• 한국데이터정보과학회:학술대회논문집
• /
• 2001.10a
• /
• pp.67-75
• /
• 2001

A completely randomized growth curve model was defined by Zerbe(1979). We propose the fully significant difference procedure for multiple comparisons of completely randomized growth curve model. The standard F test is useful tool to multiple comparisons of the completely randomized growth curve model. The proposed method is applied to experimental data.

• Journal of the Korean Data and Information Science Society
• /
• v.14 no.2
• /
• pp.313-323
• /
• 2003

For the growth curve model with arbitrary covariance structure, known as unstructured covariance matrix, the problems of detecting outliers are discussed in this paper. In order to detect outliers in the growth curve model, the test statistics using U-distribution is established. After detecting outliers in growth curve model, we test homo and/or hetero-geneous covariance matrices using PSR Quasi-Bayes Criterion. For illustration, one numerical example is discussed, which compares between before and after outlier deleting.

• The KIPS Transactions:PartD
• /
• v.11D no.3
• /
• pp.597-604
• /
• 2004

Accurate software cost estimation is essential to both developers and customers. Most of the cost estimating models based on the size measure methods, such as LOC and FP, are obtained through size estimation. The accuracy of size estimation directly influences the accuracy of cost estimation. As a result, the overall structure of regression-based cost models applies the power function based on software size. Many growth phenomenon in nature such as the growth in living organism, performance of technology, and learning capability of human show an S-shaped curve. This paper proposes a model which estimates the developing effort by using the growth curve. The presented model assumes that the relation cost and size follows the growth curve. The appropriateness of the growth curve model based on Function Point, Full-Function Point and Use-Case Point, which are the general methods in estimating the software size have been confirmed. The proposed growth curve model shows similar performance with power function model. In conclusion, the growth curve model can be applied in the estimation of the software cost.

• IE interfaces
• /
• v.23 no.3
• /
• pp.205-212
• /
• 2010

The learning curve model is a mathematical form which represents the relationship between the manufacturing experience and its effectiveness. The semiconductor manufacturing is widely known as an appropriate example for the learning effect due to its complicated manufacturing processes. In this paper, I propose a new compound learning curve model for semiconductor products in which the general learning curve model and the growth curve are composed. The dependent variable and the effective independent variables of the model were abstracted from the existing learning curve models and selected according to multiple regression processes. The simulation results using the historical DRAM data show that the proposed compound learning curve model is one of adequate models for describing learning effect of semiconductor products.

• Journal of the Korean Data and Information Science Society
• /
• v.10 no.2
• /
• pp.369-385
• /
• 1999

For the growth curve model with arbitrary covariance structure, known as unstructured covariance matrix, the problems of detecting outliers are discussed in this paper. In order to detect outliers in the growth curve model, the likelihood ratio testing statistics in mean shift model is established and its distribution is derived. After we detected outliers in growth curve model, we test homo and/or hetero-geneous covariance matrices using PSR Quasi-Bayes Criterion. For illustration, one numerical example is discussed, which compares between before and after outlier deleting.

• Korean Journal of Agricultural Science
• /
• v.43 no.4
• /
• pp.623-633
• /
• 2016

A total of 6,973 steer growth records of Hanwoo breeding bull's progeny test data collected from 1989 to 2015 were analyzed to identify the most appropriate growth curve among three growth curve models (Gompertz, Logistic and von Bertalanffy). The Gompertz growth curve model equation was $W_t=990.5e^{{-2.7479e}^{-0.00241t}}$, the Logistic growth curve model equation was $W_t=772(1+8.3314e^{-0.00475t})^{-1}$, and the von Bertalanffy growth curve model equation was $W_t=1,196.4(1-0.646e^{-0.00162t})^3$. The Gompertz model parameters A, b, and k were estimated to be $990.5{\pm}10.27$, $2.7479{\pm}0.0068$, and $0.00241{\pm}0.000028$, respectively. The inflection point age was estimated to be 421 days and the weight of inflection point was 365.3 kg. The Logistic model parameters A, b, and k were estimated to be $772.0{\pm}4.12$, $8.3314{\pm}0.0453$, and $0.00475{\pm}0.000033$, respectively. The inflection point age was estimated to be 445 days and the weight of inflection point was 385.0 kg. The von Bertalanffy model parameters A, b, and k were estimated to be $1196.4{\pm}18.39$, $0.646{\pm}0.0010$, and $0.00162{\pm}0.000027$, respectively. The inflection point age was estimated to be 405 days and the weight of inflection point was 352.0 kg. Mature body weight of the von Bertalanffy model was 1196.4 kg, the Gompertz model was 990.5 kg, and the Logistic model was 772.0 kg. The difference between actual and estimated weights was similar in the Logistic model and the von Bertalanffy model. The difference between market weight and estimated market weight was the lowest in the Gompertz model. The growth curve using the von Bertalanffy model showed the lowest mean square error.

• The KIPS Transactions:PartD
• /
• v.11D no.7 s.96
• /
• pp.1451-1458
• /
• 2004

Current software reliability growth models based on Gompertz growth curve are all logarithmic type. Software reliability growth models based on logarithmic type Gompertz growth curve has difficulties in parameter estimation. Therefore this paper proposes a software reliability growth model based on the logistic type Gompertz growth curie. Its usefulness is empirically verified by analyzing the failure data sets obtained from 13 different software projects. The parameters of model are estimated by linear regression through variable transformation or Virene's method. The proposed model is compared with respect to the average relative prediction error criterion. Experimental results show that the pro-posed model performs better the models based on the logarithmic type Gompertz growth curve.

• Journal of Korean Society for Quality Management
• /
• v.23 no.1
• /
• pp.95-105
• /
• 1995

The error structure of nonlinearized technological growth models, such as, the Pearl curve, the Gompertz curve and the Wei bull growth curve, has zero mean and a constant variance over time. Transformed models, however, like the linearized Fisher-Pry model. the linearized Gompertz growth curve, and the linearized Weibull growth curve have increasing variance from t = 0 to the inflection point.

• Journal of Environmental Science International
• /
• v.31 no.9
• /
• pp.793-801
• /
• 2022

This study was carried out to provide basic data for logical forest management by developing a site index curve reflecting the current growth characteristics of Cryptomeria japonica stands in Korea. The height growth model was developed using the Chapman-Richards, Schumacher, Gompertz, and Weibull algebraic difference equations, which are widely used in growth estimation, for data collected from 119 plots through the 7th National Forest Inventory and stand survey. The Chapman-Richards equation, with the highest model fit, was selected as the best equation for the height growth model, and a site index curve was developed using the guide curve method. To compare the developed site index curve with that on the yield table, paired T-tests with a significance level of 5% were performed. The results indicated that there were no significant differences between the site index curve values at all ages, and the p-value was smaller after the reference age than before. Therefore, the site index curve developed through this study reflects the characteristics of the changing growth environment of C. japonica stands and can be used in accordance with the site index curve on the current yield table. Thus, this information can be considered valuable as basic data for reasonable forest management.

• Journal of Korean Society for Quality Management
• /
• v.25 no.1
• /
• pp.44-55
• /
• 1997

In order to determine procedures for a, pp.opriate model selection of technological growth curves, numerous time series that were representative of growth behavior were collected according to data characteristics. Three different growth curve models were fitted onto data sets in an attempt to determine which growth curve models achieved the best forecasts for types of growth data. The analysis of the results gives rise to an a, pp.oach for selecting a, pp.opriate growth curve models for a given set of data, prior to fitting the models, based on the characteristics of the goodness of fit test.