• The Korean Journal of Applied Statistics
• /
• v.31 no.3
• /
• pp.409-416
• /
• 2018

Significant research has been conducted in the financial sector on the behavior of investors in the stock market. In this paper, we directly measure the degree of interest using the ranking of the frequency mentioned in the stock message board operated by Daum Communications Corp. and test the fact that the higher ranking of the frequency results in the higher stock returns in order to investigate the attention effect on the stock returns in the Korean stock market. We also propose and apply the likelihood ratio test procedure for order restricted hypotheses in order to test the attention effect. The test results shows that the higher rank in the frequency mentioned in the message board is related to stock returns (p-value < $10^{-6}$). Therefore, we conclude that an investors' attention effects exist in the Korean stock market.

• The Korean Journal of Applied Statistics
• /
• v.25 no.1
• /
• pp.29-43
• /
• 2012

Financial data such as stock index returns and exchange rates have the properties of heavy tail and asymmetry compared to normal distribution. When we estimate VaR using the GARCH model (with the conditional return distribution of normal) it shows the tendency of the lower estimation and clustering in the losses over the estimated VaR. In this paper, we argue that this problem can be resolved through the adaptation of the unbounded Johnson distribution as that of the condition return. We also compare this model with the GARCH with the conditional return distribution of normal and student-t. Using the losses exceed the ex-ante VaR, estimates, we check the validity of the GARCH models through the failure proportion test and the clustering test. We nd that the GARCH model with conditional return distribution of unbounded Johnson provides an appropriate estimation of the VaR and does not occur the clustering of violations.

• The Korean Journal of Applied Statistics
• /
• v.34 no.6
• /
• pp.863-874
• /
• 2021

In this paper, we propose a post-selection inference procedure for the fused lasso signal approximator (FLSA). The FLSA finds underlying sparse piecewise constant mean structure by applying total variation (TV) semi-norm as a penalty term. However, it is widely known that this convex relaxation can cause asymptotic inconsistency in change points detection. As a result, there can remain false change points even though we try to find the best subset of change points via a tuning procedure. To remove these false change points, we propose a post-selection inference for the FLSA. The proposed procedure applies a permutation test based on CUSUM statistic. Our post-selection inference procedure is an extension of the permutation test of Antoch and Hušková (2001) which deals with single change point problems, to multiple change points detection problems in combination with the FLSA. Numerical study results show that the proposed procedure is better than naïve z-tests and tests based on the limiting distribution of CUSUM statistics.

• Journal of the Korean Statistical Society
• /
• v.11 no.2
• /
• pp.109-117
• /
• 1982

In this paper, a preliminary study is performed on the subset selection procedures which are based on the trimmed means and the Hodges-Lehmann estimator derived from the Wilcoxon test. The proposed procedures are compared to the Gupta's rule through a small smaple Monte Carlo study. The results show that the procedures based on the robust estimators are successful in terms of efficiency and robustness.

• The Korean Journal of Applied Statistics
• /
• v.23 no.1
• /
• pp.73-79
• /
• 2010

Missing values for unit root processes are imputed by the most recent observations. Treating the imputed observations as if they are complete ones, semiparametric unit root tests are extended to missing value situations. Also, an invariance principle for the partial sum process of the imputed observations is established under some mild conditions, which shows that the extended tests have the same limiting null distributions as those based on complete observations. The proposed tests are illustrated by analyzing an unequally spaced real data set.

• Journal of the Korean Data and Information Science Society
• /
• v.14 no.1
• /
• pp.119-129
• /
• 2003

We propose a new logistic regression model of normality curves for normal(diseased) and abnormal(nondiseased) classifications by neural networks in data mining. The fitted logistic regression lines are estimated, interpreted and plotted by the neural network technique. A few goodness-of-fit test statistics for normality are discussed and the performances by the fitted logistic regression lines are conducted.

• Communications for Statistical Applications and Methods
• /
• v.3 no.3
• /
• pp.31-37
• /
• 1996

A hierarchical loglinear model comparison method is developed which is based on the well kmown partitioned likelihood ratio statistiss. For any paels, we can regard the difference of the geedness of fit statistics as the variation explained by a full model, and develop a partial test to compare a full model with a reduced model in that hierarchy. Note that this has similar arguments as that of the regression analysis.

• Proceedings of the Korean Statistical Society Conference
• /
• 2003.05a
• /
• pp.183-189
• /
• 2003

A momentum threshold autoregressive (MTAR) model, a nonlinear autoregressive model, is analyzed in a Bayesian framework. Parameter estimation in the presence of missing data is done by using Markov chain Monte Carlo methods. We also propose simple Bayesian test procedures for asymmetry and unit roots. The proposed method is applied to a set of Korea unemployment rate data and reveals evidence for asymmetry and a unit root.

• Journal of the Korean Data and Information Science Society
• /
• v.15 no.4
• /
• pp.911-920
• /
• 2004

We try receiver operating characteristic(ROC) curves by neural networks of logistic function. The models are shown to arise from model classification for normal (diseased) and abnormal (nondiseased) groups in medical research. A few goodness-of-fit test statistics using normality curves are discussed and the performances using neural networks of logistic function are conducted.

• Communications for Statistical Applications and Methods
• /
• v.3 no.1
• /
• pp.145-153
• /
• 1996

Nonparametric tests for comparing umbrella pattern treatment effects with a control in a one-way layout were studied in Chen and Wolfe (1993). In this paper we propose a modification that improves the power of the Chen-Wolfe test. The results of a Monte Carlo power study are discussed.