Jochen Einbeck
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Jochen Einbeck has a total of 189 co-authors. Here are the top co-authors by number of shared publications:
- Nadja Reissland
Department of Psychology Durham University Durham UK
6 shared publications - Elizabeth A. Ainsbury
UK Health Security Agency, London, England, UNITED KINGDOM OF GREAT BRITAIN AND NORTHERN IRELAND
5 shared publications - Tathagata Basu
University of Strathclyde
5 shared publications - Akansha Singh
Department of Anthropology, Durham University, Durham, UK
4 shared publications - Amani Almohaimeed
Affiliation Department of Statistics and Operations Research, College of Science, Qassim University, Buraydah, Saudi Arabia
4 shared publications Ludger Evers
Department of Statistics, University of Glasgow, Glasgow G12 8QQ, Scotland
4 shared publications
Latest Publications
- Open Access
- 2 September 2026
- Published by F1000 Research Ltd in F1000Research
- Vol. 15, 1476
The eefAnalytics R package for the Analysis of Randomised Controlled Trials in Education
The eefAnalytics R package provides functions to analyse randomised controlled trials according to the study design, including simple randomized trials, cluster randomized trials, and multisite trials. The eefAnalytics package enables R users to easily obtain conditional and unconditional Hedges’ g effect sizes and their confidence or credible intervals. A central contribution of this software package is the correct computation of effect size uncertainties incorporating the variance of the denominator. Statistical models are chosen according to design type, with a simple linear regression model for simple randomized trials, and appropriate multi-level models for cluster randomised and multisite trials. Beside the effect sizes and their confidence/credible intervals in both frequentist and Bayesian approaches, the package also facilitates Bayesian, permutation and bootstrap techniques, and provides functions for the visualization of results such as posterior random effects. This article provides an overview of the modelling techniques used as the basis of the eefAnalytics package and demonstrates its application with examples. The package is available from CRAN: https://cran.r-project.org/package=eefAnalytics.
- 2 September 2026
- Published by F1000 Research Ltd in F1000Research
- Vol. 15, 1476
Open AccessThe eefAnalytics R package for the Analysis of Randomised Controlled Trials in Education
The eefAnalytics R package provides functions to analyse randomised controlled trials according to the study design, including simple randomized trials, cluster randomized trials, and multisite trials. The eefAnalytics package enables R users to easily obtain conditional and unconditional Hedges’ g effect sizes and their confidence or credible intervals. A central contribution of this software package is the correct computation of effect size uncertainties incorporating the variance of the denominator. Statistical models are chosen according to design type, with a simple linear regression model for simple randomized trials, and appropriate multi-level models for cluster randomised and multisite trials. Beside the effect sizes and their confidence/credible intervals in both frequentist and Bayesian approaches, the package also facilitates Bayesian, permutation and bootstrap techniques, and provides functions for the visualization of results such as posterior random effects. This article provides an overview of the modelling techniques used as the basis of the eefAnalytics package and demonstrates its application with examples. The package is available from CRAN: https://cran.r-project.org/package=eefAnalytics.
- Open Access
- 10 August 2026
- Published by MDPI AG in Mathematics
- Vol. 14 (16) , 2885
Single and Double Ratio Estimators for the Poisson Parameter
Classical parameter estimation for Poisson-distributed data relies mainly on maximum likelihood estimation (MLE), which assumes that the data perfectly adhere to the model assumptions, including equidispersion. However, real-world datasets often suffer from structural discrepancies that violate these assumptions, leading to biased estimates and inflated mean squared errors. This study derives two estimators—simple ratio (SR) and double ratio (DR) estimators—which are based on ratios of observed frequencies around the mode of the data. Consistency of the estimators is established analytically. Using a Monte Carlo simulation, we evaluate the performance of these estimators across four critical scenarios: outliers, right truncation, zero-inflation, and zero-truncation. In all these scenarios, the proposed estimators showed consistent behavior and, in most scenarios, superior performance to the MLE, especially for larger sample sizes. Real data examples illustrate the proposed estimators.
