• Journal of the Korean Mathematical Society
• /
• v.45 no.6
• /
• pp.1753-1767
• /
• 2008

Consider the nonparametric regression model $Y_{ni}\;=\;g(x_{ni})+{\epsilon}_{ni}$ ($1\;{\leq}\;i\;{\leq}\;n$), where g($\cdot$) is an unknown regression function, $x_{ni}$ are known fixed design points, and the correlated errors {${\epsilon}_{ni}$, $1\;{\leq}\;i\;{\leq}\;n$} have the same distribution as {$V_i$, $1\;{\leq}\;i\;{\leq}\;n$}, here $V_t\;=\;{\sum}^{\infty}_{j=-{\infty}}\;{\psi}_je_{t-j}$ with ${\sum}^{\infty}_{j=-{\infty}}\;|{\psi}_j|$ < $\infty$ and {$e_t$} are negatively associated random variables. Under appropriate conditions, we derive a Berry-Esseen type bound for the estimator of g($\cdot$). As corollary, by choice of the weights, the Berry-Esseen type bound can attain O($n^{-1/4}({\log}\;n)^{3/4}$).

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.9 no.1
• /
• pp.99-110
• /
• 2005

This paper suggests an efficient approach for stochastic bicriteria programming problem (SBCPP) with random variables in both the objective functions and in the right-hand side of the constraints. The suggested approach uses the statistical inference through two different techniques: In one of them, the SBCPP is transformed into an equivalent deterministic bicriteria programming problem (DBCPP), then the nonnegative weighted sum approach will be used to transform the bicriteria programming problem into a single objective programming problem, and the other technique, the nonnegative weighted sum approach is used to transform the SBCPP to an equivalent stochastic single objective programming problem, then apply the same procedure to convert stochastic single objective programming problem into its equivalent deterministic single objective programming problem (DSOPP). In both techniques the resulting problem can be solved as a nonlinear programming problem to get the efficient solutions. Finally, a comparison between the two different techniques is discussed, and illustrated example is given to demonstrate the actual application of these techniques.

• Bulletin of the Korean Mathematical Society
• /
• v.48 no.6
• /
• pp.1137-1146
• /
• 2011

Let {$X_i$, $i{\geq}1$} be a sequence of i.i.d. nondegenerate random variables which is in the domain of attraction of the normal law with mean zero and possibly infinite variance. Denote $S_n={\sum}_{i=1}^n\;X_i$, $M_n=max_{1{\leq}i{\leq}n}\;{\mid}S_i{\mid}$ and $V_n^2={\sum}_{i=1}^n\;X_i^2$. Then for d > -1, we showed that under some regularity conditions, $$\lim_{{\varepsilon}{\searrow}0}{\varepsilon}^2^{d+1}\sum_{n=1}^{\infty}\frac{(loglogn)^d}{nlogn}I\{M_n/V_n{\geq}\sqrt{2loglogn}({\varepsilon}+{\alpha}_n)\}=\frac{2}{\sqrt{\pi}(1+d)}{\Gamma}(d+3/2)\sum_{k=0}^{\infty}\frac{(-1)^k}{(2k+1)^{2d+2}}\;a.s.$$ holds in this paper, where If g denotes the indicator function.

• Journal of the Korean Mathematical Society
• /
• v.43 no.3
• /
• pp.529-538
• /
• 2006

In this paper we derive the central limit theorem for ${\sum}^n_{i=l}\;a_{ni}{\xi}_{i},\;where\;\{a_{ni},\;1\;{\le}\;i\;{\le}n\}$ is a triangular array of non-negative numbers such that $sup_n{\sum}^n_{i=l}\;a^2_{ni}\;<\;{\infty},\;max_{1{\le}i{\le}n\;a_{ni}{\to}\;0\;as\;n{\to}{\infty}\;and\;{\xi}'_{i}s$ are a linearly positive quadrant dependent sequence. We also apply this result to consider a central limit theorem for a partial sum of a generalized linear process of the form $X_n\;=\;{\sum}^{\infty}_{j=-{\infty}}a_{k+j}{\xi}_{j}$.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.21 no.9
• /
• pp.2433-2443
• /
• 1996

