• 품질경영학회지
• /
• 제34권2호
• /
• pp.12-21
• /
• 2006

This paper considers the problem of selecting the most profitable process mean for production processes where measurement errors exist in inspection systems. For such situations, a sequential inspection procedure is proposed to reduce measurement errors. The decision to accept, reject, or take an additional inspection of an item is made at every measurement point until the number of repeated measurements reaches its upper bound. An expected profit model is constructed and the optimal process mean, the cut-off values, and the upper bound of the number of repeated measurements are obtained when accepted(rejected) items are sold at regular(reduced) price. A numerical study is performed to investigate the performance of the proposed procedure.

• 대한산업공학회지
• /
• 제30권1호
• /
• pp.36-43
• /
• 2004

In-line measurement systems are preferred to those in analytical laboratories, since in-line systems provide rapid response to process upsets. If an in-line measurement system exhibits an unstable variation and if this instability in measurement variation goes undetected, it will make the process monitoring procedure invalid. This paper presents a stability evaluation procedure for the in-line measurement system using two independent readings from the in-line measurement system and one reading from the analytical laboratory, which requires less measurement cost and time.

• 한국품질경영학회:학술대회논문집
• /
• 한국품질경영학회 2006년도 춘계학술대회
• /
• pp.334-337
• /
• 2006

This paper considers the problem of selecting the most profitable process mean for production processes where measurement errors exist in inspection systems. For such situations, a sequential inspection procedure is proposed to reduce measurement errors. The decision to accept, reject, or take an additional inspection of an item is made at every measurement point until the number of repeated measurements reaches its upper bound. An expected profit model is constructed and the optimal process mean, the cut-off values, and the upper bound of the number of repeated measurements are obtained when accepted(rejected) items are sold at regular(reduced) price. A numerical study is performed to investigate the performance of the proposed procedure.

• 대한임상검사과학회지
• /
• 제45권2호
• /
• pp.60-65
• /
• 2013

Data from repeated measurements are accomplished through repeatedly processing the same subject under different conditions and different points of view. The power of testing enhances the choice of pertinent analysis methods that agrees with the characteristics of data concerned and the situation involved. Along with the clinical example, this paper compares the analysis of the variance on ex-post tests, gain score analysis, analysis by mixed design and analysis of covariance employable for repeating measure. Comparing the analysis of variance on ex post test, and gain score analysis on correlations, leads to the fact that the latter enhances the power of the test and diminishes the variance of error terms. The concluded probability, identified that the gain score analysis and the mixed design on interaction between "between subjects factor" and "within subjects factor", are identical. The analysis of covariance, demonstrated better power of the test and smaller error terms than the gain score analysis. Research on four analysis method found that the analysis of covariance is the most appropriate in clinical data than two repeated test with high correlation and ex ante affects ex post.

• Imaging Science in Dentistry
• /
• 제34권3호
• /
• pp.123-128
• /
• 2004

Purpose: To evaluate the reliability of measurements in spiral tomography through assessing the visibility of the alveolar crest and the measurements between the alveolar crest and other anatomic structures. Materials and Methods: 110 spiral tomograms of the jaws were taken by Scanora X-ray unit from the patients. The visibility of the alveolar crests was estimated by 3 observers and classified as clearly visible, questionable visibility, or not visible. 3 observers measured the distance between the alveolar crest and the reference points of anatomic structures. The measurements were repeated 2 weeks later. Results: 52.9% of alveolar crests on upper jaws and 61.5% of alveolar crests on lower jaws were visible. The interobserver and intraobserver agreements on the visibility were low. The mean ranges of the measurements were 1.39 mm (SD = 1.37 mm) on maxilla and 1.03 mm (SD = 1.01 mm) on mandible in the interobserver evaluation. The interobserver variance was greater than the intraobserver variance in the measurements of distance. Conclusion: Spiral tomography showed a relatively low reliability in the visibility and measurements of the alveolar crest.

• Journal of the Korean Data and Information Science Society
• /
• 제21권6호
• /
• pp.1263-1270
• /
• 2010

60명의 환자들을 20명씩3개 그룹으로 나누어 각 그룹마다 다른 종류의 식이요법을 실시한 후 1주 간격으로 5주간에 걸쳐서 콜레스테롤 수치에 대한 반복측정 자료를 얻었다. 해당자료를 바탕으로 적합성여부와 유의성 검정을 실시한 결과 등분산 Toeplitz가 다양한 공분산행렬 형태들 중에서 가장 적합한 공분산구조 모형으로 판명되었다. 이 모형에서는 시점들 간의 상관계수는 0.64-0.78로 대체적으로 높은 상관관계들을 보여주고 있으며, 모수인자들의 유의성검정 결과, 시간효과는 대단히 유의하게 나타났으나, 처리 및 처리와 시간과의 교호작용효과는 유의하지 않은 것으로 판명되었다.

