• The Korean Journal of Applied Statistics
• /
• v.34 no.5
• /
• pp.761-772
• /
• 2021

Simulation results for the comparison of estimators of interest are usually reported in tables or plots. However, if the simulations are conducted under various conditions for many estimators, the comparison can be difficult to be made with tables or plots. Furthermore, for algorithms that take a long time to run, the number of iterations of the simulation is costly to to be increased. The analysis of simulation results using regression models allows us to compare the estimators more systematically and effectively. Since variances in performance measures may vary depending on the simulation conditions and estimators, the heteroscedasticity of the error term should be allowed in the regression model. And multiple comparisons should be made because multiple estimators should be compared simultaneously. We introduce background theories of heteroscedasticity and multiple comparisons in the context of analyzing simulation results. We also present a concrete example.

• Communications for Statistical Applications and Methods
• /
• v.27 no.6
• /
• pp.649-673
• /
• 2020

This paper makes a theoretical contribution by providing clear and detailed derivation of economic agents' decision problems including elastic labor supply in Gertler's overlapping generation (OLG) model. We apply the model to the Korean economy by calibration based on Korean economic data. It also analyzes the impact of current social issues such as aging and extension of retirement age, on the Korean economy in a long-run equilibrium. Subsequently, we also discuss the implications of the analysis. Aging has prolonged the period of retirement; therefore, population structure changes by the increase in the proportion of retirees, the total consumption-to-GDP ratio decreases, and capital stock increases due to reduced propensity to consume out of wealth in preparation for an individual's retirement life. The implementation of retirement age extension increases the proportion of retirees relatively less and alleviates fluctuations in labor supply and the share of financial assets for both economic agents. However, the decrements in consumption-to-GDP ratio is larger than before, and this leads to a larger rise in the capital stock compared to when there is only an aging effect.

• Communications for Statistical Applications and Methods
• /
• v.29 no.1
• /
• pp.65-83
• /
• 2022

Although various statistical methods have been developed to map time-dependent genetic factors, most identified genetic variants can explain only a small portion of the estimated genetic variation in longitudinal traits. Gene-gene and gene-time/environment interactions are known to be important putative sources of the missing heritability. However, mapping epistatic gene-gene interactions is extremely difficult due to the very large parameter spaces for models containing such interactions. In this paper, we develop a Gaussian process (GP) based nonparametric Bayesian variable selection method for longitudinal data. It maps multiple genetic markers without restricting to pairwise interactions. Rather than modeling each main and interaction term explicitly, the GP model measures the importance of each marker, regardless of whether it is mostly due to a main effect or some interaction effect(s), via an unspecified function. To improve the flexibility of the GP model, we propose a novel grid-based method for the within-subject dependence structure. The proposed method can accurately approximate complex covariance structures. The dimension of the covariance matrix depends only on the number of fixed grid points although each subject may have different numbers of measurements at different time points. The deviance information criterion (DIC) and the Bayesian predictive information criterion (BPIC) are proposed for selecting an optimal number of grid points. To efficiently draw posterior samples, we combine a hybrid Monte Carlo method with a partially collapsed Gibbs (PCG) sampler. We apply the proposed GP model to a mouse dataset on age-related body weight.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.17 no.4
• /
• pp.183-189
• /
• 2024

In order to effectively predict time series data, this study proposed a hybrid prediction model that decomposes the data into trend, seasonality, and residual components using Seasonal-Trend Decomposition on Loess, and then applies ARIMA to the trend component, Fourier Series Regression to the seasonality component, and XGBoost to the remaining components. In addition, performance comparison experiments including ARIMA, XGBoost, LSTM, EMD-ARIMA, and CEEMDAN-LSTM models were conducted to evaluate the prediction performance of each model. The experimental results show that the proposed hybrid model outperforms the existing single models with the best performance indicator values in MAPE(3.8%), MAAPE(3.5%), and RMSE(0.35) metrics.

