• Communications for Statistical Applications and Methods
• /
• v.10 no.1
• /
• pp.135-144
• /
• 2003

This work is concerned with comparison of the recently developed disparity measures for the partial association model in three dimensional categorical data. Data are generated by using simulation on each term in the log-linear model equation based on the partial association model, which is a proposed method in this paper. This alternative Monte Carlo methods are explored to study the behavior of disparity measures such as the power divergence statistic I(λ), the Pearson chi-square statistic X$^2$, the likelihood ratio statistic G$^2$, the blended weight chi-square statistic BWCS(λ), the blended weight Hellinger distance statistic BWHD(λ), and the negative exponential disparity statistic NED(λ) for moderate sample sizes. We find that the power divergence statistic I(2/3) and the blended weight Hellinger distance family BWHD(1/9) are the best tests with respect to size and power.

• Journal of Families and Better Life
• /
• v.20 no.1
• /
• pp.45-56
• /
• 2002

The main purposes of this article are to introduce the theoretical backgrounds and empirical application methods of two different Models for the function of expenditure, and to compare the goodness-o(-fit of the two models: a single-equation model and a complete-system-of-demand-equation model. For the empirical analysis of the single-equation model, a linear formula and a double-leg formula were employed. In order to test the complete-system-of-demand-equation model empirically, the \"Linear Approximation/Almost Ideal Demand System (LA/AIDS)" was used. The independent variables were the total living expense and expenditure categories Price index. The data used in this study were obtained from the quarterly statistics of "The Annual Report on the Urban Family Income and Expenditure Survey (Dosigagyeyonbo)" and "The Annual Report on the Consumer Price Index (Sobijamulgajaryo)," for the years 1994 to 1997. The goodness-of-fit (R-square) was higher with the complete-system-of-demand-equation model than with the single-equation model for the budget share on food (excluding eating-out expenses) and for the share on cultural and recreational activities. However, there was no difference between the two models in terms of the proportion of the expenditure on automobile fuel.fuel.

• Korean Journal of Agricultural Science
• /
• v.38 no.4
• /
• pp.761-767
• /
• 2011

The objective of this study was to predict total bacteria count of pork meats by using the portable electronic nose systems developed throughout two stages of the prototypes. Total bacteria counts were measured for pork meats stored at $4^{\circ}C$ for 21days and compared with the signals of the electronic nose systems. PLS(Partial least square), PCR (Principal component regression), MLR (Multiple linear regression) models were developed for the prediction of total bacteria count of pork meats. The coefficient of determination ($R_p{^2}$) and root mean square error of prediction (RMSEP) for the models were 0.789 and 0.784 log CFU/g with the 1st system for the pork loin, 0.796 and 0.597 log CFU/g with the 2nd system for the pork belly, and 0.661 and 0.576 log CFU/g with the 2nd system for the pork loin respectively. The results show that the developed electronic system has potential to predict total bacteria count of pork meats.

• The Korean Journal of Applied Statistics
• /
• v.4 no.2
• /
• pp.117-127
• /
• 1991

Coefficient of determination $R^2$ is most frequently used descriptive measure in practical use of linear regression analysis. But there have been controversies on defining this measure in the cases of linear regression without the intercept, weighted linear regression and robust linear regression. Several authors such as Kvalseth(1985) and Willet and Singer(1988) proposed many variations of $R^2$ to meet the situations. However, theire measures are not satisfactory due to the lack of a universal principle. In this study, we propose a unfied approach to defining the coefficient of determination $R^2$ using the concept of likelihood distance. This new measure is in good accordance with typical $R^2$ in linear regression and, moreover, can be applied to nonlinear regression models and generalized linear models such as logit and log-linear models.

• Journal of Korean Society on Water Environment
• /
• v.36 no.6
• /
• pp.489-499
• /
• 2020

Effective science-based management of the basin water resources requires an understanding of the characteristics of the streams, such as the baseflow discharge. In this study, the base flow was estimated in the two watersheds with the least artificial factors among the Nakdong River watersheds, as determined using the chemical hydrograph separation technique. The 16-year (2004-2019) discontinuous observed stream flow and electrical conductivity data in the Total Maximum Daily Load (TMDL) monitoring network were extended to continuous daily data using the TANK model and the 7-parameter log-linear model combined with the minimum variance unbiased estimator. The annual base flows at the upper Namgang Dam basin and the upper Nakdong River basin were both analyzed to be about 56% of the total annual flow. The monthly base flow ratio showed a high monthly deviation, as it was found to be higher than 0.9 in the dry season and about 0.46 in the rainy season. This is in line with the prevailing common sense notion that in winter, most of the stream flow is base flow, due to the characteristics of the dry season winter in Korea. It is expected that the chemical-based hydrological separation technique involving TANK and the 7-parameter log-linear models used in this study can help quantify the base flow required for systematic watershed water environment management.

• Journal of Korea Water Resources Association
• /
• v.40 no.1 s.174
• /
• pp.39-50
• /
• 2007

This paper presents applications of the log-linear ROCOF(rate-of-occurrence-of-failure) and the Weibull ROCOF to model the failure rate of individual cast iron pipes in a water distribution system and provides a method of estimating the economically optimal replacement time of the pipes using the 'modified time-scale'. The performance of the two ROCOFs is examined using the maximized log-likelihood estimates of the ROCOFs for the two types of failure data: 'failure-time data' and 'failure-number data'. The optimal replacement time equations for the two models are developed by applying the 'modified time-scale' to ensure the numerical convergence of the estimated values of the model parameters. The methodology is applied to the case study water distribution cast iron pipes and it is found that the log-linear ROCOF has better modeling capability than the Weibull ROCOF when the 'failure-time data' is used. Furthermore, the 'failure-time data' is determined to be more appropriate for both ROCOFs compared to the 'failure-number data' in terms of the ROCOF modeling performances for the water mains under study, implying that recording each failure time results in better modeling of the failure rate than recording failure numbers in some time intervals.

