• Journal of the Korea Society of Computer and Information
• /
• v.18 no.1
• /
• pp.177-183
• /
• 2013

In this paper, Cohen's kappa and weighted kappa are applied to measuring classification accuracy when performing classification in data minig. Cohen's kappa compensates for classifications that may be due to chance and is used for the data with nominal or ordinal scales. Especially, for the ordinal data, weighted kappa which measures the classification accuracy by quantifying the classification errors as weights is used. We used two weights (linear weight, quadratic weight) for calculations of weighted kappa. Also for the calculation and comparison of kappa and weighted kappa we used a real data set, fat-liver data.

• East Asian mathematical journal
• /
• v.31 no.5
• /
• pp.695-706
• /
• 2015

Let ${\mathcal{H}}$ be an infinite dimensional complex Hilbert space, and let $B({\mathcal{H}})$ be the algebra of all bounded linear operators on ${\mathcal{H}}$. Recall that an operator $T{\in}B({\mathcal{H})$ has property B(n) if ${\mid}T^n{\mid}{\geq}{\mid}T{\mid}^n$, $n{\geq}2$, which generalizes the class A-operator. We characterize the property B(n) of weighted shifts $S_{\lambda}$ over (${\eta},\;{\kappa}$)-type directed trees which appeared in the study of subnormality of weighted shifts over directed trees recently. In addition, we discuss the property B(n) of weighted shifts $S_{\lambda}$ over (2, 1)-type directed trees with nonzero weights are being distinct with respect to $n{\geq}2$. And we give some properties of weighted shifts $S_{\lambda}$ over (2, 1)-type directed trees with property B(2).

• Bulletin of the Korean Mathematical Society
• /
• v.40 no.2
• /
• pp.341-349
• /
• 2003

Let {$x_{nk}\;$\mid$1\;\leq\;k\;\leq\;n,\;n\;\geq\;1$} be an array of random varianbles and $\{a_n$\mid$n\;\geq\;1\}\;and\;\{b_n$\mid$n\;\geq\;1} be a sequence of constants with $a_n\;>\;0,\;b_n\;>\;0,\;n\;\geq\;1. In this paper, for array of row negatively associated(NA) random variables, we establish a general weak law of large numbers (WLLA) of the form (${\sum_{\kappa=1}}^n\;a_{\kappa}X_{n\kappa}\;-\;\nu_{n\kappa})\;/b_n$ converges in probability to zero, as $n\;\rightarrow\;\infty$, where {$\nu_{n\kappa}$\mid$1\;\leq\;\kappa\;\leq\;n,\;n\;\geq\;1$} is a suitable array of constants.

• Communications of the Korean Mathematical Society
• /
• v.28 no.4
• /
• pp.741-750
• /
• 2013

To study the operator inequalities, the notions of class A operators and quasi-class A operators are developed up to recently. In this paper, quasi-$A(n,{\kappa})$ class operator for $n{\geq}2$ and ${\kappa}{\geq}0$ is introduced as a new notion, which generalizes the quasi-class A operator. We obtain some structural properties of these operators. Also we characterize quasi-$A(n,{\kappa})$ classes for n and ${\kappa}$ via backward extension of weighted shift operators. Finally, we give a simple example of quasi-$A(n,{\kappa})$ operators with two variables.

• The Korean Journal of Applied Statistics
• /
• v.22 no.5
• /
• pp.1073-1084
• /
• 2009

For ordinal categorical $R{\times}R$ tables, a weighted measure of association, $H_{\omega}$, was proposed and its maximum likelihood estimator and asymptotic variance were drived. We redefined the last paradox of ${\kappa}$ and proved its relation to marginal distributions. We also introduced the new paradox of ${\kappa}$ and summaried the general relationships between ${\kappa}$ and marginal distributions.

