• Journal of the Korean Data and Information Science Society
• /
• v.25 no.1
• /
• pp.177-185
• /
• 2014

Under bivariate normal distribution assumptions, the interaction and quadratic terms are needed in the logistic regression model with two predictors. However, depending on the correlation coefficient and the variances of two conditional distributions, the interaction and quadratic terms may not be necessary. Although the need for these terms can be determined by comparing the two scatter plots, it is not as useful for interaction terms. We explore the structure and usefulness of the 3-D residual plot as a tool for dealing with interaction in logistic regression models. If predictors have an interaction effect, a 3-D residual plot can show the effect. This is illustrated by simulated and real data.

• Journal of The Korean Society of Grassland and Forage Science
• /
• v.19 no.4
• /
• pp.325-332
• /
• 1999

A manure management plan is important for all dairy operations. This experiment was conducted to determine the effect of different nitrogen(N) application rates of liquid cattle manure on the forage quality, N recovery, and total forage yields of corn-oats cropping system and soil properties at the National Livestock Research Institute, RDA, Suweon in 1997. Eight treatments consisting of no fertilizer, chemical fertilizer $320kg\;N\;ha^{-1}$ as urea, the continuous applications of 320, 640 and $960kg\;N\;ha^{-1}$ as liquid cattle manure(LCM), the residual effects of 200, 400 and $600kg\;N\;ha^{-1}$ as liquid cattle manure were arranged in a randomized complete block design with three replications. Mean plant height of fall sown oats was 70 and 61cm at the continuous application and the residual effect plots, respectively. Mean dry matter percent of fall sown oats at the residual effect plots was higher by 0.9% than that of oats at the continuous application plots, but there were no differences among all treatments. Mean crude protein(CP), acid detergent fiber(ADF), and neutral detergent fiber (NDF) contents of fall sown oats at the continuous application plots were higher by 1.0, 1.6, and 3.1%, respectively, than those of the residual effect plots. Also, there were significant differences among treatments (P<0.05). Total forage dry matter yields of corn and oats cropping system were ranged from 11,365 to $25,668kg\;ha^{-1}$ among the treatments. The yield was orderly ranked as LCM $960kg\;N\;ha^{-1}$ > LCM $600kg\;N\;ha^{-1}$ > LCM $640kg\;N\;ha^{-1}$ > LCM $400kg\;N\;ha^{-1}$ (P<0.05). Compared with the control, manurial value(MV) was 158 and 139% for the plot of the LCM $960kg\;N\;ha^{-1}$ and that of the LCM $600kg\;N\;ha^{-1}$, respectively. N recovery percent of fall sown oats was the highest at the plot of the LCM $200kg\;N\;ha^{-1}$ by 50%, and then was higher in order of the LCM $400kg\;N\;ha^{-1}$, LCM $600kg\;N\;ha^{-1}$, and LCM $320kg\;N\;ha^{-1}$. Contents of exchangeable cation in the soil of the residual effect plots was higher than that of the continuous application plots. These results suggest that the LCM $600kg\;N\;ha^{-1}$ may be the most effective in total forage dry matter yields, manurial value, N recovery, and utilizing liquid manure N under the corn and oats double cropping system.

• Journal of the Korean Data and Information Science Society
• /
• v.21 no.1
• /
• pp.21-32
• /
• 2010

Graphical regression is a paradigm for obtaining regression information using plots without model assumptions. The general goal of this approach is to find lowdimensional sufficient summary plots without loss of important information. Model assessments using residual plots are less likely to be successful in models that are not linear. As an alternative approach, marginal model plots provide a general graphical method for assessing the model. We apply the methods of graphical regression and model assessment using marginal model plots to the logistic regression model.

• Korean Journal of Organic Agriculture
• /
• v.11 no.4
• /
• pp.93-102
• /
• 2003

This research was made to determine the optimum mixing ratio cattle manure and food waste investigating the effect that gets the growth and reproductive efficiency of earthworm and productivity of earthworm casts at processing process when handled cattle manure and food waste by vermicomposting, in order to establish the treatment system of organic wastes by vermicomposting. Survival ratio of earthworm was highest in the mixing ratio 80~100% : 20~0% of cattle manure and food Waste, and the increasing ratio was highest in cattle manure 100%, and the number of young worms, the weight of young worms and the productivity of earthworm casts in plots more than the mixing ratio 60% of cattle manure were significantly higher than in the other treatment plots(p<0.05). Total nitrogen and carbon contents in earthworm cast were decreased when rearing time of earthworm was increased. Carbon and nitrogen rate(C/N) of earthworm cast in plots more than the mixing ratio 80% of cattle manure was significantly higher than in the other treatment plots(p<0.05). pH in earthworm cast was higher than that in residual matter. The contents of electrolytic conductivity in the higher mixing ratio of food waste were significantly higher than those in the other treatment plots(p<0.05).