- 10 August 2026
- Published by MDPI AG in Mathematics
- Vol. 14 (16) , 2885
Open AccessSingle and Double Ratio Estimators for the Poisson Parameter
Classical parameter estimation for Poisson-distributed data relies mainly on maximum likelihood estimation (MLE), which assumes that the data perfectly adhere to the model assumptions, including equidispersion. However, real-world datasets often suffer from structural discrepancies that violate these assumptions, leading to biased estimates and inflated mean squared errors. This study derives two estimators—simple ratio (SR) and double ratio (DR) estimators—which are based on ratios of observed frequencies around the mode of the data. Consistency of the estimators is established analytically. Using a Monte Carlo simulation, we evaluate the performance of these estimators across four critical scenarios: outliers, right truncation, zero-inflation, and zero-truncation. In all these scenarios, the proposed estimators showed consistent behavior and, in most scenarios, superior performance to the MLE, especially for larger sample sizes. Real data examples illustrate the proposed estimators.
- Open Access
- 12 May 2026
- Published by Wiley in Developmental Psychobiology
- Vol. 68 (3) , e70165
Do Human Fetuses Form Long‐Lasting Chemosensory Memories? Longitudinal Follow‐Up From Fetus to Young Child of Facial Responses to Flavor/Odor Stimuli
Prenatal flavor exposure is known to provide the foundation for later flavor or odor preferences in humans, yet the persistence of fetal flavor/odor memories into early childhood remains unclear. In previous studies, fetuses at 32‐ and 36 weeks gestation were shown to display discriminative facial reactions following a single‐dose flavor stimulation (bitter kale vs. non‐bitter carrot), and repeated exposure to these flavors from 36 weeks until birth was associated with responses to flavor‐specific odors in the first postnatal month. The current longitudinal follow‐up tested whether the prenatal exposure to two specific flavors results in flavor‐specific odor reactions at 3 years of age. Children ( n = 12) who had participated in the fetal and neonatal phases of the study were tested at 3 years of age using controlled olfactory presentations of the same flavors. Results showed that the 3‐year‐olds exhibited a significantly reduced rate of negative facial expressions in response to the odor they had been repeatedly exposed to in utero ( p < 0.001), indicating continuity from prenatal sensory experience to early childhood behavioral responses. Thus, flavor exposure in late gestation can result in long‐lasting flavor/odor memory, confirming that the prenatal chemosensory environment can shape behavioral tendencies years after birth.
- 12 May 2026
- Published by Wiley in Developmental Psychobiology
- Vol. 68 (3) , e70165
Open AccessDo Human Fetuses Form Long‐Lasting Chemosensory Memories? Longitudinal Follow‐Up From Fetus to Young Child of Facial Responses to Flavor/Odor Stimuli
Prenatal flavor exposure is known to provide the foundation for later flavor or odor preferences in humans, yet the persistence of fetal flavor/odor memories into early childhood remains unclear. In previous studies, fetuses at 32‐ and 36 weeks gestation were shown to display discriminative facial reactions following a single‐dose flavor stimulation (bitter kale vs. non‐bitter carrot), and repeated exposure to these flavors from 36 weeks until birth was associated with responses to flavor‐specific odors in the first postnatal month. The current longitudinal follow‐up tested whether the prenatal exposure to two specific flavors results in flavor‐specific odor reactions at 3 years of age. Children ( n = 12) who had participated in the fetal and neonatal phases of the study were tested at 3 years of age using controlled olfactory presentations of the same flavors. Results showed that the 3‐year‐olds exhibited a significantly reduced rate of negative facial expressions in response to the odor they had been repeatedly exposed to in utero ( p < 0.001), indicating continuity from prenatal sensory experience to early childhood behavioral responses. Thus, flavor exposure in late gestation can result in long‐lasting flavor/odor memory, confirming that the prenatal chemosensory environment can shape behavioral tendencies years after birth.