• Bulletin of the Korean Chemical Society
• /
• v.27 no.2
• /
• pp.211-218
• /
• 2006

This work deals with 24 substances composed of nitrogen-containing heterocycles. The relationships between the chromatographic retention factor (k) and those physicochemical properties which are relevant in quantitative structure-properties relationship (QSPR) studies, such as the polarizability $(\alpha)$, molar refractivity (MR), lipophilicity (logP), dipole moment $(\mu)$, total energy $(E_{tot})$, heat of formation $(\Delta H_f)$, molecular surface area $(S_M)$, and binding energy $(E_b)$, were investigated. The accuracy of the simple linear regressions between the chromatographic retention and the descriptors for all of the compounds was satisfactory (correlation coefficient, $0.8 \leq r \leq 1.0$). The QSPR models of these nitrogen-containing heterocyclic compounds could be predicted with a multiple linear regression equation having the statistical index, r = 1.000. This work demonstrated the successful application of the multiple linear approaches through the development of accurate predictive equations for retention factors in liquid chromatography.

• Journal of the Korean Chemical Society
• /
• v.60 no.4
• /
• pp.225-234
• /
• 2016

The activity of 34 sulfonamide derivatives has been estimated by means of multiple linear regression (MLR), artificial neural network (ANN), simulated annealing (SA) and genetic algorithm (GA) techniques. These models were also utilized to select the most efficient subsets of descriptors in a cross-validation procedure for non-linear -log (IC50) prediction. The results obtained using GA-ANN were compared with MLR-MLR, MLR-ANN, SA-ANN and GA-ANN approaches. A high predictive ability was observed for the MLR-MLR, MLR-ANN, SA-ANN and MLR-GA models, with root mean sum square errors (RMSE) of 0.3958, 0.1006, 0.0359, 0.0326 and 0.0282 in gas phase and 0.2871, 0.0475, 0.0268, 0.0376 and 0.0097 in solvent, respectively (N=34). The results obtained using the GA-ANN method indicated that the activity of derivatives of sulfonamides depends on different parameters including DP03, BID, AAC, RDF035v, JGI9, TIE, R7e+, BELM6 descriptors in gas phase and Mor 32u, ESpm03d, RDF070v, ATS8m, MATS2e and R4p, L1u and R3m in solvent. In conclusion, the comparison of the quality of the ANN with different MLR models showed that ANN has a better predictive ability.

• Journal of Korean Society on Water Environment
• /
• v.23 no.2
• /
• pp.251-259
• /
• 2007

In this study three log-transformed linear regression models are compared with the focus of bias correction problem. The models are the traditional simple linear regression estimator (SL), the quasi maximum likelihood estimator (QMLE) and the minimum variance unbiased estimator (MVUE). Using such models, suspended solid loads can be estimated using the discharge - suspended solid data set that has been measured by NIER Nakdong River Water Environment Laboratory. As a result, SL shows negative bias for most values of the measured discharge range. QMLE is nearly unbiased for moderate values of the measured discharge range, but shows increasingly positive bias for either large or small value of the measured discharge range. MVUE is unbiased. It is also analyzed how the estimated regression coefficient and exponent are distributed along Nakdong river main stream.

• Journal of Korean Society of Occupational and Environmental Hygiene
• /
• v.6 no.1
• /
• pp.88-96
• /
• 1996

This study was conducted to establish model between lead and ZPP concentration in blood of workers exposed to lead. Workers employed in secondary smelting manufacturing industry showed $85.1{\mu}g/dl$ of blood lead level, exceeding $60{\mu}g/dl$, the Criteria for Removal defined by Occupational Safety and Health Act of Korea. Average blood lead level of workers in the battery manufacturing industry was $51.3{\mu}g/dl$, locating between $40{\mu}g/dl$ and $60{\mu}g/dl$, the Criteria for Requiring Medical Removal. Blood lead level of in the litharge and radiator manufacturing industry was below $40{\mu}g/dl$, the Criteria Requiring Temporary Medical Removal. Blood lead levels of workers by industry were Significantly different(p<0.05). 50(21 %) showed blood lead levels above $60{\mu}g/dl$, the Criteria for Removal and 66(27.7 %) showed blood lead levels between the Criteria for Requiring Medical Removal, $40-60{\mu}g/dl$. Thus, approximately 50 percent of workers indicated blood lead levels above $40{\mu}g/dl$, the Criteria Requiring Temporary Medical Removal and should receive medical examination and consultation including biological monitoring. Average ZPP level of workers employed in the secondary smelting industry was $186.2{\mu}g/dl$, exceeding above $150{\mu}g/dl$, the Criteria for Removal. Seventy seven of all workers(32.3 %) showed ZPP level above $100-150{\mu}g/dl$, the Criteria for Requiring Medical Removal. The most appropriate model for predicting ZPP in blood was log-linear regression model. Log linear regression models between lead and ZPP concentrations in blood was Log ZPP(${\mu}g/dl$) = -0.2340 + 1.2270 Log Pb-B(${\mu}g/dl$)(standard error of estimate: 0,089, ${\gamma}^2=0.4456$, n=238, P=0.0001), Blood-in-lead explained 44.56 % of the variance in log(ZPP in blood).