scholarly journals Proper Specification of Nonproportional Hazards Corrections in Duration Models

2017 ◽  
Vol 25 (1) ◽  
pp. 138-144 ◽  
Author(s):  
Shuai Jin ◽  
Frederick J. Boehmke
Keyword(s):  
Proportional Hazards ◽  
Model Specification ◽  
Duration Models ◽  
Time Varying ◽  
Nonproportional Hazards ◽  
Incorrect Model ◽  
Proper Estimation ◽  
Time Invariant ◽  
Time Varying Covariates ◽  
Biased Estimates

Parametric and nonparametric duration models assume proportional hazards: The effect of a covariate on the hazard rate stays constant over time. Researchers have developed techniques to test and correct nonproportional hazards, including interacting the covariates with some function of time. Including this interaction term means that the specification now involves time-varying covariates, and the model specification should reflect this feature. However, in situations with no time-varying covariates initially, researchers often continue to model the duration with only time-invariant covariates. This error results in biased estimates, particularly for the covariates interacted with time. We investigate this issue in over forty political science articles and find that of those studies that begin with time-invariant covariates and correct for nonproportional hazards the majority suffer from incorrect model specification. Proper estimation usually produces substantively or statistically different results.

scholarly journals Doubly robust estimator of risk in the presence of censoring dependent on time-varying covariates: application to a primary prevention trial for coronary events with pravastatin

2020 ◽  
Author(s):  
Takuya Kawahara ◽  
Tomohiro Shinozaki ◽  
Yutaka Matsuyama
Keyword(s):  
Model Misspecification ◽  
Clinical Trial Data ◽  
Dependent Censoring ◽  
Model Specification ◽  
Robust Estimator ◽  
Time Varying ◽  
Simulation Studies ◽  
Kaplan Meier ◽  
Doubly Robust ◽  
Time Varying Covariates

Abstract Background: In the presence of dependent censoring even after stratification of baseline covariates, the Kaplan–Meier estimator provides an inconsistent estimate of risk. To account for dependent censoring, time-varying covariates can be used along with two statistical methods: the inverse probability of censoring weighted (IPCW) Kaplan–Meier estimator and the parametric g-formula estimator. The consistency of the IPCW Kaplan–Meier estimator depends on the correctness of the model specification of censoring hazard, whereas that of the parametric g-formula estimator depends on the correctness of the models for event hazard and time-varying covariates. Methods: We combined the IPCW Kaplan–Meier estimator and the parametric g-formula estimator into a doubly robust estimator that can adjust for dependent censoring. The estimator is theoretically more robust to model misspecification than the IPCW Kaplan–Meier estimator and the parametric g-formula estimator. We conducted simulation studies with a time-varying covariate that affected both time-to-event and censoring under correct and incorrect models for censoring, event, and time-varying covariates. We applied our proposed estimator to a large clinical trial data with censoring before the end of follow-up. Results: Simulation studies demonstrated that our proposed estimator is doubly robust, namely it is consistent if either the model for the IPCW Kaplan–Meier estimator or the models for the parametric g-formula estimator, but not necessarily both, is correctly specified. Simulation studies and data application demonstrated that our estimator can be more efficient than the IPCW Kaplan–Meier estimator. Conclusions: The proposed estimator is useful for estimation of risk if censoring is affected by time-varying risk factors.

“I Hope I Get It”: impact of Tony Award nominations and wins on Broadway production longevity

2018 ◽  
Vol 8 (1) ◽  
pp. 30-46 ◽  
Author(s):  
Russell Thomas Warne
Keyword(s):  
Statistical Power ◽  
Open Science ◽  
Production Costs ◽  
Time Varying ◽  
Cumulative Impact ◽  
Content Type ◽  
Theater Production ◽  
Time Invariant ◽  
The Impact ◽  
Time Varying Covariates

PurposeThe purpose of this paper is to ascertain the relative impact of different Tony Award nominations and wins on the financial success of a Broadway theater production, as defined by the length of the production’s run.Design/methodology/approachCox hazard regression was used to identify the impact of Tony Award nominations and wins (time-varying covariates), while controlling for several time-invariant covariates: type of production (play or musical, revival or original Broadway production), production costs (operationalized via the cast size), the month and year of opening, and initial marketing success (defined as the percentage of first full week’s tickets sold).FindingsThe award with the strongest relationship with production longevity was the Tony Award for Best Musical (nomination OR=0.566,p=0.110; win OR=0.323,p=0.020). Several other awards had a relationship with production longevity, but most were not statistically significant.Research limitations/implicationsThe limitations include the low statistical power for many time-varying covariates and the cumulative impact of multiple awards was not investigated. Future researchers interested in the Broadway industry should not combine Tony Awards because of the varying impact on economic outcomes for a production.Originality/valueThis study is the first to investigate all 22 Tony Award nominations and wins and their individual impact on an economic outcome. This paper includes the study’s raw data and SPSS syntax to comply with open science practices. The author encourages readers to replicate the analysis.

scholarly journals Pain Persistence Is Associated With Increased Odds of MCI in Late Midlife and Early Older Adulthood

2021 ◽  
Vol 5 (Supplement_1) ◽  
pp. 115-115
Author(s):  
Tyler Bell ◽  
Jeremy Elman ◽  
Carol Franz ◽  
William Kremen
Keyword(s):  
Pain Intensity ◽  
Persistent Pain ◽  
Time Varying ◽  
Opioid Use ◽  
Older Adulthood ◽  
Clinical Pain ◽  
Time Invariant ◽  
The Impact ◽  
Time Varying Covariates ◽  
Late Midlife