• Genomics & Informatics
• /
• v.19 no.4
• /
• pp.36.1-36.11
• /
• 2021

Predicting individual traits and diseases from genetic variants is critical to fulfilling the promise of personalized medicine. The genetic variants from genome-wide association studies (GWAS), including variants well below GWAS significance, can be aggregated into highly significant predictions across a wide range of complex traits and diseases. The recent arrival of large-sample public biobanks enables highly accurate polygenic predictions based on genetic variants across the whole genome. Various statistical methodologies and diverse computational tools have been introduced and developed to computed the polygenic risk score (PRS) more accurately. However, many researchers utilize PRS tools without a thorough understanding of the underlying model and how to specify the parameters for the best performance. It is advantageous to study the statistical models implemented in computational tools for PRS estimation and the formulas of parameters to be specified. Here, we review a variety of recent statistical methodologies and computational tools for PRS computation.

• Journal of Digital Convergence
• /
• v.10 no.9
• /
• pp.111-122
• /
• 2012

In this study, we consider the integration of cognitive components and emotion to account for communication behaviors and activism on a consumer advocacy website. The challenge of integrating situational theory and anger activism model was empirically explored utilizing an online survey with the members of the virtual community, which was designed to raise issues and to protest against the product defects of a product. Our findings indicated that along with the cognitive perception in the situational theory, anger as a negative emotion was the most significant predictor strongly associated with communication behaviors and activism on the organization. More interestingly, the model that integrates anger with cognitive components significantly improves its explanatory power compared with one including only cognitive components as explanatory variables.

• Communications for Statistical Applications and Methods
• /
• v.15 no.1
• /
• pp.27-41
• /
• 2008

A graphical method of checking the adequacy of a generalized linear model is proposed. The graph helps to assess the assumption that the link function of mean can be expressed as a linear combination of explanatory variables in the generalized linear model. For the graph the boosting technique is applied to estimate nonparametrically the relationship between the link function of the mean and the explanatory variables, though any other nonparametric regression methods can be applied. Through simulation studies with normal and binary data, the effectiveness of the graph is demonstrated. And we list some limitations and technical details of the graph.

• The Korean Journal of Applied Statistics
• /
• v.32 no.5
• /
• pp.763-782
• /
• 2019

This paper proposes a probabilistic document ranking model incorporating term dependencies. Document ranking is a fundamental information retrieval task. The task is to sort documents in a collection according to the relevance to the user query (Qin et al., Information Retrieval Journal, 13, 346-374, 2010). A probabilistic model is a model for computing the conditional probability of the relevance of each document given query. Most of the widely used models assume the term independence because it is challenging to compute the joint probabilities of multiple terms. Words in natural language texts are obviously highly correlated. In this paper, we assume a multinomial distribution model to calculate the relevance probability of a document by considering the dependency structure of words, and propose an information retrieval model to rank a document by estimating the probability with the maximum entropy method. The results of the ranking simulation experiment in various multinomial situations show better retrieval results than a model that assumes the independence of words. The results of document ranking experiments using real-world datasets LETOR OHSUMED also show better retrieval results.

• The Korean Journal of Applied Statistics
• /
• v.26 no.3
• /
• pp.531-547
• /
• 2013

Multiple life models are useful in multiple life insurance and multiple life annuities when the payment times of benets in these insurance products are contingent on the future life times of at least two people. A reverse mortgage is an annuity whose monthly payments terminate at the death time of the last survivor; however, actuaries have used female life table to calculate monthly payments of a reverse mortgage. This approach may overestimate monthly payments. This paper suggests a last-survivor life table rather than a female life table to avoid the overestimation of monthly payments. Next, this paper derives the distribution of the future life time of last survivor, and calculates the expected life times of male, female and last survivor. This paper calculates principal limits and monthly payments in cases of male life table, female life table and last-survivor life table, respectively. Some numerical examples are discussed.

• Journal of the Korean Data and Information Science Society
• /
• v.24 no.4
• /
• pp.723-736
• /
• 2013

The importance of lapse rate is highly increasing due to the introduction of Cash Flow Pricing system, non-refund-of-reserve insurance policy, and IFRS (International Financial Reporting System) to the Korean insurance market. Researches on lapse rate have mainly focused on simple data analysis and regression analysis, etc. However, lapse rate can be analyzed by survival analysis and can be well explained in terms of several covariates with Cox proportional hazard model. Guaranteed minimum benefits embedded in variable annuities require more elegant statistical analysis of lapse rate. Hence, this paper analyzes data of policyholders with variable annuities by using Cox proportional hazard model. The key variables of policy holder that influences the lapse rate are payment method, premium, lapse insured to term insured, reserve-GMXB ratio, and age.