It is difficult to understand the safety profile of drugs based on a single clinical trial since clinical trials are often designed to prove efficacies, and sample size is not powered for safety assessment. Thus, meta-analysis would be a valuable tool to infer the safety profiles utilizing multiple studies. Individual clinical trials usually report the incidence proportions of adverse events (AEs) observed in the study. The follow-up duration may be study-specific, and furthermore different between the treatment groups within a single study. It often occurs in oncology clinical trials and if this is the case, it is hard to interpret the aggregated relative risk of AEs and compare the risk of AEs between the treatment groups with the standard meta-analysis techniques. The progression-free survival or the overall survival is often used as the primary endpoint in oncology clinical trials and the Kaplan–Meier estimates of the survival functions for the primary endpoint are often demonstrated graphically, which give us information of the follow-up duration of the AEs. We propose novel meta-analysis methods for AEs that address differences in follow-up durations by efficiently utilizing the Kaplan–Meier estimates of the primary endpoint. We adapt our approach using both simulated data and real data from a meta-analysis of bevacizumab. Simulation studies demonstrate that the proposed methods perform well when follow-up time differs between trials and groups.

This paper introduces a novel expectation-maximization (EM) algorithm for estimating general phase-type (PH) distributions from left-truncated and right-censored (LTRC) data, a common challenge in survival analysis. The proposed algorithm is highly efficient with computational complexity that scales with the number of nonzero elements in the generator matrix. This feature makes the estimation of high-dimensional, sparse PH models computationally tractable and enables the practical use of the computationally intensive extended information criterion for model selection. Numerical experiments demonstrate its significant speed advantage over a modern benchmark and the applicability of PH models to complex lifetime data.

In this article, the effects of regional autocratic linkage on the survival of autocratic regimes are analysed. Scholars have suggested that regional factors shape regime survival through processes of diffusion. However, in most accounts, diffusion is simply derived from characteristics of the region, such as the number or proportion of regional autocracies. In contrast, it is argued here that it is the actual linkages between countries that must be examined. Regional political, economic and social ties between autocratic regimes create domestic and external stakes in the regime, counterweigh democratisation pressure and facilitate autocratic learning. The study employs the average volume of trade, migration and diplomatic exchanges between autocratic regimes within a region as proxies for regional autocratic linkage, and asserts that regional autocratic linkage is on the rise. Applying Cox survival models on a dataset of regional autocratic linkage and regime survival between 1946 and 2009, it is found that regional autocratic linkage significantly reduces the likelihood of autocratic regime breakdown. These effects hold when the proportion of autocratic regimes within a region is controlled for, suggesting that one must look beyond the characteristics of the countries within a region and focus on the ties and linkages between them.

The objective of this article is to contribute to an understanding of the evolution of a population of social economy enterprises faced with the economic crisis, namely by referring to the case of Montreal. We apply a two-step approach. For one, we use an innovative discrete-time survival model that takes spatial heterogeneity into account. In a second step, this model is used to predict the survival of different forms of the social economy, according to various proposed typologies for identifying hybrid organizational forms. It is understood that certain organizational forms (professional social economy) have fared better than others (emerging social economy). Organizations combining several sources of financing and several forms of paid or volunteer work likewise have greater chances of survival.

Co-optation is one of the most important concepts that have been discussed in recent years to explain the persistence of autocratic regimes. Institutions like parties, legislatures, and elections have all been shown to fulfil a co-optation function. However, a broader assessment of co-optation beyond an institutional focus has yet to be undertaken. This article addresses this lacuna and presents a comprehensive concept and operationalisation of co-optation in autocratic regimes. The article argues that co-optation is constituted by the compensation of the regime’s vulnerability to threats posed by powerful societal pressure groups. The article highlights how compensation of vulnerability can be achieved through institutional inclusion or material benefits, and how this has to be tailored to the respective pressure group’s requirements. I collect twenty-six indicators of vulnerability and compensation related to six societal pressure groups and aggregate them into an index of co-optation that reflects the structure of the theoretical concept. The index is evaluated by examining distributions within and across categories of autocratic legislatures, and by testing its effect on autocratic regime breakdown in a set of Cox survival models.

In this study, we investigate the impact of the age of prime ministers and ministers on the stability of governments across 21 democracies. We examine this issue by using Cox survival analysis, leveraging an original dataset and adopting a comparative perspective. The findings of the study document that younger prime ministers face a lower risk of government discretionary termination compared to their older counterparts. This effect does not appear to be statistically significant for cabinet ministers. By shedding light on this uncharted relationship, we contribute to the flourishing literature on youth representation in politics and the established research agenda on the factors affecting the survival in office of democratic governments. We conclude the study by discussing the implications of the findings for democracy and suggesting avenues for future research.

