• The Korean Journal of Applied Statistics
• /
• v.33 no.2
• /
• pp.123-136
• /
• 2020

It is common to encounter correlated multiple outcomes measured on the same subject in various research fields. In developmental toxicity studies, presence of malformed pups and fetal weight are measured on the pregnant dams exposed to different levels of a toxic substance. Joint analysis of such two outcomes can result in more efficient inferences than separate models for each outcome. Most methods for joint modeling assume a normal distribution as random effects. However, in developmental toxicity studies, the response distributions may change irregularly in location and shape as the level of toxic substance changes, which may not be captured by a normal random effects model. Motivated by applications in developmental toxicity studies, we propose a Bayesian joint model for binary and continuous outcomes. In our model, we incorporate a skewed logit model for the binary outcome to allow the response distributions to have flexibly in both symmetric and asymmetric shapes on the toxic levels. We apply our proposed method to data from a developmental toxicity study of diethylhexyl phthalate.

• KIISE Transactions on Computing Practices
• /
• v.23 no.10
• /
• pp.599-604
• /
• 2017

A useful application of smart assistants is to predict and suggest users' daily behaviors the way real assistants do. Conventional methods to predict behavior have mainly used explicit schedule information logged by a user or extracted from e-mail or SNS data. However, gathering explicit information for smart assistants has limitations, and much of a user's routine behavior is not logged in the first place. In this paper, we suggest a novel approach that combines explicit schedule information with patterns of routine behavior. We propose using inference based on a Markov decision process and learning with a reward function based on inverse reinforcement learning. The results of our experiment shows that the proposed method outperforms comparable models on a life-log dataset collected over six weeks.

• Journal of the Korean Data and Information Science Society
• /
• v.20 no.5
• /
• pp.787-796
• /
• 2009

A random coefficient model is applied when times of the repeated measurements are not fixed in experiments with respect to the subjects. The procedures of the inference of a random coefficient model are same as those of a mixed model. Diet experimental data was used for applying the random coefficient model. Various random coefficient models are investigated for the experimental data, and are compared each other. Finally, optimal random coefficient model would be selected. It resulted from the analysis that for the fixed effect factor, the baseline, treatment, height, and time effect were very significant. The treatment effect of the diet foods and exercises were more effective in losing weight than the effect of the diet foods only. The fixed cubic time effect was very significant. The variance components corresponding to the subject effect, linear time effect, quadratic time effect, and cubic time effect of the random coefficients are all positive. When quartic time effect was added as random coefficients the model did not converge. Thus random coefficients up to the cubic terms was considered as the optimal model.

• Journal of the Korean School Mathematics Society
• /
• v.5 no.1
• /
• pp.111-122
• /
• 2002

The purpose of this study was to examine high school second graders' understanding of the basic nature of logarithm, the major type of error they made about logarithmic function and the cause of such an error, and to seek ways to instruct it better. For that purpose, three research questions were posed: 1. Investigate how much high school students in their second year comprehend the nature of logarithm. 2. Analyze what type of error they make about logarithmic function. 3. Analyze the cause of their error according to the selected error models and how it could be taught more efficiently. The findings of this study were as below: First, the natural science students had a better understanding of the basic nature of logarithm than the academic students. What produced the widest gap between the two groups' understanding was applying the nature of logarithm to the given problems, and what caused the smallest gap was the definition of logarithm and the condition of base. Second, the academic students had a poorer understanding of the basic nature of logarithmic function graph and of applying the nature of logarithm to the given problems. Third, the natural science students didn't comprehend well the basic nature of logarithmic function graph, the nature of characteristics and mantissa. Fourth, for all the students from academic and natural science courses, the most common errors were caused by the poor understanding of theorem or nature of the ［E4] model. Fifth, the academic students made more frequent errors due to the unfamiliar signs of the ［El］ model, the imperfect understanding of theorem or nature of the ［E4］ model, and the technical part of the ［E6］ model. Sixth, the natural science students made more frequent errors because of the improper problem interpretation of the ［E2］ model and the logically improper inference of the ［E3］ model.

• Journal of Korean Institute of Industrial Engineers
• /
• v.37 no.4
• /
• pp.323-330
• /
• 2011

Globalization of market and diversification of customers' needs make enterprises to collaboration of participants in supply chain. To establish collaboration, supply chain must have the flexibility and reconfigurability, which are supported by fractal based supply chain management (FrSCM). In this paper, base on the FrSCM, formulation of trust model among the enterprises in the supply chain, and development of profit sharing strategies in the supply chain based on the trust model are investigated. To evaluate trust model, generation of enterprise's goal and its description, extraction and systematic composition of trust factors and trust evaluation are investigated. Based on the developed model, we developed the fuzzy inference engine to evaluate the trust value in terms of numerical value. And then revenue sharing strategies are developed based on the fractal concept and trust model for the collaborative SCM. The fractal concept is used to obtain the optimal production and transportation plans. In addition, the trust model will be integrated into the RS model. In such an RS model, the supply chain will obtain the maximum total profit and profit of each participant depends on its trust value.