- Open Access
Assessing the Accuracy of Bootstrap-Based Standard Errors in Regression Models with Unobserved Heterogeneity
When the data at hand are suspected to stem from several latent subpopulations, Statisticians commonly speak of “unobserved heterogeneity”. While the presence and importance of this phenomenon is commonly acknowledged, there is relatively little guidance on how to carry out correct inferences under unobserved heterogeneities, even in relatively simple scenarios such as the linear regression model. In this work, bootstrap algorithms for the computation of standard errors are investigated in the context of a mixture-based regression approach which accounts for the clustered nature of the data. Of interest is both the accuracy of the standard errors (evidenced by confidence interval coverage rates) and the relative reduction in standard errors achieved in comparison to a naïve linear model fit. Simulations and a real data example are provided.
Open AccessAssessing the Accuracy of Bootstrap-Based Standard Errors in Regression Models with Unobserved Heterogeneity
When the data at hand are suspected to stem from several latent subpopulations, Statisticians commonly speak of “unobserved heterogeneity”. While the presence and importance of this phenomenon is commonly acknowledged, there is relatively little guidance on how to carry out correct inferences under unobserved heterogeneities, even in relatively simple scenarios such as the linear regression model. In this work, bootstrap algorithms for the computation of standard errors are investigated in the context of a mixture-based regression approach which accounts for the clustered nature of the data. Of interest is both the accuracy of the standard errors (evidenced by confidence interval coverage rates) and the relative reduction in standard errors achieved in comparison to a naïve linear model fit. Simulations and a real data example are provided.
- Open Access
- 6 August 2025
- Published by MDPI AG in Information
- Vol. 16 (8) , 672
A Procedure to Estimate Dose and Time of Exposure to Ionizing Radiation from the γ-H2AX Assay
Accurately estimating the radiation dose received by an individual is essential for evaluating potential damage caused by exposure to ionizing radiation. Most retrospective dosimetry methods require the time since exposure to be known and rely on calibration curves specific to that time point. In this work, we introduce a novel method tailored to the γ-H2AX assay, which is a protein-based biomarker for radiation exposure, that enables the estimation of both the radiation dose and the time of exposure within a plausible post-exposure interval. Specifically, we extend calibration curves available at two distinct time points by incorporating the biological decay of foci, resulting in a model that captures the joint dependence of foci count on both dose and time. We demonstrate the applicability of this approach using both real-world and simulated data.
- 6 August 2025
- Published by MDPI AG in Information
- Vol. 16 (8) , 672
Open AccessA Procedure to Estimate Dose and Time of Exposure to Ionizing Radiation from the γ-H2AX Assay
Accurately estimating the radiation dose received by an individual is essential for evaluating potential damage caused by exposure to ionizing radiation. Most retrospective dosimetry methods require the time since exposure to be known and rely on calibration curves specific to that time point. In this work, we introduce a novel method tailored to the γ-H2AX assay, which is a protein-based biomarker for radiation exposure, that enables the estimation of both the radiation dose and the time of exposure within a plausible post-exposure interval. Specifically, we extend calibration curves available at two distinct time points by incorporating the biological decay of foci, resulting in a model that captures the joint dependence of foci count on both dose and time. We demonstrate the applicability of this approach using both real-world and simulated data.
- Open Access
- 24 May 2025
- Published by Elsevier in Psychiatry Research
- Vol. 351, 116564
Managing unusual sensory experiences in at-risk mental state for psychosis in England: A parallel group, single-blind, randomised controlled feasibility trial
- 24 May 2025
- Published by Elsevier in Psychiatry Research
- Vol. 351, 116564
Open AccessManaging unusual sensory experiences in at-risk mental state for psychosis in England: A parallel group, single-blind, randomised controlled feasibility trial
- Open Access
- 2 April 2025
- Published by Wiley in Early Intervention in Psychiatry
- Vol. 19 (4) , e70035
Preferences for Psychological Therapy or Support Within an ARMS Psychological Therapies Trial: The Importance of Targeted Intervention for Unusual Sensory Experiences
Background: Individuals with an at risk mental state (ARMS) often experience hallucinatory‐type experiences, which we refer to as unusual sensory experiences (USE). However, it is not known whether individuals want to know more about USE or discuss these in therapy. Our preferences study asked whether individuals who are referred into a treatment trial for USE in ARMS consider attention to USE important.Methods: Ninety‐four service users of ARMS services within two UK National Health Service (NHS) mental health trusts completed the study‐specific, “Preferences for psychological therapy or support” questionnaire. Questions elicited preferences for target of therapeutic work and therapist approach. Analysis employs a repeated measures ANOVA with post hoc analysis of difference between preferences.Results: Treatment preferences which help understand causes of USE and how to manage USE were the group priority above talking therapy generally or a focus on low mood or anxiety. Provision of medication was the lowest priority in treatment preference though it was important to some. Overall, working with a therapist to make sense of experiences was more important than having space to talk, new ideas for coping, or working collaboratively on goals.Conclusions: Psychological intervention for individuals with at‐risk mental state needs to include acceptable and credible psychoeducation on causes of USE and how to manage these.
