• Journal of applied mathematics & informatics
• /
• v.18 no.1_2
• /
• pp.247-259
• /
• 2005

Necessary and sufficient conditions, under which there exists (at least) a sequence of vectors of real numbers for which the distribution function (d.f.) of any vector of extreme order statistics converges to a non-degenerate limit, are derived. The interesting thing is that these conditions solely depend on the univariate marginals. Moreover, the limit splits into the product of the limit univariate marginals if all the bivariate marginals of the trivariate d.f., from which the sample is drawn, is of negative quadrant dependent random variables (r.v.'s). Finally, all these results are stated for the multivariate extremes with arbitrary dimensions.

• Communications for Statistical Applications and Methods
• /
• v.20 no.6
• /
• pp.475-480
• /
• 2013

The surplus process in a risk model is stochastically analyzed. We obtain the characteristic function of the level of the surplus at a finite time, by establishing and solving an integro-differential equation for the distribution function of the surplus. The characteristic function of the stationary distribution of the surplus is also obtained by assuming that an investment of the surplus is made to other business when the surplus reaches a sufficient level. As a consequence, we obtain the first and second moments of the surplus both at a finite time and in an infinite horizon (in the long-run).

• Journal of the Korean Data and Information Science Society
• /
• v.19 no.4
• /
• pp.1173-1181
• /
• 2008

In this paper, when the parameter of interest is the shape parameter in Pareto distribution, we develop likelihood based inference for this parameter. Specially, we develop signed log-likelihood ratio statistic and the modified signed log-likelihood ratio statistic for the shape parameter. It is well-known that as sample size grows, the modified signed log-likelihood ratio statistic converges to standard normal distribution faster than the signed log-likelihood ratio statistic. But the computation of the modified signed log-likelihood statistic is hard or even impossible when the sufficient statistics and the ancillary statistics are not clear. In this case, one can consider an approximation to the modified signed log-likelihood statistic. Specially, when the parameter of interest is informationally orthogonal to the nuisance parameters, we propose the approximate modified signed log-likelihood statistic. Through simulation, we investigate the performances of the proposed statistics with the signed log-likelihood statistic.

• Bulletin of the Korean Mathematical Society
• /
• v.59 no.4
• /
• pp.979-991
• /
• 2022

A special class of exponential dispersion models is the class of Tweedie distributions. This class is very significant in statistical modeling as it includes a number of familiar distributions such as Gaussian, Gamma and compound Poisson. A Tweedie distribution has a power parameter p, a mean m and a dispersion parameter 𝜙. The value of the power parameter lies in identifying the corresponding distribution of the Tweedie family. The basic objective of this research work resides in investigating the existence of the implicit estimator of the power parameter of the Tweedie distribution. A necessary and sufficient condition on the mean parameter m, suggesting that the implicit estimator of the power parameter p exists, was established and we provided some asymptotic properties of this estimator.

• Nonlinear Functional Analysis and Applications
• /
• v.27 no.3
• /
• pp.533-551
• /
• 2022

In this paper, we introduce several types 𝛼-𝜓 interpolative proximal contractions and provide some sufficient conditions to prove the existence of best proximity points for these contractions in metric spaces. In the case of proximal contraction of the first kind, these metric spaces are not necessarily complete. Meanwhile, some new results can derive from our results. Finally, some examples are provided to show the validity of our results.

• Communications for Statistical Applications and Methods
• /
• v.23 no.3
• /
• pp.259-268
• /
• 2016

High-dimensional survival data with large numbers of predictors has become more common. The analysis of such data can be facilitated if the dimensions of predictors are adequately reduced. Recent studies show that a method called sliced inverse regression (SIR) is an effective dimension reduction tool in high-dimensional survival regression. However, it faces incapability in implementation due to a double categorization procedure. This problem can be overcome in the right-censoring type by transforming the observed survival time and censoring status into a single variable. This provides more flexibility in the categorization, so the applicability of SIR can be enhanced. Numerical studies show that the proposed transforming approach is equally good to (or even better) than the usual SIR application in both balanced and highly-unbalanced censoring status. The real data example also confirms its practical usefulness, so the proposed approach should be an effective and valuable addition to usual statistical practitioners.

