• KIEAE Journal
• /
• v.15 no.5
• /
• pp.13-20
• /
• 2015

Purpose: In order to upgrade the energy performance of existing building, energy audit stage should be implemented first because it is useful method to find where the problems occur and know how much time and cost consumption for retrofit. In overseas researches, three levels of audit is proposed whereas there are no standards for audit in Korea. Besides, most studies use dynamic simulation in detail like audit level 3 even though the level 2 can save time and cost than level 3. Thus, this paper focused on audit level 2 and proposed the audit method with the simple linear regression analysis model. Method: Two parameters were considered for the simple regression analysis, which were the monthly electric use and the mean outdoor temperature data. The former is a dependent variable and the latter is a independent variable, and the building's energy performance profile was estimated from the regression analysis method. In this analysis, we found the abnormal point in cooling season and the more detailed analysis were conducted about the three heat source equipments. Result: Comparing with real and predicted models, the total consumption of predicted model was higher than real value as 23,608 kWh but it was the results that was reflected the compulsory control in 2013. Consequently, it was analyzed that the revised model could save the cooling energy as well as reduce peak electric use than before.

• Korean Journal of Veterinary Research
• /
• v.53 no.2
• /
• pp.73-76
• /
• 2013

The aim of this study was to produce a simple and inexpensive technique for estimating the obturator foramen area (OFA) from young calves based on the hypothesis that OFA can be extrapolated from simple linear measurements. Three linear measurements - dorsoventral height, craneocaudal width and total perimeter of obturator foramen - were obtained from 55 bovine hemicoxae. Different algorithms for determining OFA were then produced with a regression analysis (curve fitting) and statistical analysis software. The most simple equation was OFA ($mm^2$) = [3,150.538 + ($36.111^*CW$)] - [147,856.033/DH] (where CW = craneocaudal width and DH = dorsoventral height, both in mm), representing a good nonlinear model with a standard deviation of error for the estimate of 232.44 and a coefficient of multiple determination of 0.846. This formula may be helpful as a repeatable and easily performed estimation of the obturator foramen area in young bovines. The area of the obturator foramen magnum can thus be estimated using this regression formula.

• Journal of Information Technology Applications and Management
• /
• v.20 no.4
• /
• pp.221-234
• /
• 2013

In this paper, we report bankruptcy risk level forecasting result for automobile parts manufacturing industry. With the premise that upstream supply risk and downstream demand risk could impact on automobile parts industry bankruptcy level in advance, we draw upon industry input-output table to use the economic indicators which could reflect the extent of supply and demand risk of the automobile parts industry. To verify the validity of each economic indicator, we applied simple linear regression for each indicators by varying the time lag from one month (t-1) to 12 months (t-12). Finally, with the valid indicators obtained through the simple regressions, the composition of valid economic indicators are derived using stepwise linear regression. Using the monthly automobile parts industry bankruptcy frequency data accumulated during the 5 years, R-square values of the stepwise linear regression results are 68.7%, 91.5%, 85.3% for the 3, 6, 9 months time lag cases each respectively. The computational testing results verifies the effectiveness of our approach in forecasting bankruptcy risk forecasting of the automobile parts industry.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.20 no.3
• /
• pp.17-29
• /
• 1995

Recently, neural network models have been employed as an alternative to regression analysis for point estimation or function fitting in various field. Thus far, however, no theoretical or empirical guides seem to exist for selecting the tool which the most suitable one for a specific function-fitting problem. In this paper, we evaluate performance of three major function-fitting techniques, regression analysis and two neural network models, back-propagation and linear-Hebbian-learning neural networks. The functions to be fitted are simple linear ones of a single independent variable. The factors considered are size of noise both in dependent and independent variables, portion of outliers, and size of the data. Based on comutational results performed in this study, some guidelines are suggested to choose the best technique that can be used for a specific problem concerned.

• The Journal of Information Technology
• /
• v.3 no.1
• /
• pp.37-44
• /
• 2000

The purchasing estimate price of diamond is affected by the factors of carat, color, clarity, certificate, cut and price with the unit of $/carat. The object of this study is to obtain the linear regression model for such purchasing estimate price and to test statistically. The optimum model is the simple regression model of $^y{\;}:{\;}10^2{\;}/{\;}(-1.5575{\;}+{\;}0.3099{\;}logx){\;}+{\;}{\varepsilon}$ statistically satisfied by the lack of fit test and has the characteristics of normality, constant variance and symmetry.