• Communications for Statistical Applications and Methods
• /
• v.7 no.1
• /
• pp.1-12
• /
• 2000

We explore the structure and usefulness of CERES plot as a basic tool for dealing with curvature as a function of the new predictor in nonlinear regression. If a predictor has a nonlinear effect and there are nonlinear relationships among the predictors the partial residual plot and augmented partial residual plot are not able to display the correct functional form of the predictor. Unlike these plots the CERES plot can show the correct from. In situations where nonlinearity exists in two predictors we extend the idea of CERES plot to three dimensions, This is illustrated by simulated data.

• Communications for Statistical Applications and Methods
• /
• v.11 no.3
• /
• pp.575-582
• /
• 2004

We explore the structure and usefulness of CERES plot as a basic tool for dealing with curvature as a function of the new predictor in generalized linear models. If a predictor has a nonlinear effect and there are nonlinear relationships among the predictors, the partial residual plot and augmented partial residual plot are not able to display the correct functional form of the predictor. Unlike these plots, the CERES plot can show the correct form. This is illustrated by simulated data.

• International Journal of Reliability and Applications
• /
• v.6 no.2
• /
• pp.79-85
• /
• 2005

We show how comparative mean residual life functions (MRL) can be used to give unique insights into strengths of materials data. Recall that Weibull's original reliability function was developed studying and fitting strengths for various materials. This creative comparing of MRL functions approach can be used for regular life data or any time to response data. We apply graphical MRL's to real data from tests of tensile strength of high quality engineered wood.

• The Korean Journal of Applied Statistics
• /
• v.24 no.5
• /
• pp.979-986
• /
• 2011

A linear regression method is commonly used to analyze data because of its simplicity and applicability; however, it is well known that data may contain some outliers and influential cases that may have a harmful effect on a statistical analysis. Thus detection and examination of outliers or influential cases are important parts of data analysis. In detecting multiple outliers, masking effects usually occur and make it difficult to identify the true outliers. We propose to use dynamic plots as a method resistant to masking effect. The procedure using dynamic plots is useful to find appropriate basic sets with which a dependent outliers detection method start and detect a true outliers set. Examples are given to demonstrate the effectiveness of the suggested idea.

• The Korean Journal of Applied Statistics
• /
• v.13 no.2
• /
• pp.407-414
• /
• 2000

Carroll and Ruppert(1988) analyzed the esterase assay data with regression model based on quasi-likelihood. Jung and Lee(1997) introduced a goodness-of-fit test for testing the adequacy of the quasi-likelihood and claimed that there is no gross inadequacy with the model because their test was not rejected. However, Lee and Xelder(199S)'s residual plots revealed that the model did not sufficiently reflect the increase of the variance with that of the mean. In this paper, we re-analyze the esterase assay data with the joint modelling of mean and dispersion in Lee and l\elder(1998) and evaluate the validity of the fitted model by applying the residual plots. And it is illustrated that Lee and Nelder(199S)'s restricted likelihood is more efficient in goodness-of-fit test for the dispersion model.

• Asian-Australasian Journal of Animal Sciences
• /
• v.14 no.10
• /
• pp.1383-1388
• /
• 2001

To explore the factors restricting animal performance in relation to sward structure under a strip-grazing system, measurements of sward factors, herbage intake and milk production at 3 levels of herbage allowance were made on perennial ryegrass (Latium perenne L.) sward for 3 experimental periods. About 29%, 36% and 52% of the biomass offered was removed by grazing in high $(42kg\;OM{\cdot}day^{-1}{\cdot}head^{-1})$, medium $(30kg\;OM{\cdot}day^{-1}{\cdot}head^{-1})$ and low $(18kg\;OM{\cdot}day^{-1}{\cdot}head^{-1})$ herbage allowance plots. Live leaf material was much more affected by grazing under different herbage allowance levels than dead material or leaf sheath. Grazing with a low herbage allowance decreased the proportion of live lamina by 93% and live lamina density by 96% before grazing. The density of dead material plus sheath was decreased by 17% after grazing at a low allowance, while it slightly increased or remained constant in the plots applied with high and medium allowances, respectively. The highly significant (p<0.01) correlations between herbage allowance and proportion (r=0.94) and density (r=0.91) of live lamina in residual sward after grazing were observed. Daily herbage intakes in the plots with high and medium levels of herbage allowance were not significantly different at $15.3kg\;OM{\cdot}head^{-1}$ in average, whereas with low level it decreased to $13.9kg\;OM{\cdot}head^{-1}$. Daily milk production was significantly (p<0.05) declined from $22.3kg{\cdot}head^{-1}$ (at high herbage allowance) to $19.7kg{\cdot}head^{-1}$ (at low herbage allowance). The data obtained clearly indicated that herbage intake and milk production were highly affected by the characteristics of residual sward, which were closely related to the level of herbage allowance.