• Journal of Nutrition and Health
• /
• v.29 no.9
• /
• pp.1021-1027
• /
• 1996

This study examined the patterns of nutrient intakes measured by 1-, 3-, 7-day recalls and records as well as food frequency questionnaire among 59 females volunteers enrolled in the university in Seoul, Korea. Over a 4 month period, a modified Willett food frequency questionnaire was administered once, and a 24-hour dietary recall was conducted 12 times and a weighted dietary record 14 times. From these 12 recalls and 14 records, 1-, 3-, 7-day data were randomly selected. For energy and 11 nutrients, group mean intakes derived from food frequency questionnaire were higher than from recalls and records. Group mean intakes from recalls and records showed little differences depending on days of dietary studies and dietary methods. Measures of agreement were calculated by weighted kappa and intraclass correlation coefficient values calculated for quintile categories while comparing to the results of 26 days recalls and records. Weighted kappa values ranged from 0.11 for riboflavin to 0.36 for vitamin C for and 1-day recall, and from 0.21 for iron to 0.31 for energy for the 1-day record. Weighted kappa values were increased as the number of days of dietary studies increased (0.34-0.57 for the 3-day recalls, 0.27-0.50 for the 3-day records, 0.50-0.68 for the 7-day recalls, and 0.50-0.65 for the 7-day records). Weighted kappa values for food frequency questionnaire were higher than the 1-day data, but lower than the 3-and-7day data(0.34 for energy, 0.31 for iron and 0.22 for vitamin C). Intraclass correlation coefficients ranged from 0.21 for vitamin A to 0.57 for calcium. The degrees of agreement by different methods and days of dietary study are lower in our study compared to agreement by different methods and days of dietary study are lower in our study compared to those in previously published studies for Western populations, partly due to the differences of data analysis methods as well as of dietary patterns between those samples and ours.

• Journal of the Korean Data and Information Science Society
• /
• v.27 no.4
• /
• pp.899-910
• /
• 2016

Asymptotic tests are often not suitable for the analysis of sparse ordered contingency tables as asymptotic p-values may either overestimate or underestimate the true pvalues. In this pater, we describe permutation procedures in which we compute exact or resampling p-values for a weighted specific-category agreement in ordered $k{\times}k$ contingency tables. We use the weighted specific-category kappa proposed by $Kv{\dot{a}}lseth$ to measure the extent to which two independent raters agree on the specific categories. We carried out comparison studies between exact p-values, resampling p-values and asymptotic p-values using $3{\times}3$ contingency data (real and artificial data sets) and $4{\times}4$ artificial contingency data.

• Journal of the Korean Society of Propulsion Engineers
• /
• v.4 no.4
• /
• pp.59-69
• /
• 2000

A numerical analysis based on two-dimensional, incompressible and compressible Navier-Stokes equations was carried out for double circular arc compressor cascade and the results are compared with available experimental data. The incompressible code based on SIMPLE algorithm adopts pressure weighted method and hybrid scheme for the convective terms. The compressible code with preconditioning method involves a upwind-biased scheme for the convective terms and LU-SGS scheme for temporal integration. Several turbulence models are evaluated by computing the turbulent viscous flows; Baldwin-Lomax, standard $\kappa$ -$\varepsilon$, $\kappa$ -$\varepsilon$ Lam. Bremhorst, standard $\kappa$-$\omega$, $\kappa$ -$\omega$ SST model.

• Communications of the Korean Mathematical Society
• /
• v.32 no.3
• /
• pp.765-778
• /
• 2017

Finding an initial feasible solution on the central path is the main difficulty of feasible interior-point methods. Although, some algorithms have been suggested to remedy this difficulty, many practical implementations often do not use perfectly centered starting points. Therefore, it is worth to analyze the case that the starting point is not exactly on the central path. In this paper, we propose a weighted-path following interior-point algorithm for solving the Cartesian $P_{\ast}({\kappa})$-linear complementarity problems (LCPs) over symmetric cones. The convergence analysis of the algorithm is shown and it is proved that the algorithm terminates after at most $O\((1+4{\kappa}){\sqrt{r}}{\log}{\frac{x^0{\diamond}s^0}{\varepsilon}}\)$ iterations.

• The Korean Journal of Applied Statistics
• /
• v.25 no.5
• /
• pp.719-731
• /
• 2012

Agreement analysis is conducted to assess reliability among rating results performed repeatedly on the same subjects by one or more raters. The kappa statistic is commonly used when rating scales are categorical. The simple and weighted kappa statistics are used to measure the degree of agreement between two raters, and the generalized kappa statistics to measure the degree of agreement among more than two raters. In this paper, we compare the performance of four different generalized kappa statistics proposed by Fleiss (1971), Conger (1980), Randolph (2005), and Gwet (2008a). We also examine how sensitive each of four generalized kappa statistics can be to the marginal probability distribution as to whether marginal balancedness and/or homogeneity hold or not. The performance of the four methods is compared in terms of the relative bias and coverage rate through simulation studies in various scenarios with different numbers of raters, subjects, and categories. A real data example is also presented to illustrate the four methods.