• Communications for Statistical Applications and Methods
• /
• v.16 no.1
• /
• pp.75-83
• /
• 2009

Parallelism tests are proposed for slope in the simple linear regression models. In this paper, we suggest the parametric test using HSD testing method (Tukey,1953) and distribution-free test using Kruskal-wallis (1952) for more than three slopes. Monte Carlo simulation study is adapted to compare the power of the proposed methods with Wilks' Lambda multivariate procedure.

• Communications for Statistical Applications and Methods
• /
• v.17 no.2
• /
• pp.141-151
• /
• 2010

Hybrid fuzzy regression analysis is used for integrating randomness and fuzziness into a regression model. Least squares support vector machine(LS-SVM) has been very successful in pattern recognition and function estimation problems for crisp data. This paper proposes a new method to evaluate hybrid fuzzy linear and nonlinear regression models with crisp inputs and fuzzy output using weighted fuzzy arithmetic(WFA) and LS-SVM. LS-SVM allows us to perform fuzzy nonlinear regression analysis by constructing a fuzzy linear regression function in a high dimensional feature space. The proposed method is not computationally expensive since its solution is obtained from a simple linear equation system. In particular, this method is a very attractive approach to modeling nonlinear data, and is nonparametric method in the sense that we do not have to assume the underlying model function for fuzzy nonlinear regression model with crisp inputs and fuzzy output. Experimental results are then presented which indicate the performance of this method.

• Communications for Statistical Applications and Methods
• /
• v.7 no.2
• /
• pp.574-574
• /
• 2000

Consider the problem of estimating regression function from a set of data which is contaminated by a long-tailed error distribution. The linear smoother is a kind of a local weighted average of response, so it is not robust against outliers. The kernel M-smoother and the lowess attain robustness against outliers by down-weighting outliers. However, the kernel M-smoother and the lowess requires the iteration for computing the robustness weights, and as Wang and Scott(1994) pointed out, the requirement of iteration is not a desirable property. In this article, we propose the robust nonparametic regression method which does not require the iteration. Robustness can be achieved not only by down-weighting outliers but also by transforming outliers. The rank transformation is a simple procedure where the data are replaced by their corresponding ranks. Iman and Conover(1979) showed the fact that the rank transformation is a robust and powerful procedure in the linear regression. In this paper, we show that we can also use the rank transformation to nonparametric regression to achieve the robustness.

• Communications for Statistical Applications and Methods
• /
• v.7 no.2
• /
• pp.575-583
• /
• 2000

Consider the problem of estimating regression function from a set of data which is contaminated by a long-tailed error distribution. The linear smoother is a kind of a local weighted average of response, so it is not robust against outliers. The kernel M-smoother and the lowess attain robustness against outliers by down-weighting outliers. However, the kernel M-smoother and the lowess requires the iteration for computing the robustness weights, and as Wang and Scott(1994) pointed out, the requirement of iteration is not a desirable property. In this article, we propose the robust nonparametic regression method which does not require the iteration. Robustness can be achieved not only by down-weighting outliers but also by transforming outliers. The rank transformation is a simple procedure where the data are replaced by their corresponding ranks. Iman and Conover(1979) showed the fact that the rank transformation is a robust and powerful procedure in the linear regression. In this paper, we show that we can also use the rank transformation to nonparametric regression to achieve the robustness.

• Korean Journal of Soil Science and Fertilizer
• /
• v.31 no.4
• /
• pp.359-367
• /
• 1998

In order to determine the nitrogen supplying capabilities (NSC) of corn fields, 47 field experiments were performed in Pennsylvania over 3 year from 1986 and NSCs were estimated by the regression analysis with chemical properties and soil attributes. Although the content of $NO_3-N$ in soil showed the best correlation with NSC ($R^2=0.518$), the standardized partial regression coefficient of $NO_3-N$ for NSC was 0.52, with some variations over the years. This value was slightly higher than those of the other properties which ranged from 0.001 to 0.351. Multiple linear regression with soil attributes for the evaluation of NSC was better than simple regression with $NO_3-N$. The coefficient of determination ($R^2$) for the evaluation of NSC was gradually increased; 0.599 with selected chemical properties, 0.698 with quantitative attributes(chemical properties and depth of Ap horizon), and 0.839 with quantitative and selected qualitative soil attributes. Consequently, in order to evaluate NSC, analysis by multiple linear regression with soil attributes was more reliable and better model than by the simple regression model.