Library · Causal inference & statistics
What Survival & Proportional Hazards Modeling got wrong, from 30 theses
Summary written by a model from the records below: The records document challenges encountered when applying survival analysis and proportional hazards models across clinical, epidemiological, and engineering domains. Common difficulties include proportional hazard assumption violations, competing terminal events that invalidate censoring assumptions, data structure mismatches, and complex machine learning methods failing against simpler baselines. These records come from graduate theses, 2021 to 2026, each labeled with its degree where the repository states it, and each links to its thesis. They were extracted by language models reading the full text, so treat each as a lead to read, not a verdict.
Plus 10 problems the authors left open, listed at the end.
Failure modes, by theses reporting them
Select a mode to jump to its records.
Proportional hazards assumptions are frequently violated across time and covariates
Survival datasets often breached the proportional hazards assumption across treatment groups, categorical predictors, and time-varying covariates. These violations distorted risk assessments and caused researchers to reject standard Cox models or log-rank splitting criteria in favor of alternative approaches like stratified models, Poisson regression, or accelerated failure time models.
Tried and failed
Cox proportional hazards survival analysis applied to longitudinal surgical reintervention rate comparison. Reason: Proportional hazards assumption was violated over time in log-log plots
Variation in readmission and treatment reintervention rates after uterine artery embolisation and myomectomy in England: a cohort study · Imperial · Doctorate
Tried and failed
Cox proportional hazards multivariable regression applied to time-to-event epidemiological cohort data. Reason: proportional hazards assumption was violated for specific categorical predictor variables
Late or missed childhood vaccination in the United Kingdom: Identifying the determinants · Imperial · PhD
Tried and failed
Cox proportional hazards survival modeling applied to time to medication discontinuation. Reason: proportional hazards assumption was violated between treatment groups
Medication and healthcare resource utilization among Texas Medicaid patients with schizophrenia prescribed second generation antipsychotic long-acting injectables · UT Austin · PhD
Tried and failed
standard Cox proportional hazards modeling applied to cost overrun risk estimation. Reason: violated the proportional hazards assumption across key covariates without interaction terms
Enhanced Construction Cost Estimation of Highway Projects using Emerging Statistical and Machine Learning Techniques · Georgia Tech · PhD
Considered and rejected
Considered and rejected: Rejected Cox proportional hazards regression for reintervention analysis because the proportional hazards assumption was violated, adopting Poisson regression with robust standard errors instead.
Comparative Effectiveness of Endovascular Therapies and Language-Based Equity in the Management of Non-Acute Subdural Hematomas · Harvard · Master's
Considered and rejected
Considered and rejected: Rejected standard Cox proportional hazards modeling because proportional hazards assumptions are invalid and misleading in the presence of change points / U-shaped curves.
Semiparametric Change Point Model for Survival Outcomes in the Presence of a U-Shaped Risk · Johns Hopkins · Master's
Considered and rejected
Considered and rejected: Rejected conventional stratification methods to resolve Cox proportional hazards violations due to heavy reliance on continuous rather than categorical covariates.
Governing open spaces: rules, goals, and metrics in innovation communities · Boston University · PhD
Considered and rejected
Considered and rejected: Rejected Cox proportional hazards event-history model because time-varying covariates violated the constant proportional hazards assumption over time.
Essays in Labor Economics and Applied Microeconomics · Texas Tech · PhD
Considered and rejected
Considered and rejected: Rejected unstratified Cox proportional hazards model for LnPCR because LnPCR violated the proportional hazards assumption (p = 0.002), adopting a stratified Cox model instead
Dosis De Dialisis Y Marcadores Emergentes De Inflamación Y Mortalidad En Pacientes En Hemodialisis Crónica: Cloro Sérico E Índice Proteina C Reactiva/ Cloro Sérico. · University of Las Palmas de Gran Canaria · PhD
Considered and rejected
Considered and rejected: Cox Proportional Hazards (CPH) modeling was rejected due to its assumption of proportional hazards across covariate values failing on the large military datasets.
PERFORMANCE OF RANDOM SURVIVAL FORESTS WITH TIME-VARYING COVARIATES IN PREDICTION OF U.S. ARMY ENLISTED ATTRITION COMPARED TO TRADITIONAL MANPOWER ANALYSIS METHODS · Naval Postgraduate School · Master's
Considered and rejected
Considered and rejected: Rejected traditional Cox proportional hazards survival modeling due to unrealistic assumptions regarding proportional hazards and inability to accommodate treatment grace periods without survival bias.
