• Proceedings of the Safety Management and Science Conference
• /
• 2011.04a
• /
• pp.701-705
• /
• 2011

The paper reviews Cronbaha's coefficient to measure a single source of error. On the contrary to classical measurement theory, the generalizability study can be used in the social survey design to calculate Generalizability Index (GI) and Dependability Index (DI) for measuring multiple sources of errors of behavior evaluation. The study proposes application guidelines to implement R:($A{\times}B$) mixed models that are composed of random factor and fixed factor.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.22 no.3
• /
• pp.75-87
• /
• 1980

Most hydro]ogic phenomena are the complex and organic products of multiple causations like climatic and hydro-geological factors. A certain significant correlation on the run-off in river basin would be expected and foreseen in advance, and the effect of each these causual and associated factors (independant variables; present-month rainfall, previous-month run-off, evapotranspiration and relative humidity etc.) upon present-month run-off(dependent variable) may be determined by multiple regression analysis. Functions between independant and dependant variables should be treated repeatedly until satisfactory and optimal combination of independant variables can be obtained. Reliability of the estimated function should be tested according to the result of statistical criterion such as analysis of variance, coefficient of determination and significance-test of regression coefficients before first estimated multiple regression model in historical sequence is determined. But some error between observed and estimated run-off is still there. The error arises because the model used is an inadequate description of the system and because the data constituting the record represent only a sample from a population of monthly discharge observation, so that estimates of model parameter will be subject to sampling errors. Since this error which is a deviation from multiple regression plane cannot be explained by first estimated multiple regression equation, it can be considered as a random error governed by law of chance in nature. This unexplained variance by multiple regression equation can be solved by stochastic approach, that is, random error can be stochastically simulated by multiplying random normal variate to standard error of estimate. Finally hybrid model on estimation of monthly run-off in nonhistorical sequence can be determined by combining the determistic component of multiple regression equation and the stochastic component of random errors. Monthly run-off in Naju station in Yong-San river basin is estimated by multiple regression model and hybrid model. And some comparisons between observed and estimated run-off and between multiple regression model and already-existing estimation methods such as Gajiyama formula, tank model and Thomas-Fiering model are done. The results are as follows. (1) The optimal function to estimate monthly run-off in historical sequence is multiple linear regression equation in overall-month unit, that is; Qn=0.788Pn+0.130Qn-1-0.273En-0.1 About 85% of total variance of monthly runoff can be explained by multiple linear regression equation and its coefficient of determination (R2) is 0.843. This means we can estimate monthly runoff in historical sequence highly significantly with short data of observation by above mentioned equation. (2) The optimal function to estimate monthly runoff in nonhistorical sequence is hybrid model combined with multiple linear regression equation in overall-month unit and stochastic component, that is; Qn=0. 788Pn+0. l30Qn-1-0. 273En-0. 10+Sy.t The rest 15% of unexplained variance of monthly runoff can be explained by addition of stochastic process and a bit more reliable results of statistical characteristics of monthly runoff in non-historical sequence are derived. This estimated monthly runoff in non-historical sequence shows up the extraordinary value (maximum, minimum value) which is not appeared in the observed runoff as a random component. (3) "Frequency best fit coefficient" (R2f) of multiple linear regression equation is 0.847 which is the same value as Gaijyama's one. This implies that multiple linear regression equation and Gajiyama formula are theoretically rather reasonable functions.

• Communications for Statistical Applications and Methods
• /
• v.12 no.2
• /
• pp.381-394
• /
• 2005

In order to estimate the damage of orchards due' to natural disasters such as typhoon, severe rain, freezing or frost, it is necessary to estimate the number of fruit bearing before and after the damage. To estimate the fruit bearing after the damages are easily done by delegations, but it cost too high to survey every insured farm household and calculate the fruit bearing before the damage. In this article, we suggest to use a random coefficient model to predict the numbers of fruit bearing in the orchards before the damage based on the tree age and the area information.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.24 no.8 s.179
• /
• pp.2074-2082
• /
• 2000

In this study, to investigate and to predict the crack growth behavior under variable amplitude loading, crack growth tests are conducted on 7075-T6 aluminum alloy. The loading wave forms are generated by normal random number generator. All wave forms have same average and RMS(root mean square) value, but different standard deviation, which is to vary the maximum load in each wave. The modified Forman's equation is used as crack growth equation. Using the retardation coefficient D defined in previous study, the load interaction effect is considered. The variability in crack growth process is described by the random variable Z which was obtained from crack growth tests under constant amplitude loading in previous work. From these, a statistical model is developed. The curves predicted by the proposed model well describe the crack growth behavior under variable amplitude loading and agree with experimental data. In addition, this model well predicts the variability in crack growth process under variable amplitude loading.