• Nutrition Research and Practice
• /
• v.11 no.2
• /
• pp.130-138
• /
• 2017

BACKGROUND/OBJECTIVES: Low consumption of fruit and vegetable is frequently viewed as an important contributor to obesity risk. With increasing childhood obesity and relatively low fruit and vegetable consumption among Thai children, there is a need to identify the determinants of the intake to promote fruit and vegetable consumption effectively. SUBJECTS/METHODS: This cross-sectional study was conducted at two conveniently selected primary schools in Nakhon Pathom. A total of 609 students (grade 4-6) completed questionnaires on personal and environmental factors. Adequate fruit and vegetable intakes were defined as a minimum of three servings of fruit or vegetable daily, and adequate total intake as at least 6 serves of fruit and vegetable daily. Data were analyzed using descriptive statistics, the chi-square test, and multiple logistic regression. RESULTS: The proportion of children with a sufficient fruit and/or vegetable intakes was low. Covariates of child's personal and environmental factors showed significant associations with sufficient intakes of fruit and/or vegetable (P < 0.05). Logistic regression analyses showed that the following factors were positively related to sufficient intake of vegetable; lower grade, a positive attitude toward vegetable, and fruit availability at home; and that greater maternal education, a positive child's attitude toward vegetable, and fruit availability at home were significantly associated with sufficient consumption of fruits and total fruit and vegetable intake. CONCLUSIONS: The present study showed that personal factors like attitude toward vegetables and socio-environmental factors, such as, greater availability of fruits were significantly associated with sufficient fruit and vegetable consumption. The importance of environmental and personal factors to successful nutrition highlights the importance of involving parents and schools.