Abstract Twenty percent of older adults will experience persistent pain, the sensation of bodily harm lasting three or more months. Persistent pain doubles the risk of dementia, but we know less about the impact on earlier stages, such as mild cognitive impairment (MCI). As a step for clarification, this study leveraged data from the Vietnam Era Twin Study of Aging (VETSA) to understand how pain persistence relates to MCI in late midlife to early older adulthood. Participants (n=1,465, 100% male) were recruited across three waves at average ages 56, 62, and 68. At each wave, participants completed the SF-36 and were asked to rate their pain intensity from none (1) to very severe (6). Clinical pain was coded as pain intensity rated more than mild (>3/6). As a time-varying predictor, pain persistence was then calculated as a running frequency of the total waves reporting clinical pain. MCI diagnosis was based on Jak-Bondi criteria. Age, depressive symptoms, comorbidities, and opioid use were included as time-varying covariates. Age and education were included as time-invariant covariates. General estimating equations showed that pain persistence over two waves, reported in 35% of the sample, increased MCI odds by 57% (OR=1.57, 95%CI: 1.28 to 1.94). Pain persistence over three waves, reported in 17% of the sample, increased MCI odds by 98% (OR=1.98, 95%CI: 1.44 to 2.70). The findings emphasize the role of pain in earlier stages of dementia and the potential importance of pain management in offsetting cognitive decline.

Role of cytoreductive nephrectomy (CN) in metastatic renal cell carcinoma (mRCC).

2021 ◽  
Vol 39 (15_suppl) ◽  
pp. 4582-4582
Author(s):  
Pooja Ghatalia ◽  
Elizabeth A. Handorf ◽  
Mengying Deng ◽  
Matthew R. Zibelman ◽  
Philip Abbosh ◽  
...  
Keyword(s):  
Propensity Score ◽  
Systemic Therapy ◽  
Proportional Hazards ◽  
Statistical Significance ◽  
Patient Characteristics ◽  
Cox Proportional Hazards ◽  
Time Varying ◽  
Health Database ◽  
Time Varying Covariates

4582 Background: The role of CN in mRCC was challenged by the results of the CARMENA trial in the targeted therapy (TT) era. We sought to evaluate the role of both upfront and deferred CN in pts receiving modern IO-based and TT regimens. Methods: Pts with synchronous mRCC who received systemic therapy (tx) for mRCC after 2011 were included from the de-identified nationwide Flatiron Health database. We evaluated 3 groups: systemic tx alone, systemic-> CN, and CN-> systemic tx. Overall survival (OS) was calculated from the time of initiation of first therapy – systemic or CN. Patient characteristics were compared using chi-squared tests or t-test. Weighted Kaplan-Meier curves, log-rank tests, and Cox proportional hazards regressions with time-varying covariates were used to assess the effect of tx on survival. Adjustment was conducted via inverse probability of treatment weighing based on the generalized propensity score, estimated via Bayesian Additive Regression Trees. Covariates in the model were age, gender, race, insurance at mRCC diagnosis, and IMDC risk group. Results: Of 1719 pts with mRCC, 972 (56.5%) received systemic tx alone, 605 (35.1%) received CN-> systemic tx, and 142 (8.2%) received systemic->CN. 310 pts received IO or IO/IO, 123 pts received IO+TT and 1152 pts received only TT. The median follow-up was 37.1 months. In adjusted analyses using propensity score weighting and time-varying covariates, CN-> systemic was significantly associated with improved OS compared with systemic tx alone (Table). When stratifying groups by type of systemic treatment (IO and TT), there was improvement of OS in the CN groups compared to systemic tx alone, although we lacked power to reach statistical significance. Among CN-treated patients, the order of systemic tx relative to CN did not change OS (hazard ratio [HR] = 1.00, 95% CI 0.76-1.32, p=0.96). Conclusions: Using a national, EHR-based cohort, which includes a large number of IO treated pts, our findings support an oncologic role for CN in select mRCC pts. The timing of CN, for pts who were able to receive both systemic therapy and CN, may not affect overall outcome. The associated improvement in survival of CN is seen in pts receiving IO and TKI based systemic tx.[Table: see text]

Modeling the Time-Varying Nature of Student Exceptionality Classification on Achievement Growth

2016 ◽  
Vol 51 (1) ◽  
pp. 38-49 ◽  
Author(s):  
Joseph F. T. Nese ◽  
Joseph J. Stevens ◽  
Ann C. Schulte ◽  
Gerald Tindal ◽  
Stephen N. Elliott
Keyword(s):  
Special Education ◽  
Mathematics Achievement ◽  
Growth Models ◽  
Model Fit ◽  
Model Specification ◽  
Time Varying ◽  
Single Model ◽  
Fit Statistics ◽  
Achievement Growth ◽  
Time Invariant

Our purpose was to examine different approaches to modeling the time-varying nature of exceptionality classification. Using longitudinal data from one state’s mathematics achievement test for 28,829 students in Grades 3 to 8, we describe the reclassification rate within special education and between general and special education, and compare four alternative growth models for students with and without disabilities with different specifications of disability classification as time-variant (TVC) or time-invariant (TIC) covariates. Although model fit statistics were inconsistent in endorsing a single model, we found that the TIC results were generally preferable to the TVC; however, the choice of model specification may rest on the purpose of the researcher and goals of representing the influence of covariates on growth.

Sign in / Sign up

Export Citation Format

Share Document