatogenous Retinal Detachment ◽  
Silicone Oil ◽  
Propensity Score Analysis ◽  
Gas Tamponade ◽  
Score Analysis ◽  
Primary Success ◽  
Silicone Oil Tamponade

Background/aimsTo compare the effects of silicone oil tamponade (SOT) to that of gas tamponade (GT) on the best-corrected visual acuity (BCVA) after successful vitrectomy for retinal detachment (RD).MethodsA retrospective, multicentre, nationwide study with RD who were registered in the Japan-RD Registry. All cases with RD treated with successful vitrectomy between February 2016 and March 2017 were studied. A propensity score matching was performed using the preoperative findings as covariates to adjust the relevant confounders. The primary outcome was the estimated mean difference of the postoperative BCVA in 6 months between eyes treated with SOT to those treated with GT.ResultsOf the 3446 cases registered, 2097 cases met the entry criteria. There were 2042 eyes that had GT and 55 eyes that had SOT. Primary success was defined as a reattached retina with no tamponade at 6 months. After propensity score matching, each group contained 40 cases. The preoperative BCVA was 0.966±0.738 logMAR units in the GT group and 1.270±0.945 logMAR units in the SOT group (p=0.177). Six months postoperatively, the BCVA in the GT group was significantly better at 0.309 logMAR units in the GT group than the 0.671 logMAR units in the SOT group (p=0.002).ConclusionsEven after successful surgery for RD, eyes that experienced SOT had poorer BCVA than eyes treated with GOT. SOT should be considered cautiously.PrecisPropensity score analysis of eyes with rhegmatogenous RD showed that postoperative vision was worse in eyes treated once with silicone oil than with gas even after completely successful surgery.

scholarly journals Propensity score matching for multilevel spatial data: accounting for geographic confounding in health disparity studies

2021 ◽  
Vol 20 (1) ◽  
Author(s):  
Melanie L. Davis ◽  
Brian Neelon ◽  
Paul J. Nietert ◽  
Lane F. Burgette ◽  
Kelly J. Hunt ◽  
...  
Keyword(s):  
Propensity Score ◽  
Spatial Heterogeneity ◽  
Racial Disparities ◽  
Propensity Score Matching ◽  
Random Effects ◽  
Propensity Score Analysis ◽  
Specialty Care ◽  
Spatial Random Effects ◽  
Patient Level ◽  
Score Analysis

Abstract Background Diabetes is a public health burden that disproportionately affects military veterans and racial minorities. Studies of racial disparities are inherently observational, and thus may require the use of methods such as Propensity Score Analysis (PSA). While traditional PSA accounts for patient-level factors, this may not be sufficient when patients are clustered at the geographic level and thus important confounders, whether observed or unobserved, vary by geographic location. Methods We employ a spatial propensity score matching method to account for “geographic confounding”, which occurs when the confounding factors, whether observed or unobserved, vary by geographic region. We augment the propensity score and outcome models with spatial random effects, which are assigned scaled Besag-York-Mollié priors to address spatial clustering and improve inferences by borrowing information across neighboring geographic regions. We apply this approach to a study exploring racial disparities in diabetes specialty care between non-Hispanic black and non-Hispanic white veterans. We construct multiple global estimates of the risk difference in diabetes care: a crude unadjusted estimate, an estimate based solely on patient-level matching, and an estimate that incorporates both patient and spatial information. Results In simulation we show that in the presence of an unmeasured geographic confounder, ignoring spatial heterogeneity results in increased relative bias and mean squared error, whereas incorporating spatial random effects improves inferences. In our study of racial disparities in diabetes specialty care, the crude unadjusted estimate suggests that specialty care is more prevalent among non-Hispanic blacks, while patient-level matching indicates that it is less prevalent. Hierarchical spatial matching supports the latter conclusion, with a further increase in the magnitude of the disparity. Conclusions These results highlight the importance of accounting for spatial heterogeneity in propensity score analysis, and suggest the need for clinical care and management strategies that are culturally sensitive and racially inclusive.

scholarly journals A Case Study About Why It Can Be Difficult To Test Whether Propensity Score Analysis Works in Field Experiments

2013 ◽  
Vol 3 (2) ◽  
pp. 1 ◽  
Author(s):  
William R. Shadish ◽  
Peter M. Steiner ◽  
Thomas D. Cook
Keyword(s):  
Experimental Data ◽  
Propensity Score ◽  
Propensity Score Matching ◽  
Field Experiments ◽  
Propensity Score Analysis ◽  
Randomized Experiment ◽  
Score Analysis ◽  
Quasi Experimental ◽  
Do So

