• Journal of the Korean Data and Information Science Society
• /
• v.28 no.5
• /
• pp.981-999
• /
• 2017

In the standard control chart assuming a simple random model, we estimate the process variance without considering the between-sample variance. If the between-sample exists in the process, the process variance is under-estimated. When the process variance is under-estimated, the narrower control limits result in the excessive false alarm rate although the sensitivity of the control chart is improved. In this paper, using the variance component model to incorporate the between-sample variance, we set the control limits using both the within- and between-sample variances, and evaluate the efficiency of the control chart in terms of the average run length (ARL). Considering the most widely used control chart types such as ${\bar{X}}$, EWMA and CUSUM control charts, we compared the differences between two cases, Case I and Case II, where the between-sample variance is ignored and considered, respectively. We also considered the two cases when the process parameters are given and estimated. The results showed that the false alarm rate of Case I increased sharply as the between-sample variance increases, while that of Case II remains the same regardless of the size of the between-sample variance, as expected.

• Communications for Statistical Applications and Methods
• /
• v.10 no.2
• /
• pp.553-566
• /
• 2003

In many cases, the measurement error variances may be functions of the unknown true values or related covariates. This paper considers design-based estimators of the parameters of these variance functions based on the within-unit sample variances. This paper devotes to: (1) define an error scale factor $\delta$; (2) develop estimators of the parameters of the linear measurement error variance function of the true values under large-sample and small-error conditions; (3) use propensity methods to adjust survey weights to account for possible selection effects at the replicate level. The proposed methods are applied to medical examination data from the U.S. Third National Health and Nutrition Examination Survey (NHANES III).

• Journal of the Korean Statistical Society
• /
• v.12 no.1
• /
• pp.36-45
• /
• 1983

After every decennial census in the U.S., national surveys such as the Consumer Expenditures surveys are redesigned. The redesigned samples will be multi-stage systematic samples. Many sampling schemes have been proposed for comparison which requires the estimation and variance estiamtion formula. This paper deals with the surveys redesign research which concerns the sample design within the Primary Sampling Unit (PSU). In constructing the estimators it deals with the problem of which first stage inflation factor to use. The expected value of the proposed estimators is also derived.

• Proceedings of the Korean Association for Survey Research Conference
• /
• 2002.11a
• /
• pp.255-274
• /
• 2002

We classify rotation sampling designs into two classes. The first class replaces sample units within the same rotation group while the second class replaces sample units between different rotation groups. The first class is specified by the three-way balanced design which is a multi-level version of previous balanced designs. We introduce an extended generalized composite estimator (EGCE) and derive its variance and mean squared error for each of the two classes of design, cooperating two types of correlations and three types of biases. Unbiased estimators are derived for difference between interview time biases, between recall time biases, and between rotation group biases. Using the variance and mean squared error, since any rotation design belongs to one of the two classes and the EGCE is a most general estimator for rotation design, we evaluate the efficiency of EGCE to simple weighted estimator and the effects of levels, design gaps, and rotation patterns on variance and mean squared error.

• Communications for Statistical Applications and Methods
• /
• v.4 no.3
• /
• pp.775-785
• /
• 1997

Robustness rates for repeated measures pairwise multiple comparison procedures were investigated in a split plot design with one between- and one within-subjects factor using untrimmed and trimmed data. Five factors were manipulated in the study: distribution, sphericity, variance-covariance heteroscedasticity, total sample size, and sample size ratio. The Welsch test (W) and the Welsch test on trimmed data $(W_{RT})$ performed better than the other procedures, but had a liberal tendency. The trimmed difference score Bonferroni Procedure $(B_{DT})$ was a good choice in some conditions.

• Journal of Environmental Impact Assessment
• /
• v.24 no.6
• /
• pp.607-618
• /
• 2015

Five years have passed since the first set of environmental samples was taken in 2011 to represent various ecosystems which would help future generations lead back to the past environment. Those samples have been preserved cryogenically in the National Environmental Specimen Bank(NESB) at the National Institute of Environmental Research. Even though there is a strict regulation (SOP, standard operating procedure) that rules over the whole sampling procedure to ensure each sample to represent the sampling area, it has not been put to the test for the validation. The question needs to be answered to clear any doubts on the representativeness and the quality of the samples. In order to address the question and ensure the sampling practice set in the SOP, many steps to the measurement of the sample, that is, from sampling in the field and the chemical analysis in the lab are broken down to evaluate the uncertainty at each level. Of the 8 species currently taken for the cryogenic preservation in the NESB, pine tree samples from two different sites were selected for this study. Duplicate samples were taken from each site according to the sampling protocol followed by the duplicate analyses which were carried out for each discrete sample. The uncertainties were evaluated by Robust ANOVA; two levels of uncertainty, one is the uncertainty from the sampling practice, and the other from the analytical process, were then compiled to give the measurement uncertainty on a measured concentration of the measurand. As a result, it was confirmed that it is the sampling practice not the analytical process that accounts for the most of the measurement uncertainty. Based on the top-down approach for the measurement uncertainty, the efficient way to ensure the representativeness of the sample was to increase the quantity of each discrete sample for the making of a composite sample, than to increase the number of the discrete samples across the site. Furthermore, the cost-effective approach to enhance the confidence level on the measurement can be expected from the efforts to lower the sampling uncertainty, not the analytical uncertainty. To test the representativeness of a composite sample of a sampling area, the variance within the site should be less than the difference from duplicate sampling. For that, a criterion, ${i.e.s^2}_{geochem}$(across the site variance) <${s^2}_{samp}$(variance at the sampling location) was proposed. In light of the criterion, the two representative samples for the two study areas passed the requirement. In contrast, whenever the variance of among the sampling locations (i.e. across the site) is larger than the sampling variance, more sampling increments need to be added within the sampling area until the requirement for the representativeness is achieved.