• Journal of Korean Society for Quality Management
• /
• v.32 no.1
• /
• pp.113-129
• /
• 2004

The reliability of the product can be improved by making the product less sensitive to noises. Especially, it Is important to make products robust against various noise factors encountered in production and field environments. In this paper, the phenomenon of degradation assumes a simple random coefficient degradation model to present analysis procedures of degradation data for robust experimental design. To alleviate weak points of previous studies, such as Taguchi's, Wasserman's, and pseudo failure time methods, novel techniques for analysis of degradation data using the cross array that regards amount of degradation as a dynamic characteristic for time are proposed. Analysis approach for degradation data using robust experimental design are classified by assumptions on parametric or nonparametric degradation rate(or slope). Also, a simulation study demonstrates the superiority of proposed methods over some previous works.

• Asian-Australasian Journal of Animal Sciences
• /
• v.31 no.10
• /
• pp.1542-1549
• /
• 2018

Objective: Because lactation periods in dairy cows lengthen with increasing total milk production, it is important to predict individual productivities after 305 days in milk (DIM) to determine the optimal lactation period. We therefore examined whether the random regression (RR) coefficient from 306 to 450 DIM (M2) can be predicted from those during the first 305 DIM (M1) by using a RR model. Methods: We analyzed test-day milk records from 85,690 Holstein cows in their first lactations and 131,727 cows in their later (second to fifth) lactations. Data in M1 and M2 were analyzed separately by using different single-trait RR animal models. We then performed a multiple regression analysis of the RR coefficients of M2 on those of M1 during the first and later lactations. Results: The first-order Legendre polynomials were practical covariates of RR for the milk yields of M2. All RR coefficients for the additive genetic (AG) effect and the intercept for the permanent environmental (PE) effect of M2 had moderate to strong correlations with the intercept for the AG effect of M1. The coefficients of determination for multiple regression of the combined intercepts for the AG and PE effects of M2 on the coefficients for the AG effect of M1 were moderate to high. The daily milk yields of M2 predicted by using the RR coefficients for the AG effect of M1 were highly correlated with those obtained by using the coefficients of M2. Conclusion: Milk production after 305 DIM can be predicted by using the RR coefficient estimates of the AG effect during the first 305 DIM.

• Communications for Statistical Applications and Methods
• /
• v.7 no.1
• /
• pp.87-96
• /
• 2000

Nonlinear time series prediction is derived and compared between statistic of modeling and neural network method. In particular mean squared errors of predication are obtained in generalized random coefficient model and generalized autoregressive conditional heteroscedastic model and compared with them by neural network forecasting.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.23 no.7 s.166
• /
• pp.1164-1172
• /
• 1999

In this study, to investigate the fatigue crack retardation behavior and the variability of retardation cycles, fatigue crack growth tests were conducted on 7075-T6 aluminum alloy under single tensile overload. A retardation coefficient, D was introduced to describe fatigue crack retardation behavior and a random variable, Z to describe the variability of fatigue crack growth. The retardation coefficient was separately formulated according to retardation behavior which is composed of delayed retardation part and retardation part. The random variable, Z was evaluated from experimental data which was obtained from fatigue crack growth tests under constant amplitude load. Using these variables, a probabilistic model was developed on the basis of the modified Forman's equation, and retardation behavior and cycles were predicted under certain overload condition. The predicted retardation curve well agrees with the trend of experimental crack retardation behavior. And this model well predicts the scatter of experimental retardation cycles.

• Structural Engineering and Mechanics
• /
• v.56 no.2
• /
• pp.257-273
• /
• 2015

Numerical value of correlation between effective parameters in the strength of a structure is as important as its stochastic properties in determining the safety of the structure. In this article investigation is made about the variation of coefficient of correlation between effective parameters in corrosion initiation time of reinforcement and the time of concrete cover cracking in reinforced concrete (RC) structures. Presence of many parameters and also error in measurement of these parameters results in uncertainty in determination of corrosion initiation and the time to crack initiation. In this paper, assuming diffusion process as chloride ingress mechanism in RC structures and considering random properties of effective parameters in this model, correlation between input parameters and predicted time to corrosion is calculated using the Monte Carlo (MC) random sampling. Results show the linear correlation between corrosion initiation time and effective input parameters increases with increasing uncertainty in the input parameters. Diffusion coefficient, concrete cover, surface chloride concentration and threshold chloride concentration have the highest correlation coefficient respectively. Also the uncertainty in the concrete cover has the greatest impact on the coefficient of correlation of corrosion initiation time and the time of crack initiation due to the corrosion phenomenon.

• Communications for Statistical Applications and Methods
• /
• v.27 no.5
• /
• pp.523-533
• /
• 2020

This paper suggests three available methods for finding nonnegative estimates of variance components of the random effects in mixed models. The three proposed methods based on the concepts of projections are called projection method I, II, and III. Each method derives sums of squares uniquely based on its own method of projections. All the sums of squares in quadratic forms are calculated as the squared lengths of projections of an observation vector; therefore, there is discussion on the decomposition of the observation vector into the sum of orthogonal projections for establishing a projection model. The projection model in matrix form is constructed by ascertaining the orthogonal projections defined on vector subspaces. Nonnegative estimates are then obtained by the projection model where all the coefficient matrices of the effects in the model are orthogonal to each other. Each method provides its own system of linear equations in a different way for the estimation of variance components; however, the estimates are given as the same regardless of the methods, whichever is used. Hartley's synthesis is used as a method for finding the coefficients of variance components.