• Journal of the Korean Statistical Society
• /
• 제26권3호
• /
• pp.319-332
• /
• 1997

The application of multivariate linear rank statistics to data with item nonresponse is considered. Only a modest extension of the complete data techniques is required when the missing data may be thought of as a random sample, and an appropriate modification of the covariances is derived. A proof of the asymptotic multivariate normality is given. A review of some related results in the literature is presented and applications including longitudinal and repeated measures designs are discussed.

• 한국시뮬레이션학회논문지
• /
• 제10권3호
• /
• pp.31-46
• /
• 2001

Repeated measurements on units under different conditions are common in biological and biomedical studies. In a number of growth and pharmacokinetic studies, the relationship between the response and the covariates is assumed to be nonlinear in some unknown parameters and the form remains the same for all units. Nonlinear random coefficient models are used to analyze such repeated measurement data. Extended least squares methods are proposed in the literature for estimating the parameters of the model. However, neither objective function has closed form expression in practice. This paper proposes Monte Carlo methods to estimate the objective functions and the corresponding estimators. A simulation study that compare various methods is included.

• 대한치과교정학회지
• /
• 제28권1호
• /
• pp.75-83
• /
• 1998

본 연구는 교정 치료를 위한 진단과 치료 계획의 수립에 널리 이용되는 진단 수단의 하나인 두부 방사선 사진을 계측하는 연구에서 볼 수 있는 오류의 중요성을 인식하고, 반복 계측의 방법으로 체계적 오차(systematic error)를 찾아내고 임의적오차(random error)의 범위를 산출하는 과정을 통해 기준점의 식별에 보다 주의가 기울여져야 할 해부학적 기준점들을 찾아보고자 시행되었는데, 통법에 의해 촬영된 100장의 측모 두부 방사선 사진을 연구대상으로 하여 61개의 기준점과 130개의 계측항목을 선정하였고 반복계측을 위해 25개의 표본을 무작위로 선정, 계측오차를 분석하여 다음과 같은 결론을 얻었다. 1. 반복계측에 따른 계측치의 비교에서 130개 전체 계측항목의 18.4%인 24개 항목에서 유의성 있는 차이를 보였다. 2. 반복계측에서 기준점 식별에 차이를 보이는 빈도는 상악 전치의 치근단점(as), 상악골의 최후방벽(tu), 연조직 nasion과 전두정(ft) 그리고 기도의 ad3점에서 매우 높았다. 3. 5%이하의 유의도를 보이는 수준까지 기준점 마킹을 수정한 후, 임의적오차의 범위는 0.67-1.71mm또는 도를 보였다. 4. 가장 임의적오차를 보인 계측항목은 상, 하악 전치가 이루는 각(interincisal angle : ILs-ILi)이었다. 5. 계측 오차의 문제는 주로 해부학적 정의에 대한 정확성의 부족과 불분명한 방사선사진상에 기인되었다. 이상의 연구 결과로 두부 방사선 사진의 계측에는 많은 오류의 가능성이 있음을 확인할 수 있었고 이에 따라 두부방사선 계측에서 뿐 아니라 계측이 이루어지는 모든 연구에서는 항상 계측오류에 대한 분석이 함께 이루어져야 할 것이며, 조사자로서 뿐만 아니라 다른 연구자의 연구결과를 올바르게 인식하기 위한 목적으로도 오류에 대한 인식은 필수적인 것으로 생각된다.

• 한국의류학회지
• /
• 제40권4호
• /
• pp.641-649
• /
• 2016

Highly precision body measurements represent basic data required by industry and researches who wish to utilize information about the human body. The proficiency and expertise of the measurers have a significant influence on the error and accuracy of data when various parts from multiple subjects' bodies are measured. Therefore, in order to measure accurate body measurements (when measuring bodies directly), it is necessary to conduct objective analyses on errors. This study calculated the Relative Technical Error of Measurement (%TEM) using data that measured each of 24 subjects and discussed errors and methods to reduce errors by conducting comparison analysis based on measured items and objects. The result of analysis indicated that the errors based on age and gender of the objects of measurement were minor; however, there were comparatively distinct differences in measured errors based on measured items. 'Right and left Shoulder Angle' for all measured subjects displayed the greatest errors and standard deviations. 'Height' dimension, Lateral Malleolus Height and Head Height had big errors; in addition, 'Circumference', Neck Base Circumference and Armscye Circumference also had big errors. More careful measurements of such items with big errors require additional educational plan such as a proposal for more objective and detailed measurement methods. Items with small errors but big standard deviations such as Waist Circumference, Calf Circumference, Minimum Leg Circumference, Chest Circumference, Hip Circumference and Waist Circumference confirmed that errors for them greatly decreased with repeated experiments and resultant measurers increased proficiency; consequently, repeated measuring experiments for these items greatly enhance accuracy.