Comparative Safety and Effectiveness of Anticonvulsants Among Older Adults · Harvard · PhD
Considered and rejected
Considered and rejected: Rejected Cox Proportional Hazards and Mantel-Haenszel log-rank tests because the proportional hazards assumption was violated (p < 0.01 on weighted-residuals score test), selecting parametric Weibull modeling and Peto-Peto-Prentice test instead.
Measuring Distributed Mentoring in an Online Fanfiction Community · University of Washington · Doctorate
Considered and rejected
Considered and rejected: Rejected traditional log-rank test splitting criterion because it relies on the proportional hazards assumption and fails when hazard curves cross.
Risk-Adjusted Time-to-Event Modeling: Integrating Absolute Risk and Biomarker-Driven Splitting · Johns Hopkins · Master's
Considered and rejected
Considered and rejected: Rejected Cox Proportional Hazards (PH) modeling in favor of Log-logistic Accelerated Failure Time (AFT) because the proportional hazards assumption did not hold and AFT directly models duration deceleration.
Ridehail and Commercial Vehicles Access in Urban Areas: Implications for Public Infrastructure Management · University of Washington · PhD
Complex machine learning and non-proportional models underperform standard baseline estimators
Flexible approaches like random survival forests, non-proportional hazard neural networks, and non-parametric estimators repeatedly failed to outperform classical Cox models or parametric baselines. These complex formulations generated higher estimation errors, excessive variance, and optimization burdens without providing predictive advantages.
Lost to a baseline
Random Survival Forest with Brier-score gradient splitting (C-index = 0.659 / error rate = 0.341) and log-rank score splitting (C-index = 0.605 / error rate = 0.395) were beaten by the Cox proportional hazards model (C-index = 0.698 / error rate = 0.302)
Prediction of second line treatment using comorbidities and patient characteristics in newly diagnosed multiple myeloma patients : a machine learning approach · UT Austin · PhD
Lost to a baseline
Random Survival Forest (C-index=0.665 / error rate=0.335) was beaten by Cox proportional hazards regression (C-index=0.698 / error rate=0.302)
Prediction of second line treatment using comorbidities and patient characteristics in newly diagnosed multiple myeloma patients : a machine learning approach · UT Austin · PhD
Lost to a baseline
When the Cox proportional hazards model is correctly specified, the nonparametric estimator exhibited higher standard deviation / variance across all biomarker values than the basic Cox model.
Statistical tools for immune correlates analysis of vaccine clinical trial data · University of Washington · PhD
Lost to a baseline
Correctly specified main-terms Cox model with Breslow estimator beat machine learning methods across MISE and MSE in proportional hazards simulations (Scenario 4).
Nonparametric methods for integration of survival analysis and machine learning · University of Washington · PhD
Tried and failed
log-normal accelerated failure time modeling applied to survival analysis with semi-competing risks. Outcome: worse than baseline. Reason: uniformly underperformed compared to Weibull and Truncated Bernstein Polynomial baseline models
Methods for Flexible Survival Analysis and Prediction of Semi-Competing Risks · Harvard · PhD
Tried and failed
random forest classification and survival modeling applied to clinical tabular outcome prediction. Outcome: worse than baseline. Reason: complex machine learning models failed to outperform classical logistic regression and Cox proportional hazards baselines
Prediction of second line treatment using comorbidities and patient characteristics in newly diagnosed multiple myeloma patients : a machine learning approach · UT Austin · PhD
Tried and failed
non-proportional hazard neural survival modeling applied to time series sensor predictive maintenance. Reason: abandoned during evaluation in favor of standard Cox proportional hazards with neural feature extraction
Predictive Maintenance in the Internet of Things: Survival Analysis and Deep Learning on Time Series Data from a Large Scale Wireless Sensor Network · Harvard · Master's
Tried and failed
learning classifier systems for survival analysis applied to germline genomic cancer prognosis. Outcome: worse than baseline. Reason: missing somatic features and restrictive rule interval bound definitions
Data limitations and structural mismatches impede survival model estimation
Models failed to converge, severely overfitted, or were rejected when data lacked censored observations, contained very few observed events, or omitted necessary time-to-event information. High-dimensional feature spaces, poorly normalized inputs, and coarse temporal resolution also prevented survival frameworks from capturing reliable relationships.
