• Communications for Statistical Applications and Methods
• /
• v.29 no.5
• /
• pp.615-627
• /
• 2022

Principal Fitted Component (PFC) is a semi-parametric sufficient dimension reduction (SDR) method, which is originally proposed in Cook (2007). According to Cook (2007), the PFC has a connection with other usual non-parametric SDR methods. The connection is limited to sliced inverse regression (Li, 1991) and ordinary least squares. Since there is no direct comparison between the two approaches in various forward regressions up to date, a practical guidance between the two approaches is necessary for usual statistical practitioners. To fill this practical necessity, in this paper, we newly derive a connection of the PFC to covariance methods (Yin and Cook, 2002), which is one of the most popular SDR methods. Also, intensive numerical studies have done closely to examine and compare the estimation performances of the semi- and non-parametric SDR methods for various forward regressions. The founding from the numerical studies are confirmed in a real data example.

• The Korean Journal of Pain
• /
• v.30 no.4
• /
• pp.243-249
• /
• 2017

Pain is subjective, while statistics related to pain research are objective. This review was written to help researchers involved in pain research make statistical decisions. The main issues are related with the level of scales that are often used in pain research, the choice of statistical methods between parametric or nonparametric statistics, and problems which arise from repeated measurements. In the field of pain research, parametric statistics used to be applied in an erroneous way. This is closely related with the scales of data and repeated measurements. The level of scales includes nominal, ordinal, interval, and ratio scales. The level of scales affects the choice of statistics between parametric or non-parametric methods. In the field of pain research, the most frequently used pain assessment scale is the ordinal scale, which would include the visual analogue scale (VAS). There used to be another view, however, which considered the VAS to be an interval or ratio scale, so that the usage of parametric statistics would be accepted practically in some cases. Repeated measurements of the same subjects always complicates statistics. It means that measurements inevitably have correlations between each other, and would preclude the application of one-way ANOVA in which independence between the measurements is necessary. Repeated measures of ANOVA (RMANOVA), however, would permit the comparison between the correlated measurements as long as the condition of sphericity assumption is satisfied. Conclusively, parametric statistical methods should be used only when the assumptions of parametric statistics, such as normality and sphericity, are established.

• Communications for Statistical Applications and Methods
• /
• v.26 no.5
• /
• pp.519-526
• /
• 2019

Response dimension reduction in a sufficient dimension reduction (SDR) context has been widely ignored until Yoo and Cook (Computational Statistics and Data Analysis, 53, 334-343, 2008) founded theories for it and developed an estimation approach. Recent research in SDR shows that a semi-parametric approach can outperform conventional non-parametric SDR methods. Yoo (Statistics: A Journal of Theoretical and Applied Statistics, 52, 409-425, 2018) developed a semi-parametric approach for response reduction in Yoo and Cook (2008) context, and Yoo (Journal of the Korean Statistical Society, 2019) completes the semi-parametric approach by proposing an unstructured method. This paper theoretically discusses and provides insightful remarks on three versions of semi-parametric approaches that can be useful for statistical practitioners. It is also possible to avoid numerical instability by presenting the results for an orthogonal transformation of the response variables.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.13 no.4
• /
• pp.594-600
• /
• 2010

In this paper, we introduced non-parametric statisticals method that could analyse the field data and proposed application ways such as repair-part demand forcasting, MTBF estimation and trend analysis, identity comparison with two populations using the analytical results. In addition, we applied that to real field data which has been collected for about ten years from K series tracked vehicle. After that, we compared the results with those using traditional parametric statistical method, and verified the usability of them.

• The Korean Journal of Applied Statistics
• /
• v.30 no.5
• /
• pp.701-717
• /
• 2017

The interest of Korean society and government on future demographic structures is increasing due to rapid aging. Korea's mortality rate is decreasing, but the declined gap is variable. In this study, we compare the Lee-Carter, Lee-Miller, Booth-Maindonald-Smith model and functional data model (FDM) as well as Coherent FDM using non-parametric smoothing technique. We are then examine a reasonable model for projecting on mortality declined rate trend in terms of accuracy of mortality rate by ages and life expectancy. The possibility of using non-parametric techniques for the prediction of mortality in Korea was also examined. Based on the analysis results, FDM and Coherent FDM, which uses the non-parametric technique and reflects the trend of recent data, are excellent. As a result, FDM and Coherent FDM are good fit, and predictability is also excellent assuming no significant future changes.

