We propose a Bayesian dynamic interbank network model with probit links that simultaneously incorporates three underlying mechanisms for interbank trading: dynamic activity indices for overall market confidence, bank-specific latent variables for individual banks' fitness as borrowers or lenders, and pairwise covariates characterizing past trading relationships. Correspondingly, a computationally efficient Gibbs sampling algorithm is developed for sampling model parameters from posterior distributions that handles constrained parameters to achieve identification in a model with latent components. By applying our Bayesian approach to the e-MID interbank market, we obtain empirically useful estimates of latent parameters that not only forecast trading linkages, but also provide pricing information about the interest rates banks charge each other. New model-based proxies of network topology change and relationship lending are proposed to investigate their impact on relevant economic variables and the price of liquidity. The model is also extended to allow logit links as a flexible alternative.
For the remaining lifetimes of an insured couple, dependence arises from not only the shared environment and lifestyle but also the broken-heart effect well-documented in demographic and biological studies. However, much of the existing literature lacks an effective way to quantify both sources of dependence. The traditional copula models capture the statistical dependence between spouses but fail to explicitly address the broken-heart effect, whereas the semi-Markov chain models incorporate the broken-heart effect without considering the dependence during marriage. In this paper, we propose a new approach to integrate the broken-heart effect through the relevation transform and proportional mortality rates. The survival function of lifetimes is derived for an insured couple and its analytical properties are discussed also. This framework enables actuaries to more accurately assess insurance risks associated with couple lifetimes. The advantages of this approach are substantiated through probabilistic analysis, simulation, and empirical study based on a real-world data application.
In this article, we analyze the cash flows associated with a homogeneous portfolio of Long-Term Care (LTC) insurance contracts, taking into account key sources of risk that may affect the profitability of such products. LTC policies generate long-term positive impacts, both socially and economically, and insurers may actively support the establishment of a fair and sustainable care system. To this aim, managing the impact of the possible risks on the profit flows plays a central role, from the insurer's point of view. We present a forward-looking actuarial analysis of the time-evolving profitability of the portfolio and analyze the impact of systematic risk resulting from inaccuracies in the estimation of claim frequencies, and explore the sensitivity of financial outcomes to different technical assumptions. To broaden our investigation, we construct a risk-adjusted constant relative risk aversion (CRRA) utility function that enables integrating stochastic variability in claim events hypothesis with the insurer's personal risk tolerance. We introduce a dynamic risk score that may reflect both contract-specific risk factors as well as wider strategic considerations, proposing some numerical evidence.
ABSTRACT In this article, we introduce a new measure for quantifying the joint variational intensity between two assets, termed the realized joint Laplace transform of volatilities. Taking into account jumps and microstructure noise, we first employ the pre‐averaging method to mitigate the impact of noise. Subsequently, we construct an estimator based on the cosine function of the pre‐averaged increments. The proposed estimator is robust against both jump and microstructure noise; under suitable conditions, we establish its consistency and asymptotic normality. The estimator achieves the optimal convergence rate for estimating integrated volatility functionals in the presence of microstructure noise. Furthermore, based on the established results, we extend our theoretical analysis to independent tests for the volatility processes of different assets. We conduct extensive simulation studies to assess the finite sample performance of our estimator and apply the measure to a real high‐frequency dataset.
