• Journal of Labour Economics
• /
• v.43 no.1
• /
• pp.59-91
• /
• 2020

The recent reform of child care policy is to give priority to double-income households in the use of childcare facilities. This study analyzed the effect of the use of childcare facilities on the employment of married women under the on-going reform. Using the data from the 19th and 21st wave of the Korean Labor and Income Study, the marginal treatment effect (MTE) analysis method was used to eliminate the selection bias in which the sub-population targeted for policy is determined according to the priority when childcare demand exceeds supply. The study finds that the employment effect of married women who use childcare facilities does not differ statistically from the employment effect of married women who do not use childcare facilities.

• Korean Journal of Remote Sensing
• /
• v.28 no.6
• /
• pp.635-651
• /
• 2012

To produce a level-3 monthly composite image from daily level-2 Sea-viewing Wide Field-of-view Sensor (SeaWiFS) chlorophyll-a concentration data set in the East Sea, we applied four average methods such as the simple average method, the geometric mean method, the maximum likelihood average method, and the weighted averaging method. Prior to performing each averaging method, we classified all pixels into normal pixels and abnormal speckles with anomalously high chlorophyll-a concentrations to eliminate speckles from the following procedure for composite methods. As a result, all composite maps did not contain the erratic effect of speckles. The geometric mean method tended to underestimate chlorophyll-a concentration values all the time as compared with other methods. The weighted averaging method was quite similar to the simple average method, however, it had a tendency to be overestimated at high-value range of chlorophyll-a concentration. Maximum likelihood method was almost similar to the simple average method by demonstrating small variance and high correlation (r=0.9962) of the differences between the two. However, it still had the disadvantage that it was very sensitive in the presence of speckles within a bin. The geometric mean was most significantly deviated from the remaining methods regardless of the magnitude of chlorophyll-a concentration values. Its bias error tended to be large when the standard deviation within a bin increased with less uniformity. It was more biased when data uniformity became small. All the methods exhibited large errors as chlorophyll-a concentration values dominantly scatter in terms of time and space. This study emphasizes the importance of the speckle removal process and proper selection of average methods to reduce composite errors for diverse scientific applications of satellite-derived chlorophyll-a concentration data.

• Journal of the Korea Society of Computer and Information
• /
• v.12 no.4
• /
• pp.33-42
• /
• 2007

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 : test coverage. This model called Enhanced non-homogeneous poission process(ENHPP). In this paper, exponential coverage and S-shaped model was reviewed, proposes the Kappa coverage model, 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 and Kolmogorov distance, for the sake of efficient model, was employed. From the analysis of mission time, the result of this comparative study shows the excellent performance of Burr coverage model rather than exponential coverage and S-shaped model using NTDS data. This analysis of failure data compared with the Kappa coverage model and the existing model(using arithmetic and Laplace trend tests, bias tests) is presented.

• The Korean Journal of Applied Statistics
• /
• v.29 no.5
• /
• pp.807-822
• /
• 2016

The composite lognormal-GPD models (LN-GPD) enjoys both merits from log-normality for the body of distribution and GPD for the thick tailedness of the observation. However, in the estimation perspective, LN-GPD model performs poorly due to numerical instability. Therefore, a two-stage procedure, that estimates threshold first then estimates other parameters later, is a natural method to consider. This paper considers five nonparametric threshold estimation methods widely used in extreme value theory and compares their performance in LN-GPD parameter estimation. A simulation study reveals that simultaneous maximum likelihood estimation performs good in threshold estimation, but very poor in tail index estimation. However, the nonparametric method performs good in tail index estimation, but introduced bias in threshold estimation. Our method is illustrated to the service time of an Israel bank call center and shows that the LN-GPD model fits better than LN or GPD model alone.

• Imaging Science in Dentistry
• /
• v.41 no.4
• /
• pp.155-159
• /
• 2011

Purpose : This study was performed to determine the prevalence of maxillary canine impaction on a basis of a single panoramic radiograph in Bangladeshi population. Materials and Methods : A random sample of seven hundred panoramic radiographs was collected from the patient record of a dental clinic. All the selected panoramic radiographs were taken from January 2009 to August 2010 by a single panoramic radiograph machine with the same exposure time (19 seconds) for all radiographs. One hundred and twenty panoramic radiographs were excluded to minimize the selection bias. In a dim lit room, an observer assessed the radiographs on a standard radiographic light box. The position of the impacted maxillary canine was recorded in line with the longitudinal axis of a tooth using the edge of a metal ruler. Data were subsequently put on SPSS 11.5 software and chi-square (${\chi}^2$) tests were applied to find out the association. Results : Among 580 panoramic radiographs it was found that impacted maxillary canines were present in only 7 (1.2%) radiographs. A statistical significant difference was found between the age of the patients and the vertical position of the impacted canines (p=0.000) and between the age of the patients and the horizontal position of the impacted canines (p=0.003). Conclusion : The prevalence was found to be low compared with the present study from the limitation of panoramic image. Further study needs to include three-dimensional imaging modality.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.1 s.39
• /
• pp.45-53
• /
• 2006