This study examines gender bias in the investigative work of medieval inquisitors, focusing on Albert of Castellario’s trial of the Waldensians in Giaveno, Italy, in 1335. Drawing upon advancements in sociological and criminological literature, we conceptualize an inquisitorial trial as a discretionary information-gathering endeavor contingent upon the inquisitor’s judgment in deciding which leads to pursue. Employing social network analysis and survival methods, we evaluate whether Albert demonstrated gender biases in his investigative decisions, particularly regarding the weight assigned to testimonies from men versus women. Our findings demonstrate that Albert was more inclined to investigate men and prioritize their testimonies, even where similar levels of incriminating evidence were present for both genders. These results highlight the influence of societal attitudes toward gender on inquisitorial practices, on the representativeness of historical records, and on prevailing understandings of heretical groups. Furthermore, this study underscores the broader utility of our methodological framework for addressing related historical inquiries, including the political motivations behind the medieval inquisition.

The Cox duration model serves as the basis for more complex duration models like competing risks, repeated events, and multistate models. These models make a number of assumptions, many of which can be assessed empirically, sometimes for substantive ends. We use Monte Carlo simulations to show the order in which practitioners assess these assumptions can impact the model’s final specification, and ultimately, can produce misleading inferences. We focus on three assumptions regarding model specification decisions: proportional hazards (PH), stratified baseline hazards, and stratum-specific covariate effects. Our results suggest checking the PH assumption before checking for stratum-specific covariate effects tends to produce the correct final specification most frequently. We reexamine a recent study of the timing of GATT/WTO applications to illustrate our points.

Developmental studies of mental disorders based on epidemiological data are often based on cross-sectional retrospective surveys. Under such designs, observations are right-censored, causing underestimation of lifetime prevalences and correlations, and inducing bias in latent trait models on the observations. In this paper we propose a Partial Likelihood (PL) method to estimate unbiased IRT models of lifetime predisposition to develop a certain outcome. A two-step estimation procedure corrects the IRT likelihood of outcome appearance with a function depending on (a) projected outcome frequencies at the end of the risk period, and (b) outcome censoring status at the time of the observation. Simulation results showed that the PL method yielded good recovery of true frequencies and intercepts. Slopes were best estimated when events were sufficiently correlated. When PL is applied to lifetime mental health disorders (assessed in the ESEMeD project surveys), estimated univariate prevalences were, on average, 1.4 times above raw estimates, and 2.06 higher in the case of bivariate prevalences.

Many large-scale standardized tests are intended to measure skills related to ability rather than the rate at which examinees can work. Time limits imposed on these tests make it difficult to distinguish between the effect of low proficiency and the effect of lack of time. This paper proposes a mixture cure-rate model approach to address this issue. Maximum likelihood estimation is proposed for parameter and variance estimation for three cases: when examinee parameters are to be estimated given precalibrated item parameters, when item parameters are to be calibrated given known examinee parameters, and when item parameters are to be estimated without assuming known examinee parameters. Large-sample properties are established for the cases under suitable regularity conditions. Simulation studies suggest that the proposed approach is appropriate for inferences concerning model parameters. In addition, not distinguishing between the effect of low proficiency and the effect of lack of time is shown to have considerable consequences for parameter estimation. A real data example is presented to demonstrate the new model. Choice of survival models for the latent power times is also discussed.

A version of the discrete proportional hazards model is developed for psychometrical applications. In such applications, a primary covariate that influences failure times is a latent variable representing a psychological construct. The Metropolis-Hastings algorithm is studied as a method for performing marginal likelihood inference on the item parameters. The model is illustrated with a real data example that relates the age at which teenagers first experience various substances to the latent ability to avoid the onset of such behaviors.

Classification and Regression Trees (CART), and their successors—bagging and random forests, are statistical learning tools that are receiving increasing attention. However, due to characteristics of censored data collection, standard CART algorithms are not immediately transferable to the context of survival analysis. Questions about the occurrence and timing of events arise throughout psychological and behavioral sciences, especially in longitudinal studies. The prediction power and other key features of tree-based methods are promising in studies where an event occurrence is the outcome of interest. This article reviews existing tree algorithms designed specifically for censored responses as well as recently developed survival ensemble methods, and introduces available computer software. Through simulations and a practical example, merits and limitations of these methods are discussed. Suggestions are provided for practical use.

The analysis of insurance and annuity products issued on multiple lives requires the use of statistical models which account for lifetime dependence. This paper presents a Dirichlet process mixture-based approach that allows to model dependent lifetimes within a group, such as married couples, accounting for individual as well as group-specific covariates. The model is analyzed in a fully Bayesian setting and illustrated to jointly model the lifetime of male–female couples in a portfolio of joint and last survivor annuities of a Canadian life insurer. The inferential approach allows to account for right censoring and left truncation, which are common features of data in survival analysis. The model shows improved in-sample and out-of-sample performance compared to traditional approaches assuming independent lifetimes and offers additional insights into the determinants of the dependence between lifetimes and their impact on joint and last survivor annuity prices.