Peikes, Moreno and Orzol (2008) sensibly caution researchers that propensity score analysis may not lead to valid causal inference in field applications. But at the same time, they made the far stronger claim to have performed an ideal test of whether propensity score matching in quasi-experimental data is capable of approximating the results of a randomized experiment in their dataset, and that this ideal test showed that such matching could not do so. In this article we show that their study does not support that conclusion because it failed to meet a number of basic criteria for an ideal test. By implication, many other purported tests of the effectiveness of propensity score analysis probably also fail to meet these criteria, and are therefore questionable contributions to the literature on the effects of propensity score analysis. DOI:10.2458/azu_jmmss_v3i2_shadish

scholarly journals A Propensity Score Analysis Shows that Empirical Treatment with Linezolid Does Not Increase the Thirty-Day Mortality Rate in Patients with Gram-Negative Bacteremia

2014 ◽  
Vol 58 (12) ◽  
pp. 7025-7031 ◽  
Author(s):  
Hugo-Guillermo Ternavasio-de la Vega ◽  
Ana-María Mateos-Díaz ◽  
Jose-Antonio Martinez ◽  
Manel Almela ◽  
Nazaret Cobos-Trigueros ◽  
...  
Keyword(s):  
Logistic Regression ◽  
Mortality Rate ◽  
Propensity Score ◽  
Propensity Score Matching ◽  
Propensity Score Analysis ◽  
Mortality Rates ◽  
Empirical Treatment ◽  
Gram Negative ◽  
Score Analysis ◽  
Gram Negative Bacteremia

ABSTRACTThe role of linezolid in empirical therapy of suspected bacteremia remains unclear. The aim of this study was to evaluate the influence of empirical use of linezolid or glycopeptides in addition to other antibiotics on the 30-day mortality rates in patients with Gram-negative bacteremia. For this purpose, 1,126 patients with Gram-negative bacteremia in the Hospital Clinic of Barcelona from 2000 to 2012 were included in this study. In order to compare the mortality rates between patients who received linezolid or glycopeptides, the propensity scores on baseline variables were used to balance the treatment groups, and both propensity score matching and propensity-adjusted logistic regression were used to compare the 30-day mortality rates between the groups. The overall 30-day mortality rate was 16.0% during the study period. Sixty-eight patients received empirical treatment with linezolid, and 1,058 received glycopeptides. The propensity score matching included 64 patients in each treatment group. After matching, the mortality rates were 14.1% (9/64) in patients who received glycopeptides and 21.9% (14/64) in those who received linezolid, and a nonsignificant association between empirical linezolid treatment and mortality rate (odds ratio [OR], 1.63; 95% confidence interval [CI], 0.69 to 3.82;P= 0.275, McNemar's test) was found. This association remained nonsignificant when variables that remained unbalanced after matching were included in a conditional logistic regression model. Further, the stratified propensity score analysis did not show any significant relationship between empirical linezolid treatment and the mortality rate after adjustment by propensity score quintiles or other variables potentially associated with mortality. In conclusion, the propensity score analysis showed that empirical treatment with linezolid compared with that with glycopeptides was not associated with 30-day mortality rates in patients with Gram-negative bacteremia.

scholarly journals Assessing student success in a Peer Assisted Learning program using propensity score matching

2021 ◽  
Author(s):  
Corey Shanbrom ◽  
Michelle Norris ◽  
Caitlin Esgana ◽  
Matthew Krauel ◽  
Vincent Pigno ◽  
...  
Keyword(s):  
Propensity Score ◽  
Student Success ◽  
Propensity Score Matching ◽  
Propensity Score Analysis ◽  
State University ◽  
Learning Program ◽  
Peer Assisted Learning ◽  
Score Analysis ◽  
Group Members ◽  
Matching Techniques

The Peer Assisted Learning program at Sacramento State University (PAL) was established in 2012 with one section supporting introductory chemistry. It now serves 17 gatekeeper courses in Biology, Chemistry, Mathematics, Physics, and Statistics, enrolling approximately 1,400 students annually. Adapting the Peer-Led Team Learning model, PAL Facilitators do not teach, tutor, or even confirm answers; they do ask scaffolding questions, provide encouragement, and ensure that all group members participate in problem-solving. Here we assess the efficacy of the program in terms of student success in the parent course. As PAL is an opt-in program, we employ propensity score matching techniques to account for confounding factors. Our analysis of 11 classes shows that PAL provides an average course GPA bump ranging from .23 to .71 grade points (mean .42). Compared to the non-PAL baseline course GPA, this amounts to an increase of 9% to 51% (mean 23%). We consider data from over 25,000 students, and our propensity score analysis uses over 10,000 students (4,519 PAL, 5,814 non-PAL) for whom appropriate matches could be found.

Role of adjuvant radiation therapy in ampullary carcinoma: Propensity-score matched SEER analysis.