Finite failure NHPP models presented in the literature exhibit either constant, monotonic increasing or monotonic decreasing failure occurrence rates per fault. In this paper, Goel-Okumoto and Yamada-Ohba-Osaki model was reviewed, proposes the $x^2$ reliability model, which can capture the increasing nature of the failure occurrence rate per fault. Algorithm to estimate the parameters used to maximum likelihood estimator and bisection method, model selection based on SSE, AIC statistics and Kolmogorov distance, for the sake of efficient model, was employed. Analysis of failure using real data set, SYS2(Allen P.Nikora and Michael R.Lyu), for the sake of proposing shape parameter of the $x^2$ distribution using the degree of freedom, was employed. This analysis of failure data compared with the $x^2$ model and the existing model using arithmetic and Laplace trend tests, Kolmogorov test is presented.

• Journal of Veterinary Clinics
• /
• v.20 no.1
• /
• pp.7-11
• /
• 2003

The selection of a test as a reference with no perfect sensitivity and specificity may lead to bias, yielding distortion of the diagnostic performance. This means it is inappropriate to use imperfect diagnostic tests as a reference method to identify infected patients in clinical environments. In this study, diagnostic performance of rapid urease test, polymerase chain reaction (PCR), and histology of gastric biopsy specimens for diagnosing Helicobacter pylori infection separately and in combination was estimated by using non-linear regression. Based on this approach, the sensitivity, specificity and likelihood ration positive and negative values for each test were as follows: urease test 99.9%, 99.9%, 99.9%, 99.6%, respectively; PCR 88.6%, 99.9%, 99.9%, 70.5%, respectively; histology 78.3%, 97%, 78.3%, 97%, respectively. Predictive values for positive and negative changes with varying Combination of three diagnostic tests employed in the study gives no substantial benefit for practitioners to screen infected patients, and urease test or PCR represents an appropriate single test in clinical environments.

• The Korean Journal of Applied Statistics
• /
• v.26 no.6
• /
• pp.1033-1041
• /
• 2013

In this paper, we investigate several variance estimators for pps systematic sampling. Unfortunately, there is no unbiased variance estimators for a systematic sample because systematic sampling can be regarded as a random selection of one cluster. This study provides guidance on which variance estimator may be more appropriate than others in several circumstances. We judge the efficiency of variance estimators for systematic sampling based on of their relative biases and relative mean square error. Also, we investigate variance estimation problems for two-stage systematic sampling applied for the Food Raw Material Consumption Survey and the Establishment Labor Force Survey simulation study, in order to consider the popular two-stage pps systematic sample design for establishment and household survey in Korea.

• Journal of Korea Technology Innovation Society
• /
• v.21 no.2
• /
• pp.738-766
• /
• 2018

The purpose of this paper is to figures out the impact on the business performance based on the case studies about the establishment of automated smart factories supported by the government. In this study, the effectiveness of supporting business is verified by comparing supported company with non-supported ones using methods such as T-test and ANOVA. The PSM method was used to solve the selection bias issue between the experimental group and the controlled group. The research results have shown that the effect of the supporting business to the automated system was tenuous, and the amount of sales and research and development costs was increased after a certain schedule passed in case of the supporting project to the smart factory. There is some time lag to appear the effect of the government supporting businesses and the supporting business to the automated system leads to long term sales increase by increasing parameters like research and development costs rather than direct influence. Therefore, this research will be useful information for the process of establishing useful basic data and policies which helps to secure new budget Government Supporting Businesses and find ways improve the business.

• Korea journal of population studies
• /
• v.29 no.3
• /
• pp.1-27
• /
• 2006

Labor market participation and occupational status for workers majoring in(natural) science and engineering are estimated and compared with workers of other majors at three levels: employment, prestigious occupations, and good occupations. For this, we utilized 2% Public Use Sample of 2000 Korea Census. The results of two-stage probit models, which adjust sample selection bias, do not support the argument that graduates of science and engineering majors are relatively disadvantaged. Workers of engineering majors are more likely to have 'good occupations' at their early job careers, but their advantages fade away quickly as they are aging. Especially at their 40s, their probability of having 'good occupations' start to be likely lower than workers of social science majors. This may be due to low human capital accumulation rates at work places along with quickly outdated skills which are acquired in colleges.