Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · 2208.09431

Simulation and inference on purely observational methods of monitoring vaccine effectiveness post-deployment: none is reliable without precise information on population behaviour

Roger F. Sewell
View original source ↗Read source document ↗Export metadata ↓

Abstract

Two observational methods are currently being used to monitor post-deployment vaccine effectiveness: the obvious crude method comparing rate testing positive per head of vaccinated population with that rate per head of unvaccinated population; and the test-negative case control (TNCC) method. The two methods give very different results. We want to know whether either method is reliable. We assume either a homogeneous population or one partitioned into two homogeneous subsets which differ only in their not-directly-observable healthcare-seeking behaviour including probability of getting vaccinated. We first consider uniform independent priors on the probabilities of being hospitalised conditional on subset, vaccination status, and infection status. We simulate from the resulting model and observe the TNCC estimate, the crude estimate, and the Bayesian central 95% confidence interval on vaccine effectiveness represented as log ratio of odds ratios for infection with and without vaccination. With these wide open priors, even when the population is homogeneous, the Bayesian 95% confidence interval typically has a width of nearly 4 nats (55-fold), implying too much uncertainty for the data collected to be of any use in monitoring effectiveness. There do exist some tight priors under which the data is useful: some lead to TNCC being more accurate while with others the crude estimate is more accurate. Thus using only data from those spontaneously choosing to be tested, we find that neither method is reliably better than the other, and indeed that the desired information is not present in this data. We conclude that effective monitoring of vaccine effectiveness and side-effects requires either strong information on the population's behaviour, or ongoing randomised controlled trials (RCTs), rather than just choosing whichever of TNCC and crude estimate gives the result we prefer to find.

Explore related subjects

stat.MEq-bio.QMstat.AP

Keep this discovery

BibTeXRIS

Roger F. Sewell. 2022-08-19. Simulation and inference on purely observational methods of monitoring vaccine effectiveness post-deployment: none is reliable without precise information on population behaviour. https://arxiv.org/abs/2208.09431

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Surprise Reduction and Nullification in Bayesian and Inverse Bayesian Inference under Ambiguous Prediction-Error Attribution

In non-stationary environments, prediction errors may signal environmental change or transient outliers, and adaptive systems must track such changes without overreacting to outliers. We distinguish surprise reduction, which updates beliefs to fit observations, from surprise nullification, which weakens constraints imposed by the predictive structure, and formalize both within Bayesian and inverse Bayesian (BIB) inference. Belief and likelihood updates are derived from variational objectives sharing a nullification strength, determined endogenously by minimizing surprise under the candidate post-update predictive distribution. In the Gaussian case, nullification expands belief and likelihood variances by a common factor relative to standard Bayesian updating, leaving the ratio unchanged. BIB thus defers attribution of the prediction error, committing to neither latent-state change nor observation-process uncertainty. The nullification strength is carried over as a candidate and is maintained or released according to the predictive surprise of the next observation. In a mean estimation task with outliers and changepoints, no scanned parameter setting of a Sage-Husa-type adaptive Kalman filter, fixed-strength BIB variant, or belief-forgetting-only variant outperforms BIB in both changepoint tracking and post-outlier stability. An oracle-informed reduced Bayesian model tracks changepoints better but is less stable after outliers. Although BIB maintains no explicit hypotheses about changepoints or outliers, it generates event-dependent dynamics. The learning rate increases after changepoints, whereas after outliers, nullification is released, and this increase is suppressed. Deferring attribution and letting subsequent observations differentiate the responses may constitute a principle of adaptive inference in non-stationary environments.

stat.ME↗
arXiv2026

Generalized Ridge Refitting for the Lasso and Prediction Improvement Bounds

We study a class of Lasso based estimators obtained by applying a quadratic correction on the Lasso equicorrelation set. The penalty matrix determines both the magnitude and geometry of the correction and contains, among other cases, the isotropic Lasso--Ridge correction, least squares refitting, Gram proportional interpolation between the Lasso and least squares, and coordinate specific penalties. We first derive a closed form representation and isolate the positive gain component of the resulting prediction improvement. We then control the remaining stochastic linear term in expectation by localizing the random signed equicorrelation model around a deterministic reference support. This yields a finite sample expectation bound that explicitly accounts for the randomness induced by Lasso model selection. The resulting decomposition provides a unified framework for understanding when Lasso based quadratic corrections can improve prediction.

stat.ME↗
arXiv2026

Discretization in covariate-adaptive randomization: gains and losses

Covariate-adaptive randomization(CAR) is widely implemented in clinical trials to balance prognostic covariates across treatment arms. Continuous covariates are often discretized into strata in practice, yet their consequences are not clearly understood. This paper provides a comprehensive study of the impact of discretization on both the CAR design process and the inferential results thereafter. We establish the asymptotic properties of both imbalance measures and treatment effect estimators under discretized and non-discretized settings. Practical recommendations are given on when and how discretization should be employed. We show that discretization in design is generally recommended, as it enhances robustness against model misspecification. However, if the true model is known, the most efficient strategy is to balance covariates according to that model in the design. The theoretical results are corroborated by extensive simulation studies and an empirical application to a diabetes trial dataset. Together, the results clarify the gains and losses of discretization in CAR and pave the way for learning impact of discretization to other designs and beyond.

stat.ME↗