• Communications for Statistical Applications and Methods
• /
• 제11권3호
• /
• pp.583-595
• /
• 2004

For the Korean Economically Active Population Survey(EAPS), we consider the composite estimator based on logistic regression model to estimate the unemployment rate for small areas(Si/Gun). Also, small area estimation technique based on hierarchical generalized linear model is proposed to include the random effect which reflect the characteristic of the small areas. The proposed estimation techniques are applied to real domestic data which is from the Korean EAPS of Choongbuk. The MSE of these estimators are estimated by Jackknife method, and the efficiencies of small area estimators are evaluated by the RRMSE. As a result, the composite estimator based on logistic model is much more efficient than others and it turns out that the composite estimator can produce the reliable estimates under the current EAPS system.

• 품질경영학회지
• /
• 제26권1호
• /
• pp.143-160
• /
• 1998

This article is concerned with the selection of subsets of predictor variables to be included in bulding the binary response logistic regression model. It is based on a Bayesian aproach, intended to propose and develop a procedure that uses probabilistic considerations for selecting promising subsets. This procedure reformulates the logistic regression setup in a hierarchical normal mixture model by introducing a set of hyperparameters that will be used to identify subset choices. It is done by use of the fact that cdf of logistic distribution is a, pp.oximately equivalent to that of $t_{(8)}$/.634 distribution. The a, pp.opriate posterior probability of each subset of predictor variables is obtained by the Gibbs sampler, which samples indirectly from the multinomial posterior distribution on the set of possible subset choices. Thus, in this procedure, the most promising subset of predictors can be identified as that with highest posterior probability. To highlight the merit of this procedure a couple of illustrative numerical examples are given.

• 한국근적외분광분석학회:학술대회논문집
• /
• 한국근적외분광분석학회 2001년도 NIR-2001
• /
• pp.1245-1245
• /
• 2001

Food adulteration is a serious consumer fraud and a matter of concern to food processors and regulatory agencies. A range of analytical methods have been investigated to facilitate the detection of adulterated or mis-labelled foods & food ingredients but most of these require sophisticated equipment, highly-qualified staff and are time-consuming. Regulatory authorities and the food industry require a screening technique which will facilitate fast and relatively inexpensive monitoring of food products with a high level of accuracy. Near infrared spectroscopy has been investigated for its potential in a number of authenticity issues including meat speciation (McElhinney, Downey & Fearn (1999) JNIRS, 7(3), 145-154; Downey, McElhinney & Fearn (2000). Appl. Spectrosc. 54(6), 894-899). This report describes further analysis of these spectral sets using a hierarchical approach and binary decisions solved using logistic regression. The sample set comprised 230 homogenized meat samples i. e. chicken (55), turkey (54), pork (55), beef (32) and lamb (34) purchased locally as whole cuts of meat over a 10-12 week period. NIR reflectance spectra were recorded over the wavelength range 400-2498nm at 2nm intervals on a NIR Systems 6500 scanning monochromator. The problem was defined as a series of binary decisions i. e. is the meat red or white\ulcorner is the red meat beef or lamb\ulcorner, is the white meat pork or poultry\ulcorner etc. Each of these decisions was made using an individual binary logistic model based on scores derived from principal component or partial least squares (PLS1 and PLS2) analysis. The results obtained were equal to or better than previous reports using factorial discriminant analysis, K-nearest neighbours and PLS2 regression. This new approach using a combination of exploratory and logistic analyses also appears to have advantages of transparency and the use of inherent structure in the spectral data. Additionally, it allows for the use of different data transforms and multivariate regression techniques at each decision step.

• 한국근적외분광분석학회:학술대회논문집
• /
• 한국근적외분광분석학회 2001년도 NIR-2001
• /
• pp.1152-1152
• /
• 2001

Food adulteration is a serious consumer fraud and a matter of concern to food processors and regulatory agencies. A range of analytical methods have been investigated to facilitate the detection of adulterated or mis-labelled foods & food ingredients but most of these require sophisticated equipment, highly-qualified staff and are time-consuming. Regulatory authorities and the food industry require a screening technique which will facilitate fast and relatively inexpensive monitoring of food products with a high level of accuracy. Near infrared spectroscopy has been investigated for its potential in a number of authenticity issues including meat speciation (McElhinney, Downey & Fearn (1999) JNIRS, 7(3), 145 154; Downey, McElhinney & Fearn (2000). Appl. Spectrosc. 54(6), 894-899). This report describes further analysis of these spectral sets using a hierarchical approach and binary decisions solved using logistic regression. The sample set comprised 230 homogenized meat samples i. e. chicken (55), turkey (54), pork (55), beef (32) and lamb (34) purchased locally as whole cuts of meat over a 10-12 week period. NIR reflectance spectra were recorded over the wavelength range 400-2498nm at 2nm intervals on a NIR Systems 6500 scanning monochromator. The problem was defined as a series of binary decisions i. e. is the meat red or white\ulcorner is the red meat beef or lamb\ulcorner, is the white meat pork or poultry\ulcorner etc. Each of these decisions was made using an individual binary logistic model based on scores derived from principal component or partial least squares (PLS1 and PLS2) analysis. The results obtained were equal to or better than previous reports using factorial discriminant analysis, K-nearest neighbours and PLS2 regression. This new approach using a combination of exploratory and logistic analyses also appears to have advantages of transparency and the use of inherent structure in the spectral data. Additionally, it allows for the use of different data transforms and multivariate regression techniques at each decision step.

