• Proceedings of the Society of Korea Industrial and System Engineering Conference
• /
• 2002.05a
• /
• pp.371-377
• /
• 2002

In this paper, We consider some generalization of these five basic indices to cover non-normal distribution. The proposed generalizations are compared with the five basic indices. The results show that the proposed generalizations are more accurate than those basic indices and other generalization in measuring process capability. We compared an estimation methods by Clements with based on sample percentiles, WVM to calculate the proposed generalization as an example. The results indicated that Clements method is more accurate than percentile method, WVM in measuring process capability. But the calculations of percentile method are easy to understand, straightforward to apply, and show be valuable used for applications.

• Journal of Korean Society for Quality Management
• /
• v.28 no.3
• /
• pp.124-132
• /
• 2000

A selected subject and a standardized scoring system were newly enforced at college entrance examination from 1999. A selected subject system means each student can select one subject in addition to common subject in the field of mathematical research II and a standardized scoring system means we standardize the score of each field as mean 50 and standard deviation 10 in order to adjust the degree of difficulty between fields. In the field of mathematical research II, there may exist not only difference of the degree of difficulty but also that of general studying ability between groups of selected subjects. So when we standardize score, we have to consider them. So far a linear equating which is a parametric method and an equi-percentile equating which is a nonparametric method have been published, but both of them supposed that the general studying ability between groups was equal. So in this paper an adjusted linear and percentile equating method which seems to be adequate to our entrance examination is suggested and is investigated by computer simulation.

• Asian Pacific Journal of Cancer Prevention
• /
• v.17 no.sup3
• /
• pp.113-117
• /
• 2016

Quantile regression is an efficient method for predicting and estimating the relationship between explanatory variables and percentile points of the response distribution, particularly for extreme percentiles of the distribution. To study the relationship between urbanization and cancer morbidity, we here applied quantile regression. This cross-sectional study was conducted for 9 cancers in 345 cities in 2007 in Iran. Data were obtained from the Ministry of Health and Medical Education and the relationship between urbanization and cancer morbidity was investigated using quantile regression and least square regression. Fitting models were compared using AIC criteria. R (3.0.1) software and the Quantreg package were used for statistical analysis. With the quantile regression model all percentiles for breast, colorectal, prostate, lung and pancreas cancers demonstrated increasing incidence rate with urbanization. The maximum increase for breast cancer was in the 90th percentile (${\beta}$=0.13, p-value<0.001), for colorectal cancer was in the 75th percentile (${\beta}$=0.048, p-value<0.001), for prostate cancer the 95th percentile (${\beta}$=0.55, p-value<0.001), for lung cancer was in 95th percentile (${\beta}$=0.52, p-value=0.006), for pancreas cancer was in 10th percentile (${\beta}$=0.011, p-value<0.001). For gastric, esophageal and skin cancers, with increasing urbanization, the incidence rate was decreased. The maximum decrease for gastric cancer was in the 90th percentile(${\beta}$=0.003, p-value<0.001), for esophageal cancer the 95th (${\beta}$=0.04, p-value=0.4) and for skin cancer also the 95th (${\beta}$=0.145, p-value=0.071). The AIC showed that for upper percentiles, the fitting of quantile regression was better than least square regression. According to the results of this study, the significant impact of urbanization on cancer morbidity requirs more effort and planning by policymakers and administrators in order to reduce risk factors such as pollution in urban areas and ensure proper nutrition recommendations are made.

• Journal of Korean Society of Water and Wastewater
• /
• v.28 no.3
• /
• pp.345-358
• /
• 2014

For introducing the groundwater quality assessment using background concentration of groundwater, several methods had been studied to estimate the background concentration of groundwater and to suggest the background concentration of study area. Some methods such as Box whisker plot, Percentile and Cumulative probability distribution had been adopted to estimate background concentration, and it was evaluated that the Cumulative probability distribution method presents more reasonable background concentration because it can consider the data distribution. So we estimated the background concentration of study area using cumulative probability distribution method. We suggested the background concentration for each hydrogeology respectively in case hydrogeological water quality similarity is very low.

• IE interfaces
• /
• v.17 no.1
• /
• pp.1-12
• /
• 2004

In a modern semiconductor device manufacturing industry, statistical bin limits on wafer level test bin data are used for minimizing value added to defective product as well as protecting end customers from potential quality and reliability excursion. Most wafer level test bin data show skewed distributions. By Monte Carlo simulation, this paper evaluates methods and sample size effect regarding determination of statistical bin limits. In the simulation, it is assumed that wafer level test bin data follow the Poisson distribution. Hence, typical shapes of the data distribution can be specified in terms of the distribution's parameter. This study examines three different methods; 1) percentile based methodology; 2) data transformation; and 3) Poisson model fitting. The mean square error is adopted as a performance measure for each simulation scenario. Then, a case study is presented. Results show that the percentile and transformation based methods give more stable statistical bin limits associated with the real dataset. However, with highly skewed distributions, the transformation based method should be used with caution in determining statistical bin limits. When the data are well fitted to a certain probability distribution, the model fitting approach can be used in the determination. As for the sample size effect, the mean square error seems to reduce exponentially according to the sample size.

• Convergence Security Journal
• /
• v.8 no.4
• /
• pp.115-120
• /
• 2008

Accurate predictions of software release times, and estimation of the reliability and availability of a software product require quantification of a critical element of the software testing process： Change-point problem. In this paper, exponential (Goel-Okumoto) model was reviewed, proposes the percentile change-point problem, which maked out efficiency application for software reliability. Algorithm to estimate the parameters used to maximum likelihood estimator and bisection method, model selection based on SSE statistics, for the sake of efficient model, was employed. Using NTDS data, The numerical example of percentilechange-point problemi s presented.

