The credibility estimator under the generalized
weighted premium principle were discussed. The results were also
extended to the versions of multitude contracts. By transforming the
probability distribution, the inhomogeneous and homogeneous
credibility estimators in the multitude models were derived, and
some statistical properties of those estimators were discussed.
Furthermore, the structure parameters in credibility factor were
estimated by bootstrap techniques. Finally, the simulation study is
presented and shows that the inhomogeneous estimator are good enough
to use in practice.
Dynamic guarantees in equity-indexed
annuities provide a floor level of protection over the investment
period. This article considers the price of the dynamic guaranteed
funds with a stochastic barrier under stochastic interest rate
environment. The explicit pricing formulas for the dynamic
guaranteed funds can be obtained when the barrier is set to be a
function of zero-coupon bond.
In this paper, we focus on the variable
selection for the linear EV model with longitudinal data when some
covariates are measured with errors. A new bias-corrected variable
selection procedure is proposed based on the combination of the
quadratic inference functions and shrinkage estimations. With
appropriate selection of the tuning parameters, we establish the
consistency and asymptotic normality of the resulting estimators.
Extensive Monte Carlo simulation studies are conducted to examine
the finite sample performance of the proposed variable selection
procedures.
This paper investigates an optimal portfolio
selection problem in a market with mispricing and stochastic
volatility. The investor's objective is to maximize the expected
power utility of the terminal wealth, and the financial market
consists of one risk-free asset, one risky asset representing the
market index, and a pair of stocks whose prices are mispriced.
Meanwhile, the volatilities of the market index and system risk are
described by Heston stochastic volatility model. Without/with
limited short selling constraints, the closed-form expressions of
the optimal strategies and the optimal value functions are derived
by the dynamic programming approach and the Lagrange multiple
method. Moreover, economic implications and numerical examples are
provided to illustrate that how the investment horizon and
mispricing error affect the optimal strategies.
In this paper, we will further study the
complete convergence of pairwise NQD random sequences. Some results
for pairwise NQD random sequences are obtained under some simple and
weak conditions. The results obtained not only extend and generalize
the results of Liu (2004) and the corresponding result of Gan and
Chen (2008), but also improve them.
In this study, we consider the pricing
problem of convert bond with default risk under a reduced form
model. We suppose that the default intensity follows the Vasicek
model, and obtain a closed form pricing formula of convert bond by
martingale method. Moreover, we provide a numerical analysis to
demonstrate the sensitivity of a default convert bond value to
changes in the model's parameters, and show that the default risk of
convert bond issuer will reduce the convert bond value.
Based on the estimates of bivariate hazard
functions, for right censored data, we give an estimator of
association parameter in Clayton model in the paper. The consistency
and asymptotic distribution are derived for the estimator.
Simulation studies show that this procedure is effective.
Compositional data is a kind of complex
qualitative data, especially its prediction research plays an
important role in management science and economics. The technology
of combination forecast is widely used in the forecast, which makes
full use of the single forecast model and makes progress on the
prediction accuracy. In this paper, the combination forecast method
is applied to the prediction of compositional data analysis, based
on some basic properties of the compositional data. We can see from
the example that using the combination forecast can get a better
prediction result.
In this paper, the surplus of an
insurance company is governed by a jump-diffusion process, and it
can be invested in a financial market with one risk-free asset and
$N$ risky assets. The parameters of surplus process and the asset
price processes depend on the regime of the financial market, which
is modeled by an observable finite-state continuous-time Markov
chain. To maximize the terminal utility, we focus on finding optimal
investment strategy and solve it by using the HJB equation. Explicit
expression for optimal strategy and the corresponding objective
function are presented when the company has an exponential utility
function, some interesting economic interpretations are involved.
Some known results of Browne (1995) and Yang and Zhang (2005) are
extended.