• Communications for Statistical Applications and Methods
• /
• v.6 no.1
• /
• pp.193-205
• /
• 1999

An approximate Bayes criterion for Behrens-Fisher problem (testing equality of means of two normal populations with unequal variances) is proposed and examined. Development of the criterion involves derivation of approximate Bayes factor using the imaginary training sample approachintroduced by Spiegelhalter and Smith (1982). The proposed criterion is designed to develop a Bayesian test criterion having a closed form, so that it provides an alternative test to those based upon asymptotic sampling theory (such as Welch's t test). For the suggested Bayes criterion, numerical study gives comparisons with a couple of asymptotic classical test criteria.

• Communications for Statistical Applications and Methods
• /
• v.10 no.3
• /
• pp.647-654
• /
• 2003

Bayesian probability models for finite populations are considered assuming so-called the super-population. We find the posterior distribution of population mean by a new approach, using the concept of pivotal quantity for the small sample case. A large sample theory is also treated throught the concept of asymptotically pivotal quantity.

• Journal of the Korean Statistical Society
• /
• v.32 no.4
• /
• pp.411-423
• /
• 2003

In this paper we develop a method for calculating a probability that a particular generalized variance is the smallest of all the K multivariate normal generalized variances. The method gives a way of comparing K multivariate populations in terms of their dispersion or spread, because the generalized variance is a scalar measure of the overall multivariate scatter. Fully parametric frequentist approach for the probability is intractable and thus a Bayesian method is pursued using a variant of weighted Monte Carlo (WMC) sampling based approach. Necessary theory involved in the method and computation is provided.

• Journal of the Korean Statistical Society
• /
• v.28 no.1
• /
• pp.107-124
• /
• 1999

An approximate Bayes criterion for multivariate Behrens-Fisher problem is proposed and examined. Development of the criterion involves derivation of approximate Bayes factor using the imaginary training sample approach introduced by Speigelhalter and Smith (1982). The criterion is designed to develop a Bayesian test, so that it provides an alternative test to other tests based upon asymptotic sampling theory (such as the tests suggested by Bennett(1951), James(1954) and Yao(1965). For the derived criterion, numerical studies demonstrate routine application and give comparisons with the classical tests.

• Genomics & Informatics
• /
• v.20 no.1
• /
• pp.8.1-8.14
• /
• 2022

Despite the success of recent genome-wide association studies investigating longitudinal traits, a large fraction of overall heritability remains unexplained. This suggests that some of the missing heritability may be accounted for by gene-gene and gene-time/environment interactions. In this paper, we develop a Bayesian variable selection method for longitudinal genetic data based on mixed models. The method jointly models the main effects and interactions of all candidate genetic variants and non-genetic factors and has higher statistical power than previous approaches. To account for the within-subject dependence structure, we propose a grid-based approach that models only one fixed-dimensional covariance matrix, which is thus applicable to data where subjects have different numbers of time points. We provide the theoretical basis of our Bayesian method and then illustrate its performance using data from the 1000 Genome Project with various simulation settings. Several simulation studies show that our multivariate method increases the statistical power compared to the corresponding univariate method and can detect gene-time/ environment interactions well. We further evaluate our method with different numbers of individuals, variants, and causal variants, as well as different trait-heritability, and conclude that our method performs reasonably well with various simulation settings.

• Research in Mathematical Education
• /
• v.11 no.4
• /
• pp.275-283
• /
• 2007

In this study, we gave 132 high school students fifteen probabilities and nine statistics problems of the Korean College Scholastic Aptitude Test and then analyzed their answer using the classical test theory and the item response theory. Using the classical test theory (the Testian 1.0) we get the item reliability ($0.730 \sim 0.765$), and using the item response theory (the Bayesian 1.0) we get the item difficulty ( $-2.32\sim0.83$ ) and discrimination ( $0.55\sim 2.71$). From results, we find out what and why students could not understand well.

• Journal of Korean Society of Transportation
• /
• v.22 no.7 s.78
• /
• pp.79-90
• /
• 2004

In this study, we applied the Bayesian Networks for the case of the trip generation models using the Seoul metropolitan area's house trip survey Data. The household income was used for the independent variable for the explanation of household size and the number of cars in a household, and the relationships between the trip generation and the households' social characteristics were identified by the Bayesian Networks. Furthermore, trip generation's characteristics such as the household income, household size and the number of cars in a household were also used for explanatory variables and the trip generation model was developed. It was found that the Bayesian Networks were useful tool to overcome the problems which were in the traditional trip generation models. In particular the various transport policies could be evaluated in the very short time by the established relationships. It is expected that the Bayesian Networks will be utilized as the important tools for the analysis of trip patterns.

• Korean Journal of Cognitive Science
• /
• v.27 no.4
• /
• pp.541-572
• /
• 2016

Causal reasoning is actively studied not only by psychologists but, in recent years, also by cognitive scientists taking the Bayesian approach. This paper seeks to provide an overview of the recent trends in causal reasoning research with a focus on the power probabilistic contrast theory of causality, a major psychological theory on causal inference. The power probabilistic contrast theory (PPCT) assumes that a cause is a power that initiates or inhibits the result. This power is purported be understood through statistical correlation under certain conditions. The paper examines the supporting empirical evidence in the development of PPCT. Also, introduced are the theoretical dispute between the PPCT and the model based on Bayesian approach, and the current developments and implications of research on causal invariance hypothesis, which states that cause operates identically regardless of the context. Recent studies have produced experimental results that cannot be readily explained by existing empirical approach. Therefore, these results call for serious examination of the power theory of causality by researchers in neighboring fields such as philosophy, statistics, and artificial intelligence.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2003.03a
• /
• pp.833-840
• /
• 2003

The stability of structure, effectiveness of design and construction are very important factors in soil-structure design. The design-parameter is based on the test through laboratory-test and field-test. There are two ways to obtain the design-parameter. One is to through test, and the other is through relative documents and references. Recently, statistics has been used to get reliable data. In this study, Kriging method as Geostatistics and the theory of Bayesian's inference are used and the design-parameters are obtained. As the result of this study to the design-parameter is reliable and information about soil condition and soil properties in design and construction is easily found.

• Proceedings of the Korean Statistical Society Conference
• /
• 2002.05a
• /
• pp.73-78
• /
• 2002

In this paper we develop a method for constructing a Bayesian HPD (highest probability density) interval of a ratio of two multivariate normal generalized variances. The method gives a way of comparing two multivariate populations in terms of their dispersion or spread, because the generalized variance is a scalar measure of the overall multivariate scatter. Fully parametric frequentist approaches for the interval is intractable and thus a Bayesian HPD(highest probability densith) interval is pursued using a variant of weighted Monte Carlo (WMC) sampling based approach introduced by Chen and Shao(1999). Necessary theory involved in the method and computation is provided.