• The Korean Journal of Applied Statistics
• /
• v.15 no.2
• /
• pp.405-414
• /
• 2002

We consider the problem of estimating the error variance of in a two-way mixed-effects ANOVA model using noninformative priors. First, we derive Jeffreys' prior, a reference prior, and matching priors. We then provide marginal posterior distributions under those noninformative priors. Finally, we provide graphs of marginal posterior densities of the error variance and credible intervals for the error variance in two real data set and compare these credible intervals.

• Proceedings of the KOSOMBE Conference
• /
• v.1997 no.05
• /
• pp.279-282
• /
• 1997

Bayesian reconstruction methods for emission computed tomography have been a topic of interest in recent years, partly because they allow for the introduction of prior information into the reconstruction problem. Early formulations incorporated priors that imposed simple spatial smoothness constraints on the underlying object using Gibbs priors in the form of four-nearest or eight-nearest neighbors. While these types of priors, known as "membrane" priors, are useful as stabilizers in otherwise unstable ML-EM reconstructions, more sophisticated prior models are needed to model underlying source distributions more accurately. In this work, we investigate whether the "thin plate" model has advantages over the simple Gibbs smoothing priors mentioned above. To test and compare quantitative performance of the reconstruction algorithms, we use Monte Carlo noise trials and calculate bias and variance images of reconstruction estimates. The conclusion is that the thin plate prior outperforms the membrane prior in terms of bias and variance.

• Journal of the Korean Data and Information Science Society
• /
• v.27 no.3
• /
• pp.835-844
• /
• 2016

We develop the testing procedures about the homogeneity of the shape parameters of several inverse Gaussian distributions in our paper. We propose default Bayesian testing procedures for the shape parameters under the reference priors. The Bayes factor based on the proper priors gives the successful results for Bayesian hypothesis testing. For the case of the lack of information, the noninformative priors such as Jereys' prior or the reference prior can be used. Jereys' prior or the reference prior involves the undefined constants in the computation of the Bayes factors. Therefore under the reference priors, we develop the Bayesian testing procedures with the intrinsic Bayes factors and the fractional Bayes factor. Simulation study for the performance of the developed testing procedures is given, and an example for illustration is given.

• Journal of The Korean Association For Science Education
• /
• v.23 no.4
• /
• pp.430-441
• /
• 2003

The purpose of this study was to investigate the effects of students' prior knowledge on scientific reasoning in solving a pendulum task with a computer simulation. Subjects were 60 Korean students: 27 fifth-grade students from an elementary school and 33 seventh grade students from a middle school located in a city with 300,000 people. This study adapted a pendulum task presented with a computer simulation on which subjects would use a pattern of multivariable causal inferences. The subjects were interviewed individually in a three-phase structured interview by the researcher and three assistants while he/she was investigating the pendulum task. This study showed that most students across grades focused heavily on demonstrating the primacy of their prior knowledge or their current hypothesis. In addition, students' theories that are part of one's prior knowledge have a significant impact on formulating, testing, and revising hypotheses. Therefore, this study supported the notion that students' prior knowledge had a strong effect on students' experimental intent and hypothesis evaluation.

• Journal of Families and Better Life
• /
• v.15 no.4
• /
• pp.41-54
• /
• 1997

The purpose of this study is to analyze information search according to consumer's prior knowledge and degree of importance of products. Questionnare survey method was used in this research. The sample was taken from 548 university students in Seoul from 19th of June to 26th of June in 1997. Statistical methods used in this study were Frequency, Percentage, Regression and path Analysis. The major findings are summarized as follows; 1) The level of Consumer's prior knowledge showed somewhat middle. 2) Degree of importance of products showed in order of quality, A/S extension exchange price reliance of a manufacturing company a design etc. 3) Information search for the consumer's prior knowledge and importance showed high on the whole. The more prior knowledge consumer have the better they recognize for the importance of products. Therefore consumers are more likely to search information.

• Journal of Korean Elementary Science Education
• /
• v.28 no.2
• /
• pp.93-104
• /
• 2009

The purpose of this study was to explore the relationship between pre-service elementary teacher's prior knowledge and processes of observations and hypotheses generation via analysis of descriptive fault patterns during observation, problem generation and hypotheses generation processes. For the purpose of this study, thirty-four undergraduate students were participated and descriptions of participants' responds were analyzed. As the result, four patterns of descriptive fault on the process of generating hypothesis were classified; 1) descriptive fault from the causalities, 2) descriptive fault from repetition of observational facts, 3) descriptive fault from the priority of prior knowledge, and 4) descriptive fault from negation of the observational facts. From the result, the researcher was able to explore the faults caused by pre-service elementary students' prior knowledge through the observational descriptive analysis with hypothetical descriptive analysis.

• Journal of the Korean Data and Information Science Society
• /
• v.23 no.2
• /
• pp.353-363
• /
• 2012

In this paper, we introduce the noninformative priors such as the matching priors and the reference priors for the common scale parameter in the Pareto distributions. It turns out that the posterior distribution under the reference priors is not proper, and Jeffreys' prior is not a matching prior. It is shown that the proposed first order prior matches the target coverage probabilities in a frequentist sense through simulation study.

• Journal of the Korean Data and Information Science Society
• /
• v.18 no.3
• /
• pp.833-845
• /
• 2007

When X and Y have independent exponential distributions, we develop a Bayesian testing procedure for the ratio of two quantiles under reference prior. The noninformative prior such as reference prior is usually improper which yields a calibration problem that makes the Bayes factor to be defined up to a multiplicative constant. So we develop a Bayesian testing procedure based on fractional Bayes factor and intrinsic Bayes factor. We show that the posterior density under the reference prior is proper and propose the Bayesian testing procedure for the ratio of two quantiles using fractional Bayes factor and intrinsic Bayes factor. Simulation study and a real data example are provided.

• Journal of the Korean Data and Information Science Society
• /
• v.20 no.3
• /
• pp.601-614
• /
• 2009

This paper derives noninformative priors for scale parameter of exponential distribution when the data are collected in multiple step stress accelerated life tests. We nd the objective priors for this model and show that the reference prior satisfies first order matching criterion. Also, we show that there exists no second order matching prior. Some simulation results are given and using artificial data, we perform Bayesian analysis for proposed priors.

• The Korean Journal of Applied Statistics
• /
• v.3 no.2
• /
• pp.91-105
• /
• 1990

Several practical prior distributions are derived using the maximum entropy principle. Also, an interactive method for estimating a prior distribution which uses the minimum cross-entropy principle is proposed when there are many prior informations. The consistency of the prior distributions obtained by the entropy principles is discussed.