• Geomechanics and Engineering
• /
• v.12 no.3
• /
• pp.441-464
• /
• 2017

The determination of the mixture parameters of stabilization has become a great concern in geotechnical applications. This paper presents an effort about the application of artificial intelligence (AI) techniques including radial basis neural network (RBNN), multi-layer perceptrons (MLP), generalized regression neural network (GRNN) and adaptive neuro-fuzzy inference system (ANFIS) in order to predict the unconfined compressive strength (UCS) of silty soil stabilized with bottom ash (BA), jute fiber (JF) and steel fiber (SF) under different freeze-thaw cycles (FTC). The dosages of the stabilizers and number of freeze-thaw cycles were employed as input (predictor) variables and the UCS values as output variable. For understanding the dominant parameter of the predictor variables on the UCS of stabilized soil, a sensitivity analysis has also been performed. The performance measures of root mean square error (RMSE), mean absolute error (MAE) and determination coefficient ($R^2$) were used for the evaluations of the prediction accuracy and applicability of the employed models. The results indicate that the predictions due to all AI techniques employed are significantly correlated with the measured UCS ($p{\leq}0.05$). They also perform better predictions than nonlinear regression (NLR) in terms of the performance measures. It is found from the model performances that RBNN approach within AI techniques yields the highest satisfactory results (RMSE = 55.4 kPa, MAE = 45.1 kPa, and $R^2=0.988$). The sensitivity analysis demonstrates that the JF inclusion within the input predictors is the most effective parameter on the UCS responses, followed by FTC.

• Asian-Australasian Journal of Animal Sciences
• /
• v.24 no.2
• /
• pp.162-172
• /
• 2011

In this paper, simulation was used to determine accuracies of genomic breeding values for polygenic traits associated with many thousands of markers obtained from high density genome scans. The statistical approach was based upon stochastically simulating a pedigree with a specified base population and a specified set of population parameters including the effective and noneffective marker distances and generation time. For this population, marker and quantitative trait locus (QTL) genotypes were generated using either a single linkage group or multiple linkage group model. Single nucleotide polymorphism (SNP) was simulated for an entire bovine genome (except for the sex chromosome, n = 29) including linkage and recombination. Individuals drawn from the simulated population with specified marker and QTL genotypes were randomly mated to establish appropriate levels of linkage disequilibrium for ten generations. Phenotype and genomic SNP data sets were obtained from individuals starting after two generations. Genetic prediction was accomplished by statistically modeling the genomic relationship matrix and standard BLUP methods. The effect of the number of linkage groups was also investigated to determine its influence on the accuracy of breeding values for genomic selection. When using high density scan data (0.08 cM marker distance), accuracies of breeding values on juveniles were obtained of 0.60 and 0.82, for a low heritable trait (0.10) and high heritable trait (0.50), respectively, in the single linkage group model. Estimates of 0.38 and 0.60 were obtained for the same cases in the multiple linkage group models. Unexpectedly, use of BLUP regression methods across many chromosomes was found to give rise to reduced accuracy in breeding value determination. The reasons for this remain a target for further research, but the role of Mendelian sampling may play a fundamental role in producing this effect.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.10
• /
• pp.588-596
• /
• 2017

Although many policy makers and scholars argue that foreign direct investment is crucial to the economic growth of developing countries, there is no universal agreement on the positive relationship between foreign direct investment inflows and economic growth. Using a cross-country analysis based on data from 88 countries for the years 1990-2015, this paper empirically explores the impact of FDI on economic growth. To this end, several versions of the neoclassical growth models, explicitly including FDI, are estimated. Subject to the appropriate caveats, the results provide further support for several key conclusions of former studies, including the inference that investment in physical capital, population growth, and human capital are important in accounting for economic growth across countries. The results show that FDI significantly contributes to economic growth in developing countries.

• The Korean Journal of Applied Statistics
• /
• v.21 no.6
• /
• pp.923-932
• /
• 2008

We are likely to face complex multivariate data which can be characterized by having a non-trivial correlation structure. For instance, omitted covariates may simultaneously affect more than one count in clustered data; hence, the modeling of the correlation structure is important for the efficiency of the estimator and the computation of correct standard errors, i.e., valid inference. A standard way to insert dependence among counts is to assume that they share some common unobservable variables. For this assumption, we fitted correlated random effect models considering multilevel model. Estimation was carried out by adopting the semiparametric approach through a finite mixture EM algorithm without parametric assumptions upon the random coefficients distribution.

• KIISE Transactions on Computing Practices
• /
• v.21 no.1
• /
• pp.94-99
• /
• 2015

With the recent machine learning paradigm of using nonparametric Bayesian statistics and statistical inference based on random sampling, the Dirichlet distribution finds many uses in a variety of graphical models. It is a multivariate generalization of the gamma distribution and is defined on a continuous (K-1)-simplex. This paper presents a sampling method for a Dirichlet distribution for the problem of dividing an integer X into a sequence of K integers which sum to X. The target samples in our problem are all positive integer vectors when multiplied by a given X. They must be sampled from the correspondingly gridded simplex. In this paper we develop a Markov Chain Monte Carlo (MCMC) proposal distribution for the neighborhood grid points on the simplex and then present the complete algorithm based on the Metropolis-Hastings algorithm. The proposed algorithm can be used for the Markov model, HMM, and Semi-Markov model for accurate state-duration modeling. It can also be used for the Gamma-Dirichlet HMM to model q the global-local duration distributions.