• Communications for Statistical Applications and Methods
• /
• v.9 no.3
• /
• pp.853-864
• /
• 2002

In the analysis of categorical data subject to misclassification errors, the observed cell proportions are adjusted by a misclassification probabilities and estimates of variances are adjusted accordingly. In this case, it is important to determine the extent to which misclassification probabilities are homogeneous within a population. This paper considers methods to evaluate the power of chi-squared tests for homogeneity with complex survey data subject to misclassification errors. Two cases are considered: adjustment with homogeneous misclassification probabilities; adjustment with heterogeneous misclassification probabilities. To estimate misclassification probabilities, logistic regression method is considered.

• Nuclear Engineering and Technology
• /
• v.53 no.10
• /
• pp.3298-3313
• /
• 2021

The objective of this study is to estimate the occurrence probabilities of severe accident phenomena based on a fuzzy elicitation technique. Normally, it is difficult to determine these probabilities due to the lack of information on severe accident progression and the highly uncertain values currently in use. In this case, fuzzy set theory (FST) can be best exploited. First, questions were devised for expert elicitation on technical issues of severe accident phenomena. To deal with ambiguities and the imprecision of previously developed (reference) probabilities, fuzzy aggregation methods based on FST were employed to derive the occurrence probabilities of severe accidents via four phases: 1) choosing experts, 2) quantifying weighting factors for the experts, 3) aggregating the experts' opinions, and 4) defuzzifying the fuzzy numbers. In this way, this study obtained expert elicitation results in the form of updated occurrence probabilities of severe accident phenomena in the OPR-1000 plant, after which the differences between the reference probabilities and the newly acquired probabilities using fuzzy aggregation were compared, with the advantages of the fuzzy technique over other approaches explained. Lastly, the impact of applying the updated severe accident probabilities on containment integrity was quantitatively investigated in a Level 2 PSA model.

• Communications for Statistical Applications and Methods
• /
• v.8 no.3
• /
• pp.589-601
• /
• 2001

Probabilities of overfilling for model selection criteria are derived for several different situations. First, one candidate model with one extra variable is compared to the current model. This is expanded to m candidate models. We show that these comparisons are not independent and discuss ovefitting probabilities. Correlation between two F-tests is derived. Finally, probabilities are computed using the dependent F distributions and F distributions based on order statistics of independent Chi-squares.

• Korean Journal of Logic
• /
• v.8 no.2
• /
• pp.59-84
• /
• 2005

Adams' Thesis, or the so-called equation Pr$(A{\rightarrow}C)$ = Pr(C|A) seems to express a correct relationship between the probabilities of conditionals and conditional probabilities. But D. K. Lewis has proved the remarkable fact that probabilities of conditionals are not conditional probabilities. In this paper 1 present a version of Lewis' triviality results and give an explanation why probabilities of conditionals are not conditional probabilities. A conditional probability of C given A has a peculiar properly in that its probability is insulated from not-A facts: the only thing relevant is the proportion of ways in which A is true which are also ways for C to be true. This peculiarity of conditional probability seems to put the great obstacle in the way of attempting to find a proposition such that its probability of being true systematically coincides with conditional probability of something else.

• The Korean Journal of Applied Statistics
• /
• v.25 no.5
• /
• pp.813-820
• /
• 2012

A surplus process with two types of claims is considered, where Type I claims occur more frequently, however, their sizes are smaller stochastically than Type II claims. The ruin probabilities of the surplus caused by each type of claim are obtained by establishing integro-differential equations for the ruin probabilities. The formulas of the ruin probabilities contain an infinite sum and convolutions that make the formulas hard to be applicable in practice; subsequently, we obtain explicit formulas for the ruin probabilities when the sizes of both types of claims are exponentially distributed. Finally, we show through a numerical example, that Type II claims have more impact on the ruin probability of the surplus than Type I claims.