• Journal of the Korean Statistical Society
• /
• 제29권4호
• /
• pp.407-422
• /
• 2000

This article is concerned with the selecting predictor variables to be included in building a class of binary response t-link regression models where both probit and logistic regression models can e approximately taken as members of the class. It is based on a modification of the stochastic search variable selection method(SSVS), intended to propose and develop a Bayesian procedure that used probabilistic considerations for selecting promising subsets of predictor variables. The procedure reformulates the binary response t-link regression setup in a hierarchical truncated normal mixture model by introducing a set of hyperparameters that will be used to identify subset choices. In this setup, the most promising subset of predictors can be identified as that with highest posterior probability in the marginal posterior distribution of the hyperparameters. To highlight the merit of the procedure, an illustrative numerical example is given.

• Communications for Statistical Applications and Methods
• /
• 제12권3호
• /
• pp.625-634
• /
• 2005

A procedure is proposed to identify multiple outliers in the logistic regression. It detects the leverage points by means of hierarchical clustering of the robust distances based on the minimum covariance determinant estimator, and then it employs a V-mask type criterion on the scatter plot of robust residuals against robust distances to classify the observations into vertical outliers, bad leverage points, good leverage points, and regular points. Effectiveness of the proposed procedure is evaluated on the basis of the classic and artificial data sets, and it is shown that the procedure deals very well with the masking and swamping effects.

• Journal of Preventive Medicine and Public Health
• /
• 제43권6호
• /
• pp.513-522
• /
• 2010

Objectives: The purpose of this study was to define the association between the medical utilization of osteoarthritis patient and its related factors. Methods: We used the 2005 Korean National Health and Nutrition Survey data and we enrolled 2833 participants who were forty or older and who were diagnosed as having osteoarthritis by a doctor within 1 year and who had suffered from osteoarthritis for more than 3 months. The Andersen behavioral model was used as the analytic framework, and the variables were categorized into predisposing, enabling, and need factors. To determine the influence of each variable on the medical utilization of osteoarthritis patient, we applied hierarchical logistic regression analysis with two stages: the first stage included the predisposing and enabling factors and the second stage included the need factors. Results: On the hierarchical logistic analysis, the variables of personal income, the type of medical security, the duration of arthritis related symptoms within 1 month, the subjective health status and the duration of osteoarthritis showed a statistically significant association with medical utilization in men. And the variables of age, limitation activity due to osteoarthritis, arthritis related symptoms within 1 month, and the subjective health status had a statistically significant association with medical utilization in women. Conclusions: The patients who tend to receive less care are those who suffer less from symptoms of osteoarthritis, those who are within the initial phase, or those with a low-level severity of osteoarthritis. It is necessary to encourage patients to receive the treatment in the initial phase.

• 대한안전경영과학회지
• /
• 제15권4호
• /
• pp.145-152
• /
• 2013

The purpose of this study was to investigate the effect of risk awareness on injury experience in quick delivery service workers. Risk awareness has complicate characteristics such as its level of worker and worker's decision about the level of other's risk perception. Data were collected by interview survey with structured questionnaire about injury experience, risk perception, work characteristics, and socio-demographic characteristics of quick delivery service workers by cross sectional survey design in 2012. The sample size was 120 respondent of quick delivery service workers. Statistical method for this study was hierarchical logistic regression method with 3 different models using socio-demographic characteristics and work characteristics and risk perception, etc. The difference between the level of risk perception of quick delivery service and other's was statistically significant effect on the experience of injury. Especially the higher the level of risk perception of quick delivery service workers is than other's, the lower the injury experience of quick delivery service worker is. The limitation of this study can be found in survey design. The future study for investigation of mechanism of the combined effect of risk perception of quick delivery service workers and others on injury experience.

• Asian Pacific Journal of Cancer Prevention
• /
• 제15권20호
• /
• pp.8801-8807
• /
• 2014

Purpose: The aim of the study was to evaluate knowledge, attitudes and behaviors of Turkish women over 20 years old on cervix cancer. Materials and Methods: This descriptive study was performed at a primary care center covering 246 women using a questionnaire composed of 3 sections and 38 questions. The data were analyzed using descriptive statistics, chi-square test in univariate analysis and multivariate hierarchical logistic regression analysis. Results: Of the 93.7% women who knew about cervical cancer, 68.0% of them had heard pap smear test and 46.1% had actually undergone a Pap smear once or more throughout their lives. According to the results of the hierarchical logistic regression analysis about factors affecting the Pap smear test; in Model 1, increase in age and education levels, in Model 2 and Model 3 increase in age and cervical cancer information points were determined. The most important information source for cervical cancer was TV-radio/media (59.9%) and health care workers (62.8%) for pap smear test. Conclusions: Although most women have heard of cervical cancer, knowledge about cervical cancer and also Pap smear screening rate are significantly lower. Having Pap smear test for women was affected by age and knowledge level about cervical cancer. Informing women about cervical cancer would be an important intervention.

• 대한안전경영과학회지
• /
• 제16권3호
• /
• pp.257-266
• /
• 2014

This study was planned to investigate the effect of the exposure to hazard factors on work environment satisfaction. Existing researches about job satisfaction have focused on the general working conditions, such as working hours, wage, human relationship, job task and so on. Korean Working Conditions Survey was used for this study because that relevant questions were included. The effect of the exposure to hazard factors on work environment satisfaction may be produced by hierarchical regression analysis because of comparison with existing model for work environment satisfaction. The exposure to hazards factors were statistically significant effect on work environment satisfaction after adjusting other confounding variables, such as gender, age, educational level, job security, work hour, work load, work autonomy, social support, etc. This study has some limitation because that KWCS was cross sectional survey. Some researches about the causal effect and its mechanism may be suggested as future study.