• Journal of the Korean Data and Information Science Society
• /
• v.28 no.3
• /
• pp.685-695
• /
• 2017

The traditional mixture of experts (ME) modeled the gate network using a certain parametric function. However, if the assumed parametric function does not properly reflect the true nature, the prediction strength of ME would become weak. For example, the parametric ME often uses logistic or multinomial logistic models for the network model. However, this could be very misleading if the true nature of the data is quite different from those models. Although, in this case, we may develop more flexible parametric models by extending the model at hand, we will never be free from such misspecification problems. In order to alleviate such weakness of the parametric ME, we propose to use the semi-parametric mixture of experts (SME) in which the gate network is estimated in a non-parametrical way. Based on this, we compared the performance of the SME with those of ME and neural networks via several simulation experiments and real data examples.

• The Korean Journal of Applied Statistics
• /
• v.34 no.4
• /
• pp.611-622
• /
• 2021

With a wide recognition that financial time series typically exhibits asymmetry patterns in volatility so called leverage effects, various asymmetric GARCH(1, 1) processes have been introduced to investigate asymmetric volatilities. A lot of researches have also been directed to non-stationary volatilities to deal with frequent high ups and downs in financial time series. This article is concerned with both asymmetric and non-stationary GARCH-type models. As a subsequent paper of Choi et al. (2020), we review various asymmetric and non-stationary GARCH(1, 1) processes, and in turn propose how to compare competing models using a parametric bootstrap methodology. As an illustration, Dow Jones Industrial Average (DJIA) is analyzed.

• Communications for Statistical Applications and Methods
• /
• v.18 no.6
• /
• pp.717-732
• /
• 2011

We consider bootstrap confidence intervals for high quantiles of heavy-tailed distribution. A semi-parametric method is compared with the non-parametric and the parametric method through simulation study.

• Korean Journal of Veterinary Research
• /
• v.47 no.2
• /
• pp.259-263
• /
• 2007

The choice of input distribution in quantitative risk assessments modeling is of great importance to get unbiased overall estimates, although it is difficult to characterize them in situations where data available are too sparse or small. The present study is particularly concerned with accommodation of uncertainties commonly encountered in the practice of modeling. The authors applied parametric and non-parametric bootstrap simulation methods which consist of re-sampling with replacement, in together with the classical Student-t statistics based on the normal distribution. The implications of these methods were demonstrated through an empirical analysis of trade volume from the amount of chicken and pork meat imported to Korea during the period of 1998-2005. The results of bootstrap method were comparable to the classical techniques, indicating that bootstrap can be an alternative approach in a specific context of trade volume. We also illustrated on what extent the bias corrected and accelerated non-parametric bootstrap method produces different estimate of interest, as compared by non-parametric bootstrap method.

• The Korean Journal of Applied Statistics
• /
• v.31 no.6
• /
• pp.677-692
• /
• 2018

The total fertility rate of Korea was 1.05 in 2017, showing a return to the 1.08 level in the year 2005. 1.05 is a very low fertility level that is far from replacement level fertility or safety zone 1.5. The number may indicate a low fertility trap. It is therefore important to predict fertility than at any other time. In the meantime, we have predicted the age-specific fertility rate and total fertility rate by various statistical methods. When the data trend is disconnected or fluctuating, it applied a nonparametric method applying the smoothness and weight. In addition, the Bayesian method of using the pre-distribution of fertility rates in advanced countries with reference to the three-stage transition phenomenon have been applied. This paper examines which method is reasonable in terms of precision and feasibility by applying estimation, forecasting, and comparing the results of the recent variability of the Korean fertility rate with parametric, non-parametric and Bayesian methods. The results of the analysis showed that the total fertility rate was in the order of KOSTAT's total fertility rate, Bayesian, parametric and non-parametric method outcomes. Given the level of TFR 1.05 in 2017, the predicted total fertility rate derived from the parametric and nonparametric models is most reasonable. In addition, if a fertility rate data is highly complete and a quality is good, the parametric model approach is superior to other methods in terms of parameter estimation, calculation efficiency and goodness-of-fit.