• Journal of Integrative Natural Science
• /
• v.5 no.3
• /
• pp.157-162
• /
• 2012

Measurement error is one of main source of error in survey. It is generally defined as the difference between an observed value and an underlying true value. An observed value with error may be expressed as a function of the true value plus error term. In some cases, the measurement error variance may be also a function of the unknown true value. The error variance function can be rewritten as a function of true value multiplied by a scale factor. This research explore methods for estimation of the measurement error variance based on the data from complex sampling design. We consider the case in which the variance of mesurement error is a linear function of unknown true value, and the error variance scale factor is small. We applied our results to the U.S. Third National Health and Nutrition Examination Survey (the U.S. NHANES III) data for empirical analyses, which has replicate measurements for relatively small subset of initial respondents's group.

• Communications for Statistical Applications and Methods
• /
• v.9 no.2
• /
• pp.315-324
• /
• 2002

For estimating the error variance under the relative squared error loss in two-way analysis of variance models, we provide a class of hierarchical Bayes estimators and then derive a subclass of the hierarchical Bayes estimators, each member of which dominates the best multiple of the error sum of squares which is known to be minimax. We also identify a subclass of non-minimax hierarchical Bayes estimators.

• Journal of applied mathematics & informatics
• /
• v.13 no.1_2
• /
• pp.501-508
• /
• 2003

Although the estimate of regression function is important, some have focused the variance estimation of error term in regression model. Different variance estimators perform well under different conditions. In many practical situations, it is rather hard to assess which conditions are approximately satisfied so as to identify the best variance estimator for the given data. In this article, we suggest SHM estimator compared to LS estimator, which is common estimator using in parametric multiple regression analysis. Moreover, a combined estimator of variance, VEM, is suggested. In the simulation study it is shown that VEM performs well in practice.

• Communications for Statistical Applications and Methods
• /
• v.2 no.2
• /
• pp.296-302
• /
• 1995

When heteroscedasticity occurs in random effects linear model, the error variance may depend on the values of one or more of the explanatory variables or on other relevant quantities such as time or spatial ordering. In this paper we derive a score test as a diagnostic tool for detecting non-constant error variance in random effefts linear model based on the model expansion on error variance. This score test is compared to loglikelihood ratio test.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.23 no.61
• /
• pp.89-98
• /
• 2000

For statistical process control, the process data are collected by the measurement system. But, the measurement system may have instrument error or/and operator error. In the measured values of products, the total observed variance consists of process variance and variance due to error of measurement system. In this paper, we design more practical T-s control chart considering estimated measurement error The effects of measurement error on the expected total cost and design parameters are investigated.

• The Korean Journal of Applied Statistics
• /
• v.15 no.2
• /
• pp.405-414
• /
• 2002

We consider the problem of estimating the error variance of in a two-way mixed-effects ANOVA model using noninformative priors. First, we derive Jeffreys' prior, a reference prior, and matching priors. We then provide marginal posterior distributions under those noninformative priors. Finally, we provide graphs of marginal posterior densities of the error variance and credible intervals for the error variance in two real data set and compare these credible intervals.

• Communications for Statistical Applications and Methods
• /
• v.6 no.2
• /
• pp.487-500
• /
• 1999

We propose a class of hierarchical Bayes estimators of the error variance under the relative squared error loss in balanced fixed-effects two-way analysis of variance models. Also we provide analytic expressions for the risk improvement of the hierarchical Bayes estimators over multiples of the error sum of squares. Using these expressions we identify a subclass of the hierarchical Bayes estimators each member of which dominates the best multiple of the error sum of squares which is known to be minimax. Numerical values of the percentage risk improvement are given in some special cases.

• Journal of the Korean Data and Information Science Society
• /
• v.22 no.3
• /
• pp.575-587
• /
• 2011

We investigate some statistical properties of several dierence-based error variance estimators in nonparametric regression model. Most of existing dierence-based methods are developed under asymptotical properties. Our focus is on the exact form of mean and variance for the lag-k dierence-based estimator and the second-order dierence-based estimator in a nite sample size. Our approach can be extended to Tong's estimator (2005) and be helpful to obtain optimal k.

• Journal of the Korean Statistical Society
• /
• v.35 no.3
• /
• pp.317-329
• /
• 2006

In the problem of estimating the error variance in the balanced fixed- effects one-way analysis of variance (ANOVA) model, Ghosh (1994) proposed hierarchical Bayes estimators and raised a conjecture for which all of his hierarchical Bayes estimators are admissible. In this paper we prove this conjecture is true by representing one-way ANOVA model to the distributional form of a multiparameter exponential family.

• Communications for Statistical Applications and Methods
• /
• v.19 no.3
• /
• pp.333-344
• /
• 2012

We consider some statistical properties of the first order difference-based error variance estimator in nonparametric regression models with a single outlier. So far under an outlier(s) such difference-based estimators has been rarely discussed. We propose the first order difference-based estimator using the leave-one-out method to detect a single outlier and simulate the outlier detection in a nonparametric regression model with the single outlier. Moreover, the outlier detection works well. The results are promising even in nonparametric regression models with many outliers using some difference based estimators.