• The Journal of Engineering Geology
• /
• v.9 no.3
• /
• pp.253-265
• /
• 1999

Physical properties of Paleozoic sedimentary rocks in Gabsan formation in Jechon area were obtained by both geophysical well log methods and core property measurements, and the similarity and difference shown between the well log and core log responses were analyzed. The physical properties obtained are natural gamma, resistivity and density. From the difference in density response between the well log and core measurement, the need of correction for natural gamma effect on density log was strongly suggested. And fairly good correlation was obtained between well log and core properties, and among natural gamma, resistivity and density by applying natural gamma correction on density log. It is noted that shale in Gabsan formation reveals very high density, even higher than the density of adjacent non-porous limestone.

• The Journal of Engineering Geology
• /
• v.25 no.2
• /
• pp.281-290
• /
• 2015

Log density data were collected and compared with the core density data throughout the southern Korean Peninsula. The comparison reveals that the log densities obtained from gamma-gamma log are much lower than the core densities obtained from laboratory density measurement of core samples. The anomalously low log densities can be attributed to the small-source density log data. Correlation analysis reveals differences between densities derived from the two methods, indicating that a data quality problem arises when using small-source log data. The problem is probably due to the fact that small-source data have not been obtained under ideal conditions for maintaining the appropriate relationship between gamma response and formation density. The frequency distribution characteristics of formation density in the southern Korean Peninsula could be determined using the core and the standard-source log data which are well-correlated.

• 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 Korea Foresty Energy
• /
• v.17 no.1
• /
• pp.23-29
• /
• 1998

This study was carried out to develop the regression model for estimating biomass of natural Pinus densiflora forests by stand density in northeast Chinese area of Mt. Paekdu. Four allometric regression models(W=aD$^b$, W=a(D$^2$H)$^b$. logW=a+b$\cdot$ logD+cD and logW=a+b$\cdot$log(D$^2$H)+c(D$^2$H)) were used to estimate biomass for each of the tree components. The suitable regression model for estimating biomass of stem, bark and whole tree above ground was logW=a+b$\cdot$log(D$^2$H)+c(D$^2$H), and that for biomass of branch, needle and needle area, logW=a+b$\cdot$logD+cD for all of the stand density classes.

• Communications for Statistical Applications and Methods
• /
• v.7 no.1
• /
• pp.13-22
• /
• 2000

We consider local likelihood method with a smoothed version of the model density in stead of an original model density. For simplicity a model is assumed as the log-linear density then we were able to show that the proposed local density estimator is less affected by changes among observations but its bias increases little bit more than that of the currently used local density estimator. Hence if we use the existing method and the proposed method in a proper way we would derive the local density estimator fitting the data in a better way.

• Journal of Ecology and Environment
• /
• v.30 no.3
• /
• pp.251-255
• /
• 2007

Self-thinning was measured in Salix communities on Bam Island in Seoul at various age stages. $D^2H$ was used to estimate tree biomass, where D is stem diameter at breast height or 10 cm height for plants with height <1.5 m, and H is height. A log-log plot of density versus $D^2H$ and correlation analysis indicated a significant relationship between density and biomass with equation 'log $D^2H$ = -1.27 log N + 7.06'. This indicates that self-thinning affects biomass in the Salix community with -1.27 as the thinning coefficient. If we assume a thinning exponent -3/2, then the allometric coefficient of the equation, log w = a log $D^2H$ + b, is 1.18. This is much higher than that for any other species studied in Korea. There were statistically significant relationships between age and density and between age and basal area and these relationships suggest guidelines for transplantation of willows and for the assessment of Salix community restoration projects in riverine wetlands based on standard density, basal area, and age. The results of this study may also increase understanding of succession processes in Salix community restoration in riverine wetlands.

• Communications for Statistical Applications and Methods
• /
• v.19 no.1
• /
• pp.1-11
• /
• 2012

We present methods to study the log-density ratio of the conditional densities of the predictors given the response variable in the logistic regression model. This allows us to select which predictors 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. A simulation study shows that the linear and log terms are required in general. If the conditional distributions of xjy for the two groups overlap significantly, we need both the linear and log terms; however, only the linear or log term is needed in the model if they are well separated.

• Communications for Statistical Applications and Methods
• /
• v.10 no.2
• /
• pp.607-617
• /
• 2003

This paper offers a practical comparison of efficiency between local likelihood approach and conventional kernel approach in density estimation. The local likelihood estimation procedure maximizes a kernel smoothed log-likelihood function with respect to a polynomial approximation of the log likelihood function. We use two types of data driven bandwidths for each method and compare the mean integrated squares for several densities. Numerical results reveal that local log-linear approach with simple plug-in bandwidth shows better performance comparing to the standard kernel approach in heavy tailed distribution. For normal mixture density cases, standard kernel estimator with the bandwidth in Sheather and Jones(1991) dominates the others in moderately large sample size.

• Communications for Statistical Applications and Methods
• /
• v.4 no.3
• /
• pp.833-845
• /
• 1997

Fourier expansion is considered for the deconvolution problem of estimating a probability density function when the sample observations are contaminated with random noise. In the log-Fourier method of density estimation for data without noise, the logarithm of the unknown density function is approximated by a trigonometric function, the unknown parameters of which are estimated by maximum likelihood. The log-Fourier density estimation method, which has been considered theoretically by Koo and Chung (1997), is studied for the finite-sample case with noise. Numerical examples using simulated data are given to show the performance of the log-Fourier deconvolution.

• 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.