• Journal of Korean Society for Quality Management
• /
• v.46 no.3
• /
• pp.509-522
• /
• 2018

Purpose: The purpose of this study was to propose more accurate mathematical model which can represent result of government quality assurance activity, especially corrective action and flaw. Methods: The collected data during government quality assurance activity was represented through histogram. To find out which distributions (Poisson distribution, Zero-Inflated Poisson distribution) could represent the histogram better, this study applied Pearson's correlation coefficient. Results: The result of this study is as follows; Histogram of corrective action during past 3 years and Zero-Inflated Poisson distribution had strong relationship that their correlation coefficients was over 0.94. Flaw data could not re-parameterize to Zero-Inflated Poisson distribution because its frequency of flaw occurrence was too small. However, histogram of flaw data during past 3 years and Poisson distribution showed strong relationship that their correlation coefficients was 0.99. Conclusion: Zero-Inflated Poisson distribution represented better than Poisson distribution to demonstrate corrective action histogram. However, in the case of flaw data histogram, Poisson distribution was more accurate than Zero-Inflated Poisson distribution.

• Journal of the Korean Data and Information Science Society
• /
• v.15 no.2
• /
• pp.387-394
• /
• 2004

Zero-Inflated Poisson distribution is Poisson distribution with excess zeros. Recently defects of product hardley happen in the manufacturing process. In this case it is desirable to apply to the Zero-Inflated Poisson distribution rather than Poisson. Our target of this paper is to study the tests for changes of rate of defects after the unknown change-point. We are going to compare the powers of the two proposed tests with likelihood tests by the simulations.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.12 no.2
• /
• pp.97-108
• /
• 2008

In this paper Bayes estimator of the parameter and reliability function of the zero-truncated Poisson distribution are obtained. Furthermore, recurrence relations for the estimator of the parameter are also derived. Monte Carlo simulation technique has been made for comparing the Bayes estimator and reliability function with the corresponding maximum likelihood estimator (MLE) of zero-truncated Poisson distribution.

• Journal of the Korean GEO-environmental Society
• /
• v.6 no.1
• /
• pp.45-51
• /
• 2005

The distribution of shaft resistance is measured by the static load test with the strain gauge or stress gauge, so that the long-term load distribution must be considered for the pile design. However, the measurement by strain gauge generally assumes the 'zero reading', which is the reading taken at 'zero time' with 'zero' load and the residual stress, which is the negative skin friction(or the negative shaft resistance) caused by the pile construction, is neglected. Therefore, the measured value by strain gauge is different from the true load-distribution because residual stresses were neglected. In this study, the three drilled shafts were constructed, and the strain measurements were carried out just after shaft construction. As a result of this study, it is shown that the true load-distribution of drilled shaft is quite different with known load distribution and the true load-distribution of drilled shaft changed from the negative skin friction to the positive skin according to the load increment.

• Journal of the Korean Statistical Society
• /
• v.11 no.2
• /
• pp.131-138
• /
• 1982

Analogous to Singh's (1978) characterization of positive-Poisson distributioin and Shanmugam and Singh's (1992) characterization of logarithmic series distribution, a characterization and its statistical application of the negative binomial distribution truncated at zero are given in this paper. While it is known that under certain conditions the negative binomial distribution truncted at zero approaches the positive-Poisson and the logarithmic series distributions, we show here that the results of this paper approach in limit the results of Singh, and Shanmugam and Singh, respectively. Using the biologicla data from Sampford (1955), we illusrate our results. Also, expressions are explicitly given to test the hypothesis whether a random sample is indeed from a geometric distribution.

• Journal of Applied Reliability
• /
• v.14 no.4
• /
• pp.220-224
• /
• 2014

A Bayesian zero-failure reliability demonstration test method for products with Weibull lifetime distribution is presented. Inverted gamma prior distribution for the scale parameter of the Weibull distribution is used to design the Bayesian test plan and selecting a prior distribution using a prior test information is discussed. A test procedure with zero-failure acceptance criterion is developed that guarantee specified reliability of a product with given confidence level. An example is provided to illustrate the use of the developed Bayesian reliability demonstration test method.

• Journal of Energy Engineering
• /
• v.23 no.3
• /
• pp.36-41
• /
• 2014

The world's overall need for natural gas (NG) has been growing up fast, especially in the residential sector. The better the estimation of residential NG consumption (RNGC) distribution, the better decision-making for a residential NG policy such as pricing, demand estimation, management options and so on. Approximating the distribution of RNGC is complicated by zero observations in the sample. To deal with the zero observations by allowing a point mass at zero, a mixture model of RNGC distributions is proposed and applied. The RNGC distribution is specified as a mixture of two distributions, one with a point mass at zero and the other with full support on the positive half of the real line. The model is empirically verified for household RNGC survey data collected in Korea. The mixture model can easily capture the common bimodality feature of the RNGC distribution. In addition, when covariates were added to the model, it was found that the probability that a household has non-expenditure significantly varies with some variables. Finally, the goodness-of-fit test suggests that the data are well represented by the mixture model.

• Journal of Applied Reliability
• /
• v.14 no.4
• /
• pp.262-266
• /
• 2014

In this paper, we consider the problem of determining the confidence level in zero-failure reliability sampling plans when the life distribution is Weibull distribution with a shape parameter m and a scale parameter ${\eta}$. We introduce zero-failure reliability sampling plans for Weibull distribution and investigate some characteristics of zero-failure reliability sampling plans. Finally, We propose new guideline for determining the confidence level in zero-failure reliability sampling plans for assuring $B_x-life$.

• Journal of Applied Reliability
• /
• v.13 no.1
• /
• pp.1-10
• /
• 2013

A Bayesian zero-failure reliability demonstration test method for products with exponential lifetime distribution is presented. Beta prior distribution for reliability of a product is used to design the Bayesian test plan and selecting a prior distribution using a prior test information is discussed. A test procedure with zero-failure acceptance criterion is developed that guarantees specified reliability of a product with given confidence level. An example is provided to illustrate the use of the developed Bayesian reliability demonstration test method.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.34 no.3
• /
• pp.43-52
• /
• 1992

Design low flows were derived from the decision of a best fitting probability distribution and of an optimum transformation method can be contributed to the planning of water utilization and management of various hydraulic structures during dry season in the main river systems in Korea. The results were analyzed and summarized as follows. 1.Basic statistics for the selected watersheds were calculated as one of means for the analysis of extremal distribution. 2.Parameters for the different frequency distributions were calculated by the method of moment. 3.Type m extremal distribution was confirmed as a best one among others for the frequency distribution of the low flows by x$^2$ goodness of fit test. 4.Formulas for the design low flows of the Type m extremal distribution with two and three parameters were dervied for the selected watersheds. 5.Design low flows for the Type m extremal distribution when a minimum drought is zero or larger than zero were derived for the selected watersheds, respectively. 6.Design low flows of the Type m extremal distribution with two parameters are appeared to be reasonable when a minimum drought approaches to zero and the observed low flows varied within a relating small range while those with three parameters are seemed to be consistent with the probability distribution of low flows when a minimum drought is larger than zero and the observed low flows showed a wide range.