The estimation of average treatment effects based on observational data is extremely important in practice and has been studied by generations statisticians under different frameworks. Existing globally efficient estimators require non-parametric a propensity score function, an outcome regression function or both, but their performance can be poor practical sample sizes. Without explicitly estimating either functions, we consider wide class calibration weights constructed to attain exact...

In recent years, general risk measures play an important role in management both finance and insurance industry. As a consequence, there is increasing number of research on optimal reinsurance decision problems using beyond the classical expected utility framework. this paper, we first show that stop-loss contract under law-invariant convex via new simple geometric argument. A similar approach then used to tackle same problem Value at Risk Conditional Tail Expectation; it interesting note...

In this paper, we study the time consistent strategies in mean-variance portfolio selection with short-selling prohibition both discrete and continuous settings. Recently, [T. Björk, A. Murgoci, X. Y. Zhou, Math. Finance, 24 (2014), pp. 1--24] considered problem state dependent risk aversion sense that is inversely proportional to current wealth, they showed control linear wealth. Considering counterpart of their equilibrium framework, corresponding "optimal" wealth process can take negative...

In this paper, we consider an $N$-player interacting strategic game in the presence of a (endogenous) dominating player, who gives direct influence on individual agents, through its impact their control sense Stackelberg game, and then whole community. Each agent is subject to delay effect collecting information, specifically at time, from player. The size his completely known by agent, while others, including plays as hidden random variable coming common fixed distribution. By invoking...

The objective of this paper is to provide an equivalent the theory developed in P.~Cardaliaguet, F.~Delarue, J.M.~Lasry, P.L.~Lions \cite{CDLL}, following approach control on Hilbert spaces introduced by authors \cite{BGY-2}. We include common noise paper, so alternative now complete. Since we consider a problem, our applies only Mean field and not mean games. assumptions are adapted guarantee unique optimal control, they insure that cost functional strictly convex coercive.

In this article, we provide a global-in-time analysis of mean field type control problems on Rn with generic cost functions allowing quadratic growth by novel ``lifting'' approach which is not the same as traditional lifting. We resolve problem in subspace L2 random variables, it can be regarded tangent space attached at initial probability measure. The linked to global solvability Hilbert-space-valued forward-backward stochastic differential equation (FBSDE). rely Jacobian flow solution...

Dear editor, The presence of the inflated zeros in single cell RNA-seq still represents a challenge. Imputation can be performed but it is not commonly used real applications because their uncertain benefits and lack in-depth benchmark for various downstream analyses. Here, we two tasks: an framework was developed to compare imputation algorithms; second, improved algorithm, afMF, developed. Our results indicated that matrix-theory-based algorithms such as afMF had great stable performance...

In this article, we consider a linear-quadratic mean field game between leader (dominating player) and group of followers (agents) under the Stackelberg setting as proposed in [A. Bensoussan, M. Chau, S. Yam, Appl. Math. Optim., 74 (2016), pp. 91-128], so that evolution each individual follower is now also subjected to delay effects from both his/her state control variables, well those leader. The overall solved by tackling three subproblems hierarchically. Their resolution corresponds...

We propose a model to assess the value of distributor in dynamic stochastic cooperative advertising supply chain which manufacturer wholesales its product who turn sells it retailer. Moreover and importantly, also intermediates pricing decisions between For resulting three‐player hierarchical game formulation chain, we characterize feedback Stackelberg equilibrium terms system coupled algebraic equations show admit unique solution. find that added by depends critically on nature demand...

In the presence of a missing response, reweighting complete case subsample by inverse nonmissing probability is both intuitive and easy to implement. When population totals some auxiliary variables are known when inclusion probabilities design, survey statisticians have developed calibration methods for improving efficiencies weighting estimators can be applied data analysis. Model-based has been proposed in sampling literature, where multidimensional first summarized into predictor function...

Abstract In this article, we consider the problem of computing expected discounted value a death benefit, e.g. in Gerber et al. (2012, 2013), regime-switching economy. Contrary to their proposed density approach, adopt Laplace transform contingent options. By alternative closed-form expressions for transforms values various options, such as call/put lookback barrier dynamic fund protection and withdrawal benefits, have been obtained. The each option can then be recovered by numerical...

This paper provides a test for the equality of multiple Sharpe ratios. First we extend multivariate ratio statistic Leung and Wong case when excess returns are independently identically distributed. We then provide that holds under much more general assumption stationary ergodic, making use generalized method moments heteroscedasticity autocorrelation consistent estimation covariance matrixes. repeat Wong's testing ratios 18 iShares using our new tests conclude hypothesis cannot be rejected...