Tried and failed
standard Cox proportional hazards model applied to high-dimensional survival datasets. Outcome: did not converge. Reason: failed to complete execution on datasets with 1,000 to 10,000 features
Considered and rejected
Considered and rejected: Rejected Cox proportional hazards regression in favor of logistic regression because specific time-to-event data were not accessible in the curated analysis files.
Tried and failed
survival analysis model coupled to finite element simulation applied to tissue thermal and pressure damage prediction. Outcome: did not generalise. Reason: training data had coarse temporal resolution and lacked uncoupled baseline parameter regimes
New tissue damage model for pressure and thermal injuries and its practical application · UT Austin · PhD
Considered and rejected
Considered and rejected: Decided against using survival analysis for churn prediction because the dataset contained no censored data (full campaign duration was recorded).
Alone with Company: Studying Individual and Social Players' In-game Behaviors in Adaptive Gamification · University of Trento · PhD
Tried and failed
deterministic regression and survival analysis applied to infrastructure asset renewal prioritization. Outcome: data insufficient. Reason: failed to capture critical parameter relationships when input data was missing or poorly normalized
Fuzzy Logic-based Economic Model for Water Main Renewal · Virginia Tech · Doctorate
Competing risks invalidate standard non-informative censoring assumptions
Treating competing terminal events like deaths as standard censored observations violated non-informative censoring assumptions. This conflation of fatal outcomes with healthy non-events led researchers to reject standard Cox regression in favor of competing risk frameworks.
Considered and rejected
Considered and rejected: Rejected Cox proportional hazards regression in favor of competing risk analysis because Cox regression inappropriately treats competing terminal events as standard censored observations.
Considered and rejected
Considered and rejected: Rejected standard Cox proportional hazards regression and Poisson models for primary hospitalisation analyses because censoring deaths conflates healthy non-admissions with fatal non-admissions and violates distribution assumptions.
Considered and rejected
Considered and rejected: Standard Cox proportional hazards model rejected for cause-specific mortality because non-respiratory deaths violate non-informative censoring assumptions, prompting the use of Fine-Gray competing risk regression.
Understanding the burden of COPD mortality: An investigation using UK electronic healthcare record data · Imperial · PhD
Variational inference and nuisance parameter expansion introduce variance and optimization difficulties
Attempting to correct for dependent truncation by adding nuisance parameters increased variance noise beyond any achieved bias reduction. Variational Bayes techniques also suffered from variance underestimation and parameter explosion that impaired optimization compared to Markov chain Monte Carlo and standard frequentist methods.
Tried and failed
adding nuisance parameters for dependent truncation correction applied to survival analysis with missing covariates. Outcome: worse than baseline. Reason: estimating additional nuisance parameters introduced more variance noise than the bias reduction gained
Missing Data and Measurement Error Methods for Left-Truncated Survival Data · Penn · PhD
Tried and failed
Bayes by Backprop variational inference applied to survival analysis neural networks. Outcome: worse than baseline. Reason: doubling parameter count impaired optimization compared to Monte Carlo Dropout and frequentist models
Predicting patient pathways: a proper concordance index, deep multi-state models, and uncertainty quantification · Imperial · PhD
Lost to a baseline
SVB marginal credible interval coverage for non-zero coefficients (0.770) was lower than MCMC (0.928) on survival analysis setting 1 with c=0.25 due to variational variance underestimation.
Variational bayes for high-dimensional linear models · Imperial · PhD
Left open by the authors
Problems the authors named and did not get to.
