arXiv subjects

Julia Dyck

Publications and source records attributed to Julia Dyck.

5 recordsLinked to original sources

arXiv2026

Applying the Weibull Shape Parameter test for signal detection in pharmacovigilance using the R package WSPsignal

Post-marketing pharmacovigilance relies on statistical signal detection methods to identify potential adverse drug reactions. The Weibull shape parameter (WSP) test concept exploits temporal information (electronic health records) to assess the hazard of an adverse event over time after drug initiation. A statistically significant deviation from constancy results in a signal. The WSP framework comprises a family of tests that differ with respect to the estimation approach (frequentist or Bayesian), the chosen time-to-event distribution (Weibull, double Weibull, power generalized Weibull) for hazard modeling, and test specification parameters. To facilitate practical application and encourage consideration of the WSP signal detection test in future research, we developed the R package WSPsignal. The package consolidates all functionalities required for WSP testing into a unified, open-source interface. It enables practitioners and researchers to apply default test specifications or perform simulation-based tuning to identify the optimal test for a given data scenario. We illustrate the package functionalities in two examples to follow along. In a large-sample setting (ca. 20 000 observations), a frequentist WSP test is considered. In a small-sample setting (ca. 1 000 observations), a Bayesian WSP test is chosen. The additional test specifications are optimized through simulation-based tuning.

stat.ME↗

arXiv2024

The BPgWSP test: a Bayesian Weibull Shape Parameter signal detection test for adverse drug reactions

We develop the Bayesian Power generalized Weibull shape parameter (BPgWSP) test as statistical method for signal detection of possible drug-adverse event associations using electronic health records for pharmacovigilance. The Bayesian approach allows the incorporation of prior knowledge about the likely time of occurrence along time-to-event data. The test is based on the shape parameters of the Power generalized Weibull (PgW) distribution. When both shape parameters are equal to one, the PgW distribution reduces to an exponential distribution, yielding a constant hazard function. This is interpreted as no temporal association between drug and adverse event (AE). The BPgWSP test involves comparing a region of practical equivalence (ROPE) around one reflecting the null hypothesis with estimated credibility intervals (CI) reflecting the posterior means of the shape parameters. The decision to raise a signal is based on the CI+ROPE tests and the selected combination rule for these outcomes. The test development requires a simulation study for tuning of the ROPE and CIs to optimize specificity and sensitivity of the test. Samples are generated under various conditions, including differences in sample size, prevalence of adverse drug reactions (ADRs), and the proportion of AEs. We explore prior assumptions reflecting the belief in the presence or absence of ADRs at different points in the observation period. Various types of ROPE, CIs, and combination rules are assessed, and optimal tuning parameters are identified based on the area under the curve. The tuned BPgWSP test is illustrated in a case study in which the time-dependent correlation between the intake of bisphosphonates and four AEs is investigated.

stat.ME↗

arXiv2024

EgoCor: an R package to facilitate the use of exponential semi-variograms for modelling the local spatial correlation structure in social epidemiology

As an alternative to using administrative areas for the evaluation of small-area health inequalities, Sauzet et al. suggested to take an ego-centred approach and model the spatial correlation structure of health outcomes at the individual level. Existing tools for the analysis of spatial data in R might appear too complex to non-specialists which could limit the use of the approach. We present the R package EgoCor which offers a user-friendly interface displaying in one function a range of graphics and tables of parameters to facilitate the decision making about which exponential parameters fit best either raw data or residuals. This function is based on the functions of the R package gstat. Moreover, we implemented a function providing the measure of uncertainty proposed by Dyck and Sauzet. With the R package EgoCor the modelling of spatial correlation structure of health outcomes or spatially structured predictors of health with a measure of uncertainty is made available to non-specialists.

stat.CO↗

arXiv2023

Optimal p-values and sample size for signal detection methods based on generalised Weibull distributions

Objectives: Statistical methods for signal detection of adverse drug reactions in electronics health records (EHRs) are not usually provided with information about optimal p-values and indicative sample sizes to achieve sufficient power. Sauzet \& Cornelius (2022) have proposed test for signal detection based on the hazard functions of Weibull type distributions (WSP tests) which make use of the time-to-event information available in EHRs. We investigate optimal p-values for these methods and sample sizes needed to reach certain test powers. Study design and setting: We perform a simulation study with a range of scenarios for sample size, rate of event due (ADRs) and not due to the drug and a random time after prescription at which ADRs occurs. Based on the area under the curve, we obtain optimal p-values of the different WSP tests for the implementation in a hypothesis free signal detection setting. We also obtain approximate sample sizes required to reach a power of 80 or 90\%. Results: The dWSP (double WSP) and the pWSP-dPWSP (combination of power WSP and dWSP) provide similar results and we recommend using a p-value of 0.01. With this p-values the sample sizes needed for a power of 80\% starts at 30 events for an ADR rate of 0.01 and a background rate of 0.01. For a background rate of 0.05 and an ADR rate equal to a 20\% increase of the background rate the number of events required is 300. Conclusion: For the implementation of WSP type test for signal detection in a hypothesis free setting a p-values of 0.01 is recommended. The number of observations and events required to achieve a correct power of detection is commensurable to the size of typical EHR data.

stat.AP↗

arXiv2023

Parameter uncertainty estimation for exponential semi-variogram models: Two generalized bootstrap methods with check- and quantile-based filtering

The estimation of parameter standard errors for semi-variogram models is challenging, given the two-step process required to fit a parametric model to spatially correlated data. Motivated by an application in the social-epidemiology, we focus on exponential semi-variogram models fitted to data between 500 to 2000 observations and little control over the sampling design. Previously proposed methods for the estimation of standard errors cannot be applied in this context. Approximate closed form solutions are too costly using generalized least squares in terms of memory capacities. The generalized bootstrap proposed by Olea and Pardo-Igúzquiza is nonetheless applicable with weighted instead of generalized least squares. However, the standard error estimates are hugely biased and imprecise. Therefore, we propose a filtering method added to the generalized bootstrap. The new development is presented and evaluated with a simulation study which shows that the generalized bootstrap with check-based filtering leads to massively improved results compared to the quantile-based filter method and previously developed approaches. We provide a case study using birthweight data.

stat.ME↗