• Journal of Institute of Control, Robotics and Systems
• /
• v.3 no.1
• /
• pp.52-60
• /
• 1997

In genetic algorithms(GA), a crossover is performed only at one or two places of a chromosome, and the fixed probabilities of crossover and mutation have been used during the entire generation. A GA with dynamic mutation is known to be superior to GAs with static mutation in performance, but so far no efficient dynamic mutation method has been presented. Accordingly in this paper, a GA is proposed to perform a uniform crossover based on the nucleotide(NU) concept, where DNA and RNA consist of NUs and also a concrete way to vary the probabilities of crossover and mutation dynamically for every generation is proposed. The efficacy of the proposed GA is demonstrated by its application to the unimodal, multimodal and nonlinear control problems, respectively. Simulation results show that in the convergence speed to the optimal value, the proposed GA was superior to existing ones, and the performance of GAs with varying probabilities of the crossover and the mutation improved as compared to GAs with fixed probabilities of the crossover and mutation. And it also shows that the NUs function as the building blocks and so the improvement of the proposed algorithm is supported by the building block hypothesis.

• Journal of the Korean Society of Safety
• /
• v.22 no.1 s.79
• /
• pp.61-66
• /
• 2007

Car crashes are the leading cause of death for persons of every age. Specially, human-related factor has been known to be the primary causal factor of such crashes than vehicle-and environmental-related factors. There are various studies to analyze driver's behavior and characteristics in driving for reducing the car crashes in many areas of car engineering, psychology, human factor, etc. However, there are almost no studies which analyze mainly the human errors in driving and estimate their probabilities in terms of human reliability analysis. This study estimates the probability of human error in driving, i.e. driver error probability. First, fifty driver errors are investigated through DBQ (Driver Behavior Questionnaire) revision and the error likelihoods in driving are collected which are judged by skillful drivers using revised DBQ. Next, these likelihoods are converted into driver error probabilities using the results that verbal probabilistic expressions are changed into quantitative probabilities. Using these probabilities we can improve the warning effects on drivers by indicating their driving error likelihoods quantitatively. We can also expect the reduction effects of car accident through controlling especially dangerous error groups which have higher probabilities. Like these, the results of this study can be used as the primary materials of safety education on drivers.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.11 no.3
• /
• pp.45-52
• /
• 2001

In this paper, we examine the method for evaluating the security of SPN structures against differential cryptanalysis and linear cryptanalysis. We present an example of SPN structures in which there is a considerable difference between the differential probabilities and the characteristic probabilities. Then we 7pose an algorithm for estimating the maximum differential probabilities and the maximum linear hull probabilities of SPN structures and an useful method for accelerating the proposed algorithm. By using this method, we obain the maximum differential probabilities and the maximum linear probabilities of round function F of block cipher E2.

• Earthquakes and Structures
• /
• v.26 no.2
• /
• pp.87-96
• /
• 2024

This paper proposes a logistic multinomial regression approach to model the spatial cross-correlation of damage probabilities among different damage states in an expanded transportation network. Utilizing Bayesian theory and the multinomial logistic model, we analyze the damage states and probabilities of bridges while incorporating damage correlation. This correlation is considered both between bridges in a network and within each bridge's damage states. The correlation model of damage probabilities is applied to the seismic assessment of a portion of Tehran's transportation network, encompassing 26 bridges. Additionally, we introduce extra daily traffic time (EDTT) as an operational parameter of the transportation network and employ the shortest path algorithm to determine the path between two nodes. Our results demonstrate that incorporating the correlation of damage probabilities reduces the travel time of the selected network. The average decrease in travel time for the correlated case compared to the uncorrelated case, using two selected EDTT models, is 53% and 71%, respectively.

• The Transactions of the Korea Information Processing Society
• /
• v.3 no.6
• /
• pp.1588-1597
• /
• 1996

This paper describes an estimation method for lexical probabilities in Korean lexical disambiguation. In the stochastic to lexical disambiguation lexical probabilities and contextual probabilities are generally estimated on the basis of statistical data extracted form corpora. It is desirable to apply lexical probabilities in terms of word phrases for Korean because sentences are spaced in the unit of word phrase. However, Korean word phrases are so multiform that there are more or less chances that lexical probabilities cannot be estimated directly in terms of word phrases though fairly large corpora are used. To overcome this problem, similarity for word phrases is defined from the lexical analysis point of view in this research and an estimation method for Korean lexical probabilities based on the similarity is proposed. In this method, when a lexical probability for a word phrase cannot be estimated directly, it is estimated indirectly through the word phrase similar to the given one. Experimental results show that the proposed approach is effective for Korean lexical disambiguation.