In this paper, a new technique is proposed for obtaining the error probabilities of the VSB(vestigial sideband modulation) signal in the presence of the cochannel interference and frequency-selective fading channel. For the receivers, a suboptimal matched filter receiver and the MLSE(maximum likelihood sequence estimation) receiver, which is known to be optimal on the fading channel, are considered. First, for the matched filter receiver, the distributions of the random variables, which determine the SER(symbol error rate) are obtained by decomposing the multi-path fading channel into Rayleigh distributed main path and Gaussian distributed remained path channels. the random variables mean the energy of the main path and subpath respecitively, and SER can be calculated from the distribution of them. Next, for the case of the MLSE receover, it is found that the random variables are expressed as a function of integrals. In order to obtain the distribution for the random variables, we expanded each element of integrals with the KL(Karhunen-Loeve) transformation. And it is derived that the distributions for the transformed random variables are given by a sum of chi-square distributions. Finally, we calculated the error rate derived formula on the two-ray fading channel, which is one of widely used models for the frequency-selective fading channel. From the numerical results, it is found that for the matched filer receiver, performance degradation is significant, while the performance degradation at the MLSE receiver is insignificant on the frequency-selective fading channel. However, in case of cochannel interference environment, the error rateis found to increase significantly both at the matched filter and at the MLSE receiver.

• Honam Mathematical Journal
• /
• v.24 no.1
• /
• pp.121-130
• /
• 2002

In this paper we prove a functional central limit theorem for a field $\{X_{\underline{j}}:{\underline{j}}{\in}Z_+^d\}$ of nonstationary associated random variables with $EX{\underline{j}}=0,\;E{\mid}X_{\underline{j}}{\mid}^{r+{\delta}}<{\infty}$ for some $r>2,\;{\delta}>0$and $u(n)=O(n^{-{\nu}})$ for some ${\nu}>0$, where $u(n):=sup_{{\underline{i}}{\in}Z_+^d{\underline{j}}:{\mid}{\underline{j}}-{\underline{i}}{\mid}{\geq}n}{\sum}cov(X_{\underline{i}},\;X_{\underline{j}}),\;{\mid}{\underline{x}}{\mid}=max({\mid}x_1{\mid},{\cdots},{\mid}x_d{\mid})\;for\;{\underline{x}}{\in}{\mathbb{R}}^d$. Our investigation implies and analogous result in the case associated random measure.

• Communications of the Korean Mathematical Society
• /
• v.26 no.1
• /
• pp.151-161
• /
• 2011

Let {$X_n$, $n{\geq}1$} be a sequence of asymptotically almost negatively associated random variables and $S_n=\sum^n_{i=1}X_i$. In the paper, we get the precise results of H$\acute{a}$jek-R$\acute{e}$nyi type inequalities for the partial sums of asymptotically almost negatively associated sequence, which generalize and improve the results of Theorem 2.4-Theorem 2.6 in Ko et al. ([4]). In addition, the large deviation of $S_n$ for sequence of asymptotically almost negatively associated random variables is studied. At last, the Marcinkiewicz type strong law of large numbers is given.

• Communications for Statistical Applications and Methods
• /
• v.21 no.3
• /
• pp.245-251
• /
• 2014

Two exponential inequalities are established for a wide class of general weakly dependent sequences of random variables, called ${\psi}$-weakly dependent process which unify weak dependence conditions such as mixing, association, Gaussian sequences and Bernoulli shifts. The ${\psi}$-weakly dependent process includes, for examples, stationary ARMA processes, bilinear processes, and threshold autoregressive processes, and includes essentially all classes of weakly dependent stationary processes of interest in statistics under natural conditions on the process parameters. The two exponential inequalities are established on more general conditions than some existing ones, and are proven in simpler ways.

• Journal of applied mathematics & informatics
• /
• v.30 no.1_2
• /
• pp.327-336
• /
• 2012

Let {$X_{ni}$, $i{\geq}1$, $n{\geq}1$} be an array of rowwise and pairwise negatively quadrant dependent random variables with mean zero, {$a_{ni}$, $i{\geq}1$, $n{\geq}1$} an array of weights and {$b_n$, $n{\geq}1$} an increasing sequence of positive integers. In this paper we consider some results concerning complete convergence of ${\sum}_{i=1}^{bn}a_{ni}X_{ni}$.

• Communications for Statistical Applications and Methods
• /
• v.9 no.3
• /
• pp.765-774
• /
• 2002

Suppose one is given a vector X of a finite set of quantities $X_i$ which are independent Poisson random variables. A null hypothesis $H_0$ about E(X) is to be tested against an alternative hypothesis $H_1$. A quantity $\sum\limits_{i}w_ix_i$ is to be computed and used for the test. The optimal values of $W_i$ are calculated for three cases: (1) signal to noise ratio is used in the test, (2) normal approximations with unequal variances to the Poisson distributions are used in the test, and (3) the Poisson distribution itself is used. The above three cases are considered to the situations that are without background noise and with background noise. A comparison is made of the optimal values of $W_i$ in the three cases for both situations.