• Journal of the Korean Statistical Society
• /
• v.23 no.2
• /
• pp.293-301
• /
• 1994

In this paper we propose a variable selection criterion minimizing influence curve in regression, and compare it with other criteria such as $C_p$(Mallows 1973) and adjusted coefficient of determination. Examples and extension to the generalized linear models are given.

• Communications for Statistical Applications and Methods
• /
• v.4 no.1
• /
• pp.1-10
• /
• 1997

Breiman(1995)에 의하여 제안된 nonnegative garrote을 Mallows $C_p$의 확장된 개념인 $C_H$의 관점에서 최소자승법, 능형회귀, 축소추정량, 변수선택등의 방법과 비교하였다. 또한 $C_H$를 각 관측값이 기여한 양으로 분해하여 nonnegative garrote의 경우 영향관측값을 검출할 수 있는 한가지 방법을 다루었다.

• Journal of Korean Society of Forest Science
• /
• v.79 no.3
• /
• pp.260-268
• /
• 1990

Two types of ridge regression estimators were compared with the ordinary least squares (OLS) estimator in order to select the "best" estimator when multicollinearitc existed. The ridge estimators were Mallows's (1973) $C_P$-like statistic, and Allen's (1974) PRESS-like statistic. The evaluation was conducted based on the predictive ability of a yield model developed by Matney et al. (1988). A total of 522 plots from the data of the Southwide Loblolly Pine Seed Source study was used in this study. All of ridge estimators were better in predictive ability than the OLS estimator. The ridge estimator obtained by using Mallows's statistic performed the best. Thus, ridge estimators can be recommended as an alternative estimator when multicollinearity exists among independent variables.

• The Korean Journal of Applied Statistics
• /
• v.11 no.2
• /
• pp.247-255
• /
• 1998

In this paper, a new subset selection problem in the Poisson model is considered under the normal predictors. It turns out that the subset model has bigger valiance than that of the Poisson model with random predictors and this has been used to derive new subset selection method similar to Mallows'$C_p$.

• Korean Journal of Food Science and Technology
• /
• v.32 no.6
• /
• pp.1271-1277
• /
• 2000

The extracts from tomatoes, apples, carrots, mallows, watercreses+pine needles, Angelica keiskei Koiz, jujubes and lemons were selected and mixed at the ratio of 3 : 3 : 3 : 1/2 : 1/2 : 1/2 : 1/2 : 1/5 on the basis of sensory evaluation. The mixed extracts were divided into three lots and treated as follows. The first lot was heated for 15 sec at $96^{\circ}C$ without centrifugation and filtration, the second filtered through a ultramembrane filter. For the third one, the ultrafiltrate combined with autoclaved retentates on the membrane filter and the previous centrifugal precipitation. The mixed juices were stored in the glass bottles with atmosphere or in film package with nitrogen gas. And then they were stored at $4^{\circ}$ and $20^{\circ}C$. During storage the treated juices showed $pH\;4.07{\sim}4.10$, titratable acidity $66.35{\sim}84.08$, soluble solid $7{\sim}9^{\circ}Brix$, reducing sugar $5.42{\sim}6.97%$, glucose $1.96{\sim}2.30%$ and fructose $3.46{\sim}4.14%$. The ultrafiltered juices showed yellow color, different from orange color of other treatment lots. Peroxidase activity and microbial population were inhibited by thermal treatment and ultrafiltration. The browning effects of the mixed juice of fruits and vegetables during storage were caused by ascorbic acid oxidation and non-enzymatic browning reaction, which could be reduced by change and packing with nitrogen gas instead of atmosphere inside bottles.

• Korean Journal of Food Science and Technology
• /
• v.30 no.1
• /
• pp.90-96
• /
• 1998

An experiment to make mixed juices carrying the freshness and other specific characteristics of vegetables and fruits which are useful for the prevention and treatment of various diseases was attempted on the emphases of pretreatment methods, combination of fruits and vegetables, and elimination of microorganisms. Blanch in boiling water prior to extraction for green vegetables, addition of ascorbic acid during extraction for tomatoes and apples, or addition of ascorbic acid after blanch in 3% acetic acid for carrots was effective to keep colors and suspended solids in liquid extract. On the basis of sensory evaluation the extracts from tomatoes, apples. carrots. mallows, watercreses+pine needles, Angelica keiskei Koiz, jujubes and lemons were selected and mixed at the ratio of 3 : 3 : 3 : 1/2 : 1/2 : 1/2 : 1/2 : 1/5. The mixed extracts were pasteurized for 15sec at $96^{\circ}C$ or filtered through a ultramembrane filter. While the centrifuge precipitation and retentates on the membrane filter were autoclaved and combined with ultrafiltrates. The mixed juices showed $pH\;4.07{\sim}4.10$ titratable acidity $66.35{\sim}84.08$, soluble solid $7{\sim}9^0Brix$, reducing sugar $5.42{\sim}6.97%$, glucose $1.96{\sim}2.30%$, fructose $3.46{\sim}4.14%$ and high content of K, Mg and Ca. Ultrafiltration showed better quality scores in color, juice. Peroxidase and microorganisms were inactivated by thermal treatment and ultrafiltration.

• Journal of Animal Science and Technology
• /
• v.55 no.5
• /
• pp.373-380
• /
• 2013

The study aimed to develop prediction models of primal cut yield using body measurements of Hanwoo steers in Korea. The progeny of 874 steers at Hanwoo Improvement Main Center from 2008 to 2010 were recorded. Pearson's correlation coefficients for primal cuts and other traits were estimated. Primal cuts were adjusted for slaughter date and age using the SAS GLM procedure. Afterwards, a stepwise regression was performed on each primal cut by fitting body measurement traits. An independent covariable was selected at the highest coefficient of determination with the greater fitness model using Mallows's Cp statistic. Results showed that primal cuts were significantly influenced by slaughter date (P<0.01). The age at slaughter, however, was only significant for the top round (P<0.05). There was a moderate to high correlation between chest girth and tenderloin (0.54), loin (0.74), and rib (0.80). Most primal cut percentages were negatively related to BFT. Similar negative to low positive correlations were observed for primal cut percentage and body size traits. In addition, a correlation of 0.21 was observed between rib percentage and chest girth. The regression of body measurements on the adjusted primal cuts were significant for later traits. Regression estimates revealed that wither height, body length, rump length, hip bone width, and chest girth are important for primal cut weight and percentage determination. In particular, chest girth was always important for primal cut weight estimates.