• Journal of the Korean Data and Information Science Society
• /
• v.23 no.1
• /
• pp.99-111
• /
• 2012

The log-density ratio of the conditional densities of the predictors given the response variable provides useful information for variable selection in the logistic regression model. In this paper, we consider the predictors that are needed and how they should be included in the model. If the conditional distributions are skewed, the distributions can be considered as gamma distributions. Under this assumption, linear and log terms are generally included in the model. The log-odds graph is a very useful graphical tool in this study. A graphical study is presented which shows that if the conditional distributions of x|y for the two groups overlap significantly, we need both the linear and quadratic terms. On the contrary, if they are well separated, only the linear or log term is needed in the model.

• Journal of the Korean Data and Information Science Society
• /
• v.18 no.1
• /
• pp.185-194
• /
• 2007

The information of covariates are available to do fully efficient fractional imputation(FEFI). The new method, FEFI with logistic regression is proposed to construct complete contingency tables. Jackknife method is used to get a standard errors of log-odds ratio from the completed table by the new method. Simulation results, when covariates have more information about categorical variables, reveal that the new method provides more efficient estimates of log-odds ratio than either multiple imputation(MI) based on data augmentation or complete case analysis.

• Asian Pacific Journal of Cancer Prevention
• /
• v.13 no.4
• /
• pp.1533-1537
• /
• 2012

In general, breast cancer is the most common malignancy among women in developed as well as some developing countries, often being the second leading cause of cancer mortality after lung cancer. Using a parametric log-logistic model to consider the effects of prognostic factors, the present study focused on the 5-year survival of women with the diagnosis of breast cancer in Southern Iran. A total of 1,148 women who were diagnosed with primary invasive breast cancer from January 2001 to January 2005 were included and divided into three prognosis groups: poor, medium, and good. The survival times as well as the hazard rates of the three different groups were compared. The log-logistic model was employed as the best parametric model which could explain survival times. The hazard rates of the poor and the medium prognosis groups were respectively 13 and 3 times greater than in the good prognosis group. Also, the difference between the overall survival rates of the poor and the medium prognosis groups was highly significant in comparison to the good prognosis group. Use of the parametric log-logistic model - also a proportional odds model - allowed assessment of the natural process of the disease based on hazard and identification of trends.

• Journal of the Korean Data and Information Science Society
• /
• v.22 no.1
• /
• pp.107-113
• /
• 2011

We present methods for studying the log-density ratio, which allow us to select which predictors are needed, and how they should be included in the logistic regression model. Under multivariate normal distributional assumptions, we investigate the form of the log-density ratio as a function of many predictors. The linear, quadratic and crossproduct terms are required in general. If two covariance matrices are equal, then the crossproduct and quadratic terms are not needed. If the variables are uncorrelated, we do not need the crossproduct terms, but we still need the linear and quadratic terms.

• Journal of Environmental Health Sciences
• /
• v.44 no.4
• /
• pp.380-390
• /
• 2018

Objective: A significant association between blood lead levels and hypertension has been reported in many studies. The relationship between cadmium and hypertension has been debated as well. We aimed to study the association of lead, cadmium, and both with hypertension in the Korean general population. Methods: We examined 5,967 adult men and 6,074 women who participated in the Korea National Health and Nutrition Examination Survey III-VI (2005, 2008-2013 years). Logistic regression models were used to examine the relationship between blood lead concentration and blood cadmium concentration and hypertension using logtransformed blood lead and cadmium concentrations as independent variables after covariate adjustment. Results: Adjusted for general characteristics, the odds ratio of log-lead to hypertension was 2.71 (1.82-4.03), and log-cadmium to hypertension was 2.52 (1.83-3.47). Estimates were found to be statistically significant (p<0.001). When a multiple logistic model was applied, the odds ratio of log-lead and log-cadmium for hypertension were 2.24 (1.50-3.36) and 2.24 (1.62-3.10), respectively. The standardized estimate coefficients of log-lead and logcadmium for hypertension were 4.77 and 6.65, respectively. Conclusion: We observed the association of blood lead concentration, blood cadmium concentration, and both with hypertension. This study suggests that exposure to lead and exposure to cadmium are both risk factors for hypertension.