• Journal of Korean Society for Quality Management
• /
• v.50 no.2
• /
• pp.199-220
• /
• 2022

Purpose: The purpose of this study is to analyze the score data released by the Korea Institute of Curriculum and Evaluation to find out the problems with the current scoring system provided by the College Scholastic Ability Test and to suggest improvement measures to solve these problems. Methods: We calculated the descriptive statistics of the standard scores using the frequency distribution table of the standard scores and identified the characteristics of the standard scores by expressing the distribution as a graph. Also, we developed an index to evaluate whether each stanine level was stably assigned and calculated the indexes for each area/subject by using the data on the number of examinees for each level. Results: We found that the relationship of conversion from raw scores to integerized standard scores is different depending on the size of the standard deviation of the raw scores, and identified the problem that the raw score information is not fairly reflected in the calculation of the percentile and level as the two raw scores are converted to one standard score. This problem can be solved by calculating the standard score to a decimal point. Conclusion: In this study, as a way to improve the quality of the scores of the current CSAT, the standard score and percentile decimal notation, the specific regulations of the standard score and stanine level calculation method, and the expansion of the open range of the scores were suggested.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.23 no.6
• /
• pp.289-299
• /
• 2019

The tendency to use a probabilistic design method rather than a deterministic design method for the design of nuclear power plants (NPPs) will increase because their safety should be considered and strictly controlled in relation to various causes of damage. The distance between a seismically isolated NPP structure and a moat wall is called the clearance to stop. The clearance to stop is obtained from the 90th percentile displacement response of a seismically isolated NPP subject to a beyond design basis earthquake (BDBE) in the probabilistic design method. The purpose of this study is to analyze the effects of heating and buckling effects on the 90th percentile displacement response of a lead-rubber bearing (LRB) subject to a BDBE. The analysis results show that considering the heating and buckling effects to estimate the clearance to stop is conservative in the evaluation of the 90th percentile displacement response. If these two effects are not taken into account in the calculation of the clearance to stop, the underestimation of the clearance to stop causes unexpected damage because of an increase in the collision probability between the moat wall and the seismically isolated NPP.

• Journal of Nutrition and Health
• /
• v.38 no.7
• /
• pp.570-577
• /
• 2005

The purpose of this study was to investigate the effect of bone mineral density on life styles, dietary habits and nutrient intakes among the male college students. The subjects were divided into four groups; $Q_1$ (calcaneus BMD < 25 percentile, n = 117), $Q_2$ (25 percentile $\le$ calcaneus BMD < 50 percentile, n = 118), $Q_3$ (50 percentile $\le$ calcaneus BMD < 75 percentile, n = 118) $Q_4$ (calcaneus BMD $\ge$ 75 percentile, n = 116). And they were asked about general characteristics, life style, dietary habit, and nutrient intake using questionnaire and 24-hr recall method. They were measured the bone mineral density of calcaneus using quantitative ultrasound. The average age of the subjects of the study was 23.0 yews and the average height, weight, and BMI were 174.7 cm, 69.0 kg, $22.5 kg/m^2$. The bone mineral density in calcaneus was $0.43 g/cm^2$ in $Q_1,\;0.50 g/cm^2$ in $Q_2,\;0.56 g/cm^2$ in $Q_3$, and $0.69 g/cm^2$ in $Q_4$ (p < 0.001). The results showed that $Q_1$ tended to have irregular exercise compared to the other three groups. Compared with $Q_1$ and $Q_2$, the frequency of skipping breakfast was lower in $Q_3$ and $Q_4$. Also the results showed that the $Q_4$ was significantly more often to drink coffee compared with the other three groups (p < 0.01). The mean daily energy intake was 2210.6 kcal ($88.4\%$ of RDA). The intake of energy, vitamin $B_2$, calcium, and zinc did not meet the Korean RDA. Also the $Q_2$consumed significantly lower intakes of protein (p < 0.05) and plant protein (p < 0.05) compared to the $Q_3$ and $Q_4$. The $Q_1$ and $Q_2$ consumed significantly lower intakes of vitamin $B_2$ (p < 0.01) compared to the $Q_3$ and $Q_4$. In conclusion, male student in lower bone mineral density appeared to have unhealthy life styles and dietary habits in terms of irregular exercise, high frequency of skipping breakfast and lower intakes of protein, vitamin $B_2$ showing a strong need proper education on meal practices and exercise habits for the bone health.

• Quality Improvement in Health Care
• /
• v.3 no.2
• /
• pp.60-68
• /
• 1997

Background : Medical records are used to assess clinical performance of physicians and quality of care. The contents which are written in medical records are considered as the objective evidences to know what the doctors think about the patient's problems. But the problem to use medical records as the assessment tools is the incompleteness of medical recording. The purpose of this study is to know if the completeness of medical recording is correlated to quality of care for inpattients and it can predict physicians's quality of care. Method : 32 clinical physicians reviewed 200 patients' medical records who were selected randomly from the inpatients who were admitted to the university hospital during July, 1995 and June, 1996. The reviewers used the structured evaluation questionnaires which were composed of two part. One part evaluated the completeness of the medical recording and the other evaluating appropriateness of diagnosis and treatment processes. We summated the scores of each items and calculated percentile scores. Results : The mean percentile score of completeness of the medical recording was 67.9% in 1995 and 79.8% in 1996. The mean percentile score of appropriateness was 52.2% in 1995 and 69.5% in 1996. This change between 1995 and 1996 was statistically significant. In non-surgical patients, the percentile scores of the completeness and those of the appropriateness were correlated positively and this correlation was statistically significant(p<0.05). In surgical patients, the positve correlation between the completeness and the appropriateness was also statistically significant(p<0.05). Discussion : In conclusion, the completeness of medical recording is considered as the good predictor of the quality of care for inpatients.