• Korea journal of population studies
• /
• v.11 no.1
• /
• pp.58-75
• /
• 1988

1.Objectives of the Study It is a well known fact that a prompt and reliable data on demographic information is essential in a proper planning and evaluation of any program of national or community level. Especially vital statistics are an important demographic component among demographic information. Realizing the importance of vital statistics, the government has made some efforts for years to improve the vital registration system which has a close relationship with the production of vital statistics. However, it is still observed that there are some limitations in utilizing vital registration data due to considerable amount of vital events which are never registered and registered but not in time or inaccurately, even though vital registration system in Korea has sound legal basis. In this connection, the objectives of the study is as follows :(1) To examine some problems of the vital registration system in various aspects, (2) To make improvement programme of continuous Demographic Survey as a supplementary source of vital statistics, and (3) To find out some alternatives for making it possible to produce and utilize the reliable vital statistics by developing analytical methodologies on that. 2. Current Situation of Vital Registration System All the vital events, i.e. births, deaths, marriages and divorces, are to be registered in time under the Civil Registration Law, Statistics Law and Regulation on Vital Statstics as a duty of people. Some recent tendencies in each of recent registration are summarized as below: (1) The completeness of vital registration .Out of all births which are occurred during a year, around 75% of those compared to the estimates are registered in the year of occurrence. .In case of death registration, the percentage of registration in the year of occurrene has been gradually increased from 86.2% in the year of 1980, but it is still below the level of 90% compared to the estimates. .The percentage of registration for marriages and divorces in the year of occurrence out of total registered numbers was revealed to be 69% and 73% respectively in 1985. (2) Continuous Demographic Survey .It is a kind of sample survey for the purpose of producing reliable vital statistics which could not be provided by the vital registration. .It covers about 17, 000 sample households at national level and important information for vital events are collected in every month by 323 expertized enumerators who are regular staff of the government. .Although the result of the survey seems to be more reliable than of vital registration, the reliability of the data is still bellow the acceptable level if compared with relevant information from other sources such as population census or special surveys. 3. Problems of Vital Registration System There are four major obstacles in improving vital registration system in Korea; (1) In general, policy priority is not given on any programme of improving vital registration system. It is, therefore, very difficult to formulate comprehensive programme through having cooperation from related authorities and sufficient financial assistance. (2) In all the laws related and system itself, there is substantial degree of overlap and irrationality. Registration of each vital event is maintained according to several laws and regulation such as Civil Registration Law, Statistics Law, Resident Registration Law and Regulation on Vital Statistics. However they are mutually overlapped and overall supervision can not be done systematically due to lack of co-operation among the authorities concerned. (3) The administration of vital registration system seems to be working inefficiently, because of most of civil servants who are in charge of vital registration are lacking of conception on vital statistics and also there is a certain extent of regidity in handling the works. Therefore, they are doing their jobs in a passive way. (4) A substantial proportion of vital events occurred is not registered within the legal time limit (i.e. within one month after the occurrence in case of birth and death) or not registered forever. Some of social customs and superstitution seem to be the potential causes especially in case of births and deaths. 4. Recommendations for the Improvement of Vital Statistics (1) Reporting systems such as civil registration, vital statistics and resident registration should be integrated under the single law. Also, administrative supervision, personnel and budget with regard to the registration system should be under the control of a single ministry. (2) It is necessary to simplify the procedures and methods of reporting vital events, i.e., reducing number of sheets of the form, making corrections easily, reducing registration items, etc. (3) Continuous Demographic Survey as a supplementary source of vital registration should be improved and special ad-hoc surveys should be conducted wth regular interval. (4) In-depth analysis should be done using various sources of data on vital statistics. 5. Concluding Remarks From this study, we can notice that temporary campaign and motivation programs are not sufficient to improve the quality of vital statistics. Strong intentions and continuous efforts of the government are needed for the improvement of the vital registration system. Furthermore, most of the data collected through the registration are not properly analyzed and utilized, partly due to the lack of appreciation among high-level governmental officials of the need for vital statistics. It is, therefore, requested that long-term improvement programs of vital statistics be implemented with policy priority and continuous efforts be given to this purpose as a long-term goal of development in Korea.

• Communications for Statistical Applications and Methods
• /
• v.31 no.2
• /
• pp.213-234
• /
• 2024

In recent decades, increasing research attention has been directed toward predicting the price of stocks in financial markets using deep learning methods. For instance, recurrent neural network (RNN) is known to be competitive for datasets with time-series data. Long short term memory (LSTM) further improves RNN by providing an alternative approach to the gradient loss problem. LSTM has its own advantage in predictive accuracy by retaining memory for a longer time. In this paper, we combine both supervised and unsupervised dimension reduction methods with LSTM to enhance the forecasting performance and refer to this as a dimension reduction based LSTM (DR-LSTM) approach. For a supervised dimension reduction method, we use methods such as sliced inverse regression (SIR), sparse SIR, and kernel SIR. Furthermore, principal component analysis (PCA), sparse PCA, and kernel PCA are used as unsupervised dimension reduction methods. Using datasets of real stock market index (S&P 500, STOXX Europe 600, and KOSPI), we present a comparative study on predictive accuracy between six DR-LSTM methods and time series modeling.

• Communications for Statistical Applications and Methods
• /
• v.24 no.5
• /
• pp.533-541
• /
• 2017

Sufficient dimension reduction (SDR) replaces original p-dimensional predictors to a lower-dimensional linearly transformed predictor. The sliced inverse regression (SIR) has the longest and most popular history of SDR methodologies. The critical weakness of SIR is its known sensitive to the numbers of slices. Recently, a fused sliced inverse regression is developed to overcome this deficit, which combines SIR kernel matrices constructed from various choices of the number of slices. In this paper, the fused sliced inverse regression and SIR are compared to show that the former has a practical advantage in survival regression over the latter. Numerical studies confirm this and real data example is presented.