• Communications for Statistical Applications and Methods
• /
• v.13 no.3
• /
• pp.755-764
• /
• 2006

Most graphical methods for categorical data can describe the structure of data and represent a measure of association among categorical variables. Among them the polyhedron plot represents sequential relationships among hierarchical log-linear models for a multidimensional contingency table. This kind of plot could be explored to describe the differences among sequential models. In this paper we suggest graphical methods, containing all the information, that reflect the relationship among all log-linear models in a certain hierarchical structure. We use the ideas of a correlation diagram.

• Communications for Statistical Applications and Methods
• /
• v.6 no.1
• /
• pp.43-52
• /
• 1999

The local influence method is adapted to quadratic discriminant analysis for the identification of influential observations affecting the estimation of probability density function probabilities and log odds. The method allows a simultaneous perturbation on all observations so that it can identify multiple influential observations. The proposed method is applied to a real data set and satisfactory result is obtained.

• The Korean Journal of Applied Statistics
• /
• v.18 no.2
• /
• pp.471-485
• /
• 2005

For categorical data analysis, the collapsibility were explained with the odds ratio (cross-product ratio). When these theories with these odds ratios are applied to real $2{\times}2{\times}K$ contingency tables, it is impossible to decide whether data are collapsible. Among graphical methods to represent odds ratios, Contour plot which is developed by Doi, Nakamura and Yamamoto (2001) could explain the structure of these data, but cannot decide on the collapsibility. In this paper, by using the Raindrop plot proposed by Barrowman and Myers (2003), we suggest an alternative method which can not only explain the structure of data, but also decide on the collapsibility.

• The Korean Journal of Applied Statistics
• /
• v.26 no.1
• /
• pp.141-149
• /
• 2013

We present methods for studying the log-density ratio that enables the selection of the predictors and the form to be included in the logistic regression model. Under bivariate normal distributional assumptions, we investigate the form of the log-density ratio as a function of two predictors. If two covariance matrices are equal, then the crossproduct and quadratic terms are not needed. If the variables are uncorrelated, we do not need the crossproduct terms, but we still need the linear and quadratic terms. We also explore other conditions in which the crossproduct and quadratic terms are not needed in the logistic regression model.

• Journal of Chest Surgery
• /
• v.54 no.2
• /
• pp.127-136
• /
• 2021

Background: This meta-analysis aimed to evaluate the incidence of tumor recurrence, postoperative myasthenia gravis, postoperative complications, and overall survival after limited versus total thymectomy for Masaoka stage I and II thymoma. Methods: A systematic search of the literature was conducted using the PubMed, Embase, MEDLINE, and Cochrane databases to identify relevant studies that compared limited and total thymectomy in Masaoka stage I-II patients. The quality of the included observational studies was assessed using the Newcastle-Ottawa Scale. The results of the meta-analysis were expressed as log-transformed odds ratios (log ORs), with 95% confidence intervals (CIs). Results: Seven observational studies with a total of 2,310 patients were included in the meta-analysis. There was an overall non-significant difference in favor of total thymectomy in terms of tumor recurrence (pooled log OR, 0.40; 95% CI, -0.07 to 0.87; p=0.10; I2=0%) and postoperative myasthenia gravis (pooled log OR, 0.12; 95% CI, -1.08 to 1.32; p=0.85; I2=22.6%). However, an overall non-significant difference was found in favor of limited thymectomy with respect to postoperative complications (pooled log OR, -0.21; 95% CI, -1.08 to 0.66; p=0.64; I2=36.1%) and overall survival (pooled log OR, -0.01; 95% CI, -0.68 to 0.66; p=0.98; I2=47.8%). Conclusion: Based on the results of this systematic review and meta-analysis, limited thymectomy as a treatment for stage I and II thymoma shows similar oncologic outcomes to total thymectomy.