2014 ◽  
Vol 32 (3_suppl) ◽  
pp. 282-282
Author(s):  
John Byun ◽  
Surbhi Grover ◽  
Lauren Michelle Hertan ◽  
Smith Apisarnthanarax
Keyword(s):  
Radiation Therapy ◽  
Propensity Score ◽  
Propensity Score Matching ◽  
Survival Benefit ◽  
Propensity Score Analysis ◽  
Ampullary Cancer ◽  
Survival Outcomes ◽  
Score Analysis ◽  
The Impact

282 Background: Ampullary cancer outcomes have been reported to compare favorably with pancreatic and biliary malignancies. Consensus guidelines on the optimal adjuvant management after resection in these patients remain unclear. Propensity score matching was used to compare the outcomes of patients with ampullary cancer receiving or not receiving radiation therapy (RT) from the Surveillance, Epidemiology, and End Results (SEER) database. Methods: Patients with a diagnosis of ampulla of vater carcinoma who underwent curative intent surgery were identified within 17 SEER registries from 1998-2008. Patients with M1 disease or follow up less than 5 months were excluded. Data on patient characteristics such as age at diagnosis, race, tumor characteristics including TNM staging and histologic subtype, and survival outcomes were extracted and compared between patients who received adjuvant RT and those who did not. Propensity score matching was used to minimize treatment selection bias within the specified characteristics and estimate the impact of RT on median survival times (MST). Matching algorithms used validated Mahalanobis nearest neighbor methods based on conditional probabilities of receiving RT. Results: Of the 1782 patients identified, 490 (25%) were treated with adjuvant RT: 318 (65%) T3/4 and 333 (68%) N1. Cox regression with propensity score analysis for patients with RT showed an overall decrease in survival time by 3.67 months (p<0.05). Propensity score analysis showed slightly worse survival in patients who received RT compared to those who did not (MST 2.7 vs. 3.0 years, respectively, p=0.04). There was a trend towards a survival benefit with RT in a subgroup of patients over the age of 66 years with T2N0 tumors (MST 4.7 vs. 2.7 years, respectively, p=0.14). Survival outcomes analyzed by other T and N stages were not statistically significant. Conclusions: Adjuvant RT does not confer a survival benefit in resected ampullary cancers as studied in the propensity-score adjusted SEER patient population. Further studies should be conducted in order to elucidate the role of adjuvant RT for ampullary cancers.

scholarly journals Evaluation of the prognostic relevance of the recommended minimum number of lymph nodes in colorectal cancer—a propensity score analysis

2021 ◽  
Author(s):  
Michaela Ramser ◽  
Leonard A. Lobbes ◽  
Rene Warschkow ◽  
Carsten T. Viehl ◽  
Johannes C. Lauscher ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Propensity Score ◽  
Propensity Score Matching ◽  
Cox Regression ◽  
Propensity Score Analysis ◽  
Disease Free Survival ◽  
Stage I ◽  
Score Analysis ◽  
Minimum Number ◽  
The Impact

Abstract Purpose Nodal status in colorectal cancer (CRC) is an important prognostic factor, and adequate lymph node (LN) staging is crucial. Whether the number of resected and analysed LN has a direct impact on overall survival (OS), cancer-specific survival (CSS) and disease-free survival (DFS) is much discussed. Guidelines request a minimum number of 12 LN to be analysed. Whether that threshold marks a prognostic relevant cut-off remains unknown. Methods Patients operated for stage I–III CRC were identified from a prospectively maintained database. The impact of the number of analysed LN on OS, CSS and DFS was assessed using Cox regression and propensity score analysis. Results Of the 687 patients, 81.8% had ≥ 12 LN resected and analysed. Median LN yield was 17.0 (IQR 13.0–23.0). Resection and analysis of ≥ 12 LN was associated with improved OS (HR = 0.73, 95% CI: 0.56–0.95, p = 0.033), CSS (HR 0.52, 95% CI: 0.31–0.85, p = 0.030) and DFS (HR = 0.73, 95% CI: 0.57–0.95, p = 0.030) in multivariate Cox analysis. After adjusting for biasing factors with propensity score matching, resection of ≥ 12 LN was significantly associated with improved OS (HR = 0.59; 95% CI: 0.43–0.81; p = 0.002), CSS (HR = 0.34; 95% CI: 0.20–0.60; p < 0.001) and DFS (HR = 0.55; 95% CI: 0.41–0.74; p < 0.001) compared to patients with < 12 LN. Conclusion Eliminating biasing factors by a propensity score matching analysis underlines the prognostic importance of the number of analysed LN. The set threshold marks the minimum number of required LN but nevertheless represents a cut-off regarding outcome in stage I–III CRC. This analysis therefore highlights the significance and importance of adherence to surgical oncological standards.

Sign in / Sign up

Export Citation Format

Share Document