Left open
Evaluate how violating the proportional hazards assumption affects the generalizability and performance of deep survival analysis models. Blocker: None
Scalable and Deep Bayesian Nonparametric Survival Analysis for Large-Scale Data · Texas Tech · PhD
Left open
Investigate alternative survival models beyond proportional hazards and proportional reversed hazards for left-truncated interval-censored data. Blocker: Lacks specific target models, mathematical formulations, or concrete test construction approaches
Analyzing Cohort Studies with Left-truncated and Interval-censored Data: A New Model-based Linear Rank-type Test · Texas State University · Master's
Left open
Evaluate alternative survival models including log-logistic, Cox proportional hazards, frailty, and cure rate models for object persistence modeling. Blocker: None
Spatio-temporal object persistence modeling and semantics for long-term robot navigation · UT Austin · PhD
Left open
Revisit Cox proportional hazards simulation studies using martingale-based score equations dM_i(t) to improve sandwich variance performance in unified estimation. Blocker: None
Improving applicability of the non-monotone unified estimate for missing data · University of Regina · Master's
Left open
Implement Cox proportional hazards models with Breslow estimator-derived weights instead of pooled logistic regressions for validation set risk prediction. Blocker: None
Statistical Methods for Outcome Measurement Error Correction, And Multi-study Prediction And Causal Inference under Study Heterogeneity · Harvard · PhD
Left open
Evaluate whether strong relationality protects against divorce, abuse, or serious illness using longitudinal survival analysis. Blocker: Lacks specific operationalization, target datasets, and defined survival models for the various non-infidelity outcomes
Is Fidelity a Matter of Turning On or Toward One’s Partner? A Survival Analysis of Sexual Quality and Strong Relationality as Protective Factors Against Infidelity · Texas Tech · PhD
Left open
Extend interval-censored measurement error estimation methods from discrete proportional hazards to continuous failure time models. Blocker: None
Left open
Extend the Bayesian project portfolio model using survival analysis and proportional hazards models to evaluate budget, time, and cost failure mechanisms. Blocker: None
A Bayesian learning approach to advance the reliability of LeAgile project portfolio management · Texas Tech · PhD
Left open
Extend the discrete proportional hazards measurement error model to allow outcome errors dependent on covariates or previous responses. Blocker: None
Left open
Implement and evaluate LSTM or Transformer architectures for Cox proportional hazards survival analysis on sequential time series sensor data. Blocker: None
Predictive Maintenance in the Internet of Things: Survival Analysis and Deep Learning on Time Series Data from a Large Scale Wireless Sensor Network · Harvard · Master's
Who has worked on this
Authors of the public theses cited on this page, most-cited first.
- Alexa Abigail Woodward · Penn · PhD · 2022
Capturing complex patterns of association in genetic data: a rule based machine learning approach to survival analysis - Lillian Boe · Penn · PhD · 2022
Statistical Approaches To Reducing Bias And Improving Variance Estimation In The Presence Of Covariate And Outcome Measurement Error - Nodari Gogoberidze · Harvard · Master's · 2021
Predictive Maintenance in the Internet of Things: Survival Analysis and Deep Learning on Time Series Data from a Large Scale Wireless Sensor Network - Victor Anyebe Anyebe · Harvard · Master's · 2026
Project 1 Title: Body Mass Index and the Risk of HIV Acquisition in Transgender Women and Men who have sex with Men: A Secondary Analysis; Project 2 Title: Global Prevalence of Metabolic Syndrome in A - Robert Flynn · Boston University · PhD · 2026
Governing open spaces: rules, goals, and metrics in innovation communities - Ignacio Mesina · Harvard · Master's · 2025
Comparative Effectiveness of Endovascular Therapies and Language-Based Equity in the Management of Non-Acute Subdural Hematomas - Helen Skirrow · Imperial · PhD · 2025
Late or missed childhood vaccination in the United Kingdom: Identifying the determinants - Michael Komodromos · Imperial · PhD · 2025
Variational bayes for high-dimensional linear models - Ernesto Francisco Valga Amado · University of Las Palmas de Gran Canaria · PhD · 2025
Dosis De Dialisis Y Marcadores Emergentes De Inflamación Y Mortalidad En Pacientes En Hemodialisis Crónica: Cloro Sérico E Índice Proteina C Reactiva/ Cloro Sérico. - Xiyao Zou · Johns Hopkins · Master's · 2025
Risk-Adjusted Time-to-Event Modeling: Integrating Absolute Risk and Biomarker-Driven Splitting - Stephen Michael Welling · Virginia Tech · Doctorate · 2025
Fuzzy Logic-based Economic Model for Water Main Renewal - Ning Dong · Texas Tech · PhD · 2025
Scalable and Deep Bayesian Nonparametric Survival Analysis for Large-Scale Data
Checking a claim in this area?
We can run the same search on any method or claim. If nothing turns up, we will say so, and that proves nothing on its own.