• The Korean Journal of Applied Statistics
• /
• v.10 no.1
• /
• pp.177-187
• /
• 1997

This article considers the power performance of the tests in unbalanced two way mixed linear models with one fixed factor. The generalized least squares (GLS) F statistic testing no differences among the effects of the levels of the fixed factor is estimated using Henderson's method III, minimum norm quadratic unbiased estimator (MINQUE) with prior guess 1, maximum likelihood (ML) and resticted maximum likelihood (REML). We investigate the power performance of these test statistics. It can be shown, through simulation, that the GLS F statistics using four estimators produce similar type I error rates and power performance.

• The Korean Journal of Applied Statistics
• /
• v.19 no.1
• /
• pp.111-120
• /
• 2006

In a two-stage two-level balanced nested design, type I error rates for the parametric tests and the rank transformed tests for the main effects and the nested effects are in overall similar to each other. Furthermore, powers for the rank transformed statistic for the main effects and the nested effects in a two-stage two-level balanced nested design are generally superior to powers for the parametric statistic When the effect size and the sample size are increased, we can find that powers increase for the parametric statistic and the rank transformed statistic are dramatically improved. Especially for the case of the fixed effects in the asymmetric distributions such as an exponential distribution, powers for the rank transformed tests are quite high rather than powers for the parametric tests.

• Annual Conference on Human and Language Technology
• /
• 2010.10a
• /
• pp.194-196
• /
• 2010

휴대폰의 광범위한 보급으로 문자메시지의 사용이 급증하고 있다. 이와 동시에 사용자가 원하지 않는 광고성 스팸문자도 넘쳐나고 있다. 본 연구는 이러한 스팸문자메시지를 자동으로 판별하는 시스템을 개발하는 것이다. 우리는 기계학습방법인 지지벡터기계(Support Vector Machine)을 사용하여 시스템을 학습하였으며 자질의 선택은 카이제곱 통계량을 이용하였다. 실험결과 F1 척도로 약 95.5%의 정확률을 얻었다

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.05a
• /
• pp.905-908
• /
• 2010

Our purpose is to develope the system which detects splogs automatically among blogs on Web environment. After removing HTML of blogs, they are tagged by part of speech(POS) tagger. Words and their POS tags information is used as a feature type. Among features, we select useful features with $x^2$ statistics and train the SVM with the selected features. Our system acquired 90.5% of F1 measure with SPLOG data set.

• Proceedings of the Korean Statistical Society Conference
• /
• 2002.11a
• /
• pp.305-309
• /
• 2002

소지역에서 직접(direct) 시계열추정을 할 수 있다면, 소지역들 추정에서 최적선형 불편예측량(BLUP)을 일반화 시킬 수 있다. 특히 조사에서 얻어지는 관측 값의 오차가 시간상으로 상관관계가 있다면 Kalman-Filter(K-F)기법이 사용 될 수 있다. 이 연구는 소지역의 실업자 수 추정에서 K-F기법으로 경제활동인구수를 이용하여 현 시점의 소지역 실업자 수를 예측함수(BLUP)를 통해 추정하였다. 그리고 단순 회귀분석 추정치와 비교하였다.

• The Korean Journal of Applied Statistics
• /
• v.33 no.3
• /
• pp.297-308
• /
• 2020

We focus on the functional autoregressive conditional heteroscedasticity (fARCH) modelling to analyze intraday volatilities based on high frequency financial time series. Multivariate volatility models are investigated to approximate fARCH(1). A formula of multi-step ahead volatilities for fARCH(1) model is derived. As an application, in implementing fARCH(1), a choice of appropriate time interval for the intraday return is discussed. High frequency KOSPI data analysis is conducted to illustrate the main contributions of the article.

• The Korean Journal of Applied Statistics
• /
• v.31 no.4
• /
• pp.475-484
• /
• 2018

Gamma generalized linear models are useful for non-negative and skewed responses. However, these models have received less attention than Poisson and binomial generalized linear models. In particular, hypothesis testing for the significance of regression coefficients has not been thoroughly studied. In this paper we assess the performance of various test statistics for gamma generalized linear models based on numerical studies. Our results show that the likelihood ratio test and F-type test are generally recommended and that the partial deviance test should be avoided in practice.

• The Korean Journal of Applied Statistics
• /
• v.8 no.1
• /
• pp.119-131
• /
• 1995

Based on Monte-Carlo simulation results we propose a robust analysis of variance procedure by utilizing trimmed mean and Winsorized variance. We deal with mainly the one-way classification case. We evaluate the empirical distribution of a pseudo-F statistic based on symmetrically Winsorized sum of squares when the population is normally distributed.

• The Korean Journal of Applied Statistics
• /
• v.19 no.2
• /
• pp.231-240
• /
• 2006

It is well understood that a paired comparison (paired t test) provides better precision than a group comparison (two-sample t test), when the pairing is effective (the variation within a pair is small). However, when the variation among the pairs is sufficiently small, the group comparison is likely to yield a better result. To get a statistical explanation of this, we examine the two methods through an analogy to one-way and two-way analysis of variance. We introduce a new measure, R statistic, which is the ratio of their confidence interval lengths, as a quantitative criterion for comparing the two methods. The distribution of the Rf statistic is described by t and F distribution functions. Through this characterization, we show that the paired comparison can be better than group comparison when the variation among the pairs is statistically significantly large.

• Journal of the Korean Data and Information Science Society
• /
• v.21 no.2
• /
• pp.231-240
• /
• 2010

If only fixed effects exist in a 4 $\times$ 4 balanced incomplete block design, powers of FR statistic for testing a main effect show the highest level with a few replications. Under the exponential and double exponential distributions, FR statistic shows relatively high powers with big differences as compared with the F statistic. Further in a traditional balanced incomplete block design, powers of FR statistic having a fixed main effect and a random block effect show superior preference for all situations without regard to the effect size of a main effect, the parameter size and the type of population distributions of a block effect. Powers of FR statistic increase in a high speed as replications increase. Overall power preference of FR statistic for testing a main effect is caused by unique characteristic of a balanced incomplete block design having one main and block effect with missing observations, which sensitively responds to small increase of main effect and sample size.