Dataset Information

Comparison of Calipers for Matching on the Disease Risk Score.

ABSTRACT: Previous studies have compared calipers for propensity score (PS) matching, but none have considered calipers for matching on the disease risk score (DRS). We used Medicare claims data to perform 3 cohort studies of medication initiators: a study of raloxifene versus alendronate in 1-year nonvertebral fracture risk, a study of cyclooxygenase 2 inhibitors versus nonselective nonsteroidal antiinflammatory medications in 6-month gastrointestinal bleeding, and a study of simvastatin + ezetimibe versus simvastatin alone in 6-month cardiovascular outcomes. The study periods for each cohort were 1998 through 2005, 1999 through 2002, and 2004 through 2005, respectively. In each cohort, we calculated 1) a DRS, 2) a prognostic PS which included the DRS as the independent variable in a PS model, and 3) the PS for each patient. We then nearest-neighbor matched on each score in a variable ratio and a fixed ratio within 8 calipers based on the standard deviation of the logit and the natural score scale. When variable ratio matching on the DRS, a caliper of 0.05 on the natural scale performed poorly when the outcome was rare. The prognostic PS did not appear to offer any consistent practical benefits over matching on the DRS directly. In general, logit-based calipers or calipers smaller than 0.05 on the natural scale performed well when DRS matching in all examples.

SUBMITTER: Connolly JG

PROVIDER: S-EPMC4867154 | biostudies-literature | 2016 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Comparison of Calipers for Matching on the Disease Risk Score.

Connolly John G JG Gagne Joshua J JJ

American journal of epidemiology 20160401 10

Previous studies have compared calipers for propensity score (PS) matching, but none have considered calipers for matching on the disease risk score (DRS). We used Medicare claims data to perform 3 cohort studies of medication initiators: a study of raloxifene versus alendronate in 1-year nonvertebral fracture risk, a study of cyclooxygenase 2 inhibitors versus nonselective nonsteroidal antiinflammatory medications in 6-month gastrointestinal bleeding, and a study of simvastatin + ezetimibe vers ...[more]

PMID: 27037270

Similar Datasets

Project description:BackgroundCardinality matching (CM), a novel matching technique, finds the largest matched sample meeting prespecified balance criteria thereby overcoming limitations of propensity score matching (PSM) associated with limited covariate overlap, which are especially pronounced in studies with small sample sizes. The current study proposes a framework for large-scale CM (LS-CM); and compares large-scale PSM (LS-PSM) and LS-CM in terms of post-match sample size, covariate balance and residual confounding at progressively smaller sample sizes.MethodsEvaluation of LS-PSM and LS-CM within a comparative cohort study of new users of angiotensin-converting enzyme inhibitor (ACEI) and thiazide or thiazide-like diuretic monotherapy identified from a U.S. insurance claims database. Candidate covariates included patient demographics, and all observed prior conditions, drug exposures and procedures. Propensity scores were calculated using LASSO regression, and candidate covariates with non-zero beta coefficients in the propensity model were defined as matching covariates for use in LS-CM. One-to-one matching was performed using progressively tighter parameter settings. Covariate balance was assessed using standardized mean differences. Hazard ratios for negative control outcomes perceived as unassociated with treatment (i.e., true hazard ratio of 1) were estimated using unconditional Cox models. Residual confounding was assessed using the expected systematic error of the empirical null distribution of negative control effect estimates compared to the ground truth. To simulate diverse research conditions, analyses were repeated within 10 %, 1 and 0.5 % subsample groups with increasingly limited covariate overlap.ResultsA total of 172,117 patients (ACEI: 129,078; thiazide: 43,039) met the study criteria. As compared to LS-PSM, LS-CM was associated with increased sample retention. Although LS-PSM achieved balance across all matching covariates within the full study population, substantial matching covariate imbalance was observed within the 1 and 0.5 % subsample groups. Meanwhile, LS-CM achieved matching covariate balance across all analyses. LS-PSM was associated with better candidate covariate balance within the full study population. Otherwise, both matching techniques achieved comparable candidate covariate balance and expected systematic error.ConclusionsLS-CM found the largest matched sample meeting prespecified balance criteria while achieving comparable candidate covariate balance and residual confounding. We recommend LS-CM as an alternative to LS-PSM in studies with small sample sizes or limited covariate overlap.

Project description:The dataset presented was collected via retrospective review from an orthopedic trauma database approved by the institutional review board at the author's institution from patients treated at any of the four hospitals serviced by the academic orthopedic surgery department. Femoral neck and intertrochanteric hip fracture patients from low energy mechanisms admitted between October 2014 and February 2020, were selected if they were age 55 or older and had recorded sex, body mass index (BMI), Charlson Comorbidity Index (CCI), American Society of Anaesthesiologists (ASA) physical status classification, Glasgow Coma Score, Abbreviated Injury Severity score for the chest, head and neck, and extremities, and ambulation status prior to injury. The resultant 1,590 subject dataset may be analysed via the supplied R statistical code to determine the frequency of equipoise in baseline and outcome variables from propensity matching via three matching schemes. The code implements three matching schemes including matching by (1) The Score for Trauma Triage in Geriatric and Middle-Aged (STTGMA) (2) CCI alone, or (3) a combination of sex, age, CCI and BMI. The code selects a subset of ten percent of hip fracture patients by a pseudorandom number generator (PRNG). The code matches the remaining patients 1:1 to the selected patients by propensity score generated by logistic regression of STTGMA, CCI, or a combination of sex, age, CCI and BMI using greedy nearest neighbor matching without replacement by the MatchIt package for R software. The code then compares matched cohorts by Chi-square, Fisher, or Mann-Whitney U test with significance level of 0.05 representing a 5% chance of significant differences due to random sampling of subjects. The supplied code repeats the random selection, matching and testing process 100,000 times for each matching method. The resultant code output is the frequency of significantly different demographic or outcome parameters among matched cohorts by matching method. This data and statistical code have reuse potential to explore alternative matching schemes. The supplied baseline variables should be robust enough to derive alternative risk scores for each patient which may be included as a matching variable for comparison. The authors also look forward to unexpected ways that this data may be used by readers.

Dataset Information

Comparison of Calipers for Matching on the Disease Risk Score.

Publications

Comparison of Calipers for Matching on the Disease Risk Score.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets