Test Limits Using Correlated Measurements

Albers, Willem; Arts, G.R.J.; Kallenberg, W.C.M.

doi:10.1080/02331889708802617

Cited by 6 publications

(9 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…instead of a 2 from (2.8), cf. Albers, Arts and Kallenberg (1995a). Due to the change of a 1 and a 2 also m(ξ * , η * , ζ * ) = g 1 (ã 1 ) changes, but only through η * , which is now equal to…”

Section: Test Regions If Parameters Are Unknownmentioning

confidence: 96%

“…( 3.4) At first sight one might expect that the expected consumer risk is close to γ, at least for moderately large n. Unfortunately, just plugging in estimates in the test limit leads to an expected consumer risk which is seriously biased (cf. Albers, Arts and Kallenberg (1995a)). To ensure that the expected consumer risk equals γ up to high precision, the test limitα +βs −â 2σZ has to be modified.…”

Section: Test Regions If Parameters Are Unknownmentioning

confidence: 99%

See 1 more Smart Citation

Test Regions Using Two or More Correlated Product Characteristics

Albers¹,

Wim²,

Arts³

et al. 1999

Technometrics

Self Cite

View full text Add to dashboard Cite

For inspection of manufactured parts, one can use the information of two or more product characteristics that are strongly related to the characteristic of interest. Under the condition that at most a given, typically very small, fraction of the accepted parts does not satisfy the specification limit, test regions are determined such that the number of accepted products is maximized. The methods are illustrated by Monte Carlo results and a numerical example from semiconductor industry.

show abstract

Section: Test Regions If Parameters Are Unknownmentioning

confidence: 96%

Section: Test Regions If Parameters Are Unknownmentioning

confidence: 99%

Test Regions Using Two or More Correlated Product Characteristics

Albers¹,

Wim²,

Arts³

et al. 1999

Technometrics

Self Cite

View full text Add to dashboard Cite

show abstract

“…Then a sample from (X1,X2) enables us to estimate means, variances and correlation. Using this, accurate test limits can be derived for this situation as well (see Albers et al, 1995). Quite often, however, the test sample of size n from (X1,X2) will form part of a considerably larger production sample of size N from X2: throughout production as a routine the simple correlated measurements are taken.…”

Section: Discussionmentioning

confidence: 99%

A simple estimator for correlation in incomplete data

Albers

Teulings

1996

Statistics & Probability Letters

View full text Add to dashboard Cite

show abstract

“…For the more realistic situation that the model is (partly) unknown, the test limits should be modi®ed. For more details see ALBERS et al (1995ALBERS et al ( ), (1996.…”

Section: Introductionmentioning

confidence: 99%