• Clinical and Experimental Reproductive Medicine
• /
• v.49 no.3
• /
• pp.196-201
• /
• 2022

Objective: This prospective consecutive study investigated the variation in sperm DNA fragmentation (SDF) in multiple semen samples from patients with cancer. Methods: Eighty-one patients with various cancers underwent multiple semen collections on 3 consecutive days for sperm cryopreservation prior to cancer treatment. A commercial Halosperm kit was used to measure SDF. Within- and between-subject coefficients of variation were estimated via random-effects analysis of variance to assess the consistency of semen parameters and SDF. Intraclass correlation coefficients (ICCs) were calculated to assess the magnitude of the between-subject component of variance relative to the total variance. Results: The volume of semen in the day-2 and day-3 samples was significantly lower compared with the day-1 sample. Most parameters showed high ICC values, suggesting that within-subject fluctuations were small relative to the between-subject variability. The highest ICC values were identified for the SDF (ICC, 0.68; 95% confidence interval [CI], 0.45-0.84) and semen volume (ICC, 0.67; 95% CI, 0.45-0.84). Conclusion: Our findings showed that repeated ejaculates from patients with cancer had stable SDF levels.

• Honam Mathematical Journal
• /
• v.25 no.1
• /
• pp.95-115
• /
• 2003

Consider the problem of estimating a $p{\times}1$ mean vector ${\theta}(p{\geq}4)$ under the quadratic loss, based on a sample $X_1,\;{\cdots}X_n$. We find an optimal decision rule within the class of Lindley type decision rules which shrink the usual one toward the mean of observations when the underlying distribution is that of a variance mixture of normals and when the norm $||{\theta}-{\bar{\theta}}1||$ is known, where ${\bar{\theta}}=(1/p)\sum_{i=1}^p{\theta}_i$ and 1 is the column vector of ones. When the norm is restricted to a known interval, typically no optimal Lindley type rule exists but we characterize a minimal complete class within the class of Lindley type decision rules. We also characterize the subclass of Lindley type decision rules that dominate the sample mean.

• Journal of the Korean Data and Information Science Society
• /
• v.21 no.4
• /
• pp.669-679
• /
• 2010

A sample survey design is suggested for the service satisfaction evaluation of regional education offices based on the sample size of 2009 Gyeongnam regional education offices's customer satisfaction survey. The sample design is developed to fit the goal of evaluation of individual regional offices and allocate at least the minimum sample size to each city or county in Gyeongnam to achieve the goal of the survey. The population is stratified according to the regions and the types of schools, and the sample of schools is selected with proportional to the size of classes within each stratum. Finally, each sample student is selected according to two-stage cluster sampling within each sample school. Weighting averages, weighting totals and so on can be evaluated for analysis purposes. Their variance estimates can be evaluated using re-sampling methods like BBR, Jackknife, linearization-substitution methods, which are generally used for the data from a complex sample.

• Journal of Korean Society for Quality Management
• /
• v.22 no.2
• /
• pp.89-97
• /
• 1994

We consider the linear calibration model: $y_1={\alpha}+{\beta}x_i+{\sigma}{\varepsilon}_i$, i = 1, ${\cdots}$, n, $y={\alpha}+{\beta}x+{\sigma}{\varepsilon}$ where ($y_1$, ${\cdots}$, $y_n$, y) stands for an observation vector, {$x_i$} fixed design vector, (${\alpha}$, ${\beta}$) vector of regression parameters, x unknown true value of interest and {${\varepsilon}_i$}, ${\varepsilon}$ are mutually uncorrelated measurement errors with zero mean and unit variance but otherwise unknown distributions. On the basis of simple small-sample low-noise approximation, we introduce a new method of comparing the mean squared errors of the various competing estimators of the true value x for finite sample size n. Then we show that a class of estimators including the classical and the inverse estimators are consistent and first-order efficient within the class of all regular consistent estimators irrespective of type of measurement errors.