- 2 April 2025
- Published by Wiley in Early Intervention in Psychiatry
- Vol. 19 (4) , e70035
Open AccessPreferences for Psychological Therapy or Support Within an ARMS Psychological Therapies Trial: The Importance of Targeted Intervention for Unusual Sensory Experiences
Background: Individuals with an at risk mental state (ARMS) often experience hallucinatory‐type experiences, which we refer to as unusual sensory experiences (USE). However, it is not known whether individuals want to know more about USE or discuss these in therapy. Our preferences study asked whether individuals who are referred into a treatment trial for USE in ARMS consider attention to USE important.Methods: Ninety‐four service users of ARMS services within two UK National Health Service (NHS) mental health trusts completed the study‐specific, “Preferences for psychological therapy or support” questionnaire. Questions elicited preferences for target of therapeutic work and therapist approach. Analysis employs a repeated measures ANOVA with post hoc analysis of difference between preferences.Results: Treatment preferences which help understand causes of USE and how to manage USE were the group priority above talking therapy generally or a focus on low mood or anxiety. Provision of medication was the lowest priority in treatment preference though it was important to some. Overall, working with a therapist to make sense of experiences was more important than having space to talk, new ideas for coping, or working collaboratively on goals.Conclusions: Psychological intervention for individuals with at‐risk mental state needs to include acceptable and credible psychoeducation on causes of USE and how to manage these.
- Open Access
- 7 February 2025
- Published by SAGE Publications in Statistical Modelling
- Vol. 26 (2) , 123-143
A two-level multivariate response model for data with latent structures
A novel approach is proposed for analysing multilevel multivariate response data. The approach is based on identifying a one-dimensional latent variable spanning the space of responses, which then induces correlation between upper-level units. The latent variable, which can be thought of as a random effect, is estimated along with the other model parameters using an EM algorithm, which can be seen in the tradition of the 'nonparametric maximum likelihood' estimator for two-level linear (univariate response) models. Simulations and real data examples from different fields are provided to illustrate the proposed methods in the context of regression and clustering applications.
- 7 February 2025
- Published by SAGE Publications in Statistical Modelling
- Vol. 26 (2) , 123-143
Open AccessA two-level multivariate response model for data with latent structures
A novel approach is proposed for analysing multilevel multivariate response data. The approach is based on identifying a one-dimensional latent variable spanning the space of responses, which then induces correlation between upper-level units. The latent variable, which can be thought of as a random effect, is estimated along with the other model parameters using an EM algorithm, which can be seen in the tradition of the 'nonparametric maximum likelihood' estimator for two-level linear (univariate response) models. Simulations and real data examples from different fields are provided to illustrate the proposed methods in the context of regression and clustering applications.
- Open Access
- 24 September 2024
- Published by Taylor & Francis in The Journal of Experimental Education
- Vol. 94 (1) , 152-169
A Comparison of Threshold-Free Measures for Assessing the Effectiveness of Educational Interventions
- 24 September 2024
- Published by Taylor & Francis in The Journal of Experimental Education
- Vol. 94 (1) , 152-169
Open AccessA Comparison of Threshold-Free Measures for Assessing the Effectiveness of Educational Interventions