Two-sided Tolerance Intervals in a Simple Linear Regression

Martina Chvosteková

Acta Universitatis Palackianae Olomucensis. Facultas Rerum Naturalium. Mathematica (2013)

  • Volume: 52, Issue: 2, page 31-41
  • ISSN: 0231-9721

Abstract

top
Numerical results for a simple linear regression indicate that the non-simultaneous two-sided tolerance intervals nearly satisfy the condition of multiple-use confidence intervals, see Lee and Mathew (2002), but the numerical computation of the limits of the multiple-use confidence intervals is needed. We modified the Lieberman–Miller method (1963) for computing the simultaneous two-sided tolerance intervals in a simple linear regression with independent normally distributed errors. The suggested tolerance intervals are the narrowest of all the known simultaneous two-sided tolerance intervals. The computation of the multiple-use confidence intervals based on the new simultaneous two-sided tolerance intervals is simple and fast.

How to cite

top

Chvosteková, Martina. "Two-sided Tolerance Intervals in a Simple Linear Regression." Acta Universitatis Palackianae Olomucensis. Facultas Rerum Naturalium. Mathematica 52.2 (2013): 31-41. <http://eudml.org/doc/260835>.

@article{Chvosteková2013,
abstract = {Numerical results for a simple linear regression indicate that the non-simultaneous two-sided tolerance intervals nearly satisfy the condition of multiple-use confidence intervals, see Lee and Mathew (2002), but the numerical computation of the limits of the multiple-use confidence intervals is needed. We modified the Lieberman–Miller method (1963) for computing the simultaneous two-sided tolerance intervals in a simple linear regression with independent normally distributed errors. The suggested tolerance intervals are the narrowest of all the known simultaneous two-sided tolerance intervals. The computation of the multiple-use confidence intervals based on the new simultaneous two-sided tolerance intervals is simple and fast.},
author = {Chvosteková, Martina},
journal = {Acta Universitatis Palackianae Olomucensis. Facultas Rerum Naturalium. Mathematica},
keywords = {multiple-use confidence interval; simultaneous two-sided tolerance interval; multiple-use confidence interval; simultaneous two-sided tolerance interval},
language = {eng},
number = {2},
pages = {31-41},
publisher = {Palacký University Olomouc},
title = {Two-sided Tolerance Intervals in a Simple Linear Regression},
url = {http://eudml.org/doc/260835},
volume = {52},
year = {2013},
}

TY - JOUR
AU - Chvosteková, Martina
TI - Two-sided Tolerance Intervals in a Simple Linear Regression
JO - Acta Universitatis Palackianae Olomucensis. Facultas Rerum Naturalium. Mathematica
PY - 2013
PB - Palacký University Olomouc
VL - 52
IS - 2
SP - 31
EP - 41
AB - Numerical results for a simple linear regression indicate that the non-simultaneous two-sided tolerance intervals nearly satisfy the condition of multiple-use confidence intervals, see Lee and Mathew (2002), but the numerical computation of the limits of the multiple-use confidence intervals is needed. We modified the Lieberman–Miller method (1963) for computing the simultaneous two-sided tolerance intervals in a simple linear regression with independent normally distributed errors. The suggested tolerance intervals are the narrowest of all the known simultaneous two-sided tolerance intervals. The computation of the multiple-use confidence intervals based on the new simultaneous two-sided tolerance intervals is simple and fast.
LA - eng
KW - multiple-use confidence interval; simultaneous two-sided tolerance interval; multiple-use confidence interval; simultaneous two-sided tolerance interval
UR - http://eudml.org/doc/260835
ER -

References

top
  1. Chvosteková, M., 10.1080/03610926.2012.724502, Communications in Statistics, Theory and Methods 42 (2013), 1145–1152. (2013) MR3031273DOI10.1080/03610926.2012.724502
  2. Chvosteková, M., Determination of two-sided tolerance interval in a linear regression model, Forum Statisticum Slovacum 6 (2010), 79–84. (2010) 
  3. Chvosteková, M., Witkovský, V., 10.2478/v10048-009-0003-9, Measurement Science Review 9 (2009), 1–8. (2009) DOI10.2478/v10048-009-0003-9
  4. Krishnamoorthy, K., Mathew, T., Statistical Tolerance Regions: Theory, Applications, and Computation, Wiley series in probability and statistics, Wiley, Chichester, 2009. (2009) MR2500599
  5. Lee, Y., Mathew, T., Advances on Theoretical and Methodological Aspects of Probability and Statistics, Taylor & Francis, London, 2002. (2002) MR1987243
  6. Lieberman, G. J., Miller, R. G., Jr., 10.1093/biomet/50.1-2.155, Biometrika 50 (1963), 155–168. (1963) Zbl0124.35501MR0158472DOI10.1093/biomet/50.1-2.155
  7. Lieberman, G. J., Miller, R. G., Hamilton, M. A., 10.1093/biomet/54.1-2.133, Biometrika 54 (1967), 133–145. (1967) MR0217953DOI10.1093/biomet/54.1-2.133
  8. Limam, M. M. T., Thomas, R., 10.1080/01621459.1988.10478666, Journal of the American Statistical Association 83 (1988), 801–804. (1988) Zbl0649.62030MR0963808DOI10.1080/01621459.1988.10478666
  9. Mee, R. W., Eberhardt, K. R., 10.1080/00401706.1996.10484501, Technometrics 38 (1996), 221–229. (1996) MR1411879DOI10.1080/00401706.1996.10484501
  10. Mee, R. W., Eberhardt, K. R., Reeve, C. P., 10.1080/00401706.1991.10484808, Technometrics 33 (1991), 211–219. (1991) MR1110358DOI10.1080/00401706.1991.10484808
  11. Scheffé, H., 10.1214/aos/1193342379, The Annals of Statistics 1 (1973), 1–37. (1973) MR0336920DOI10.1214/aos/1193342379
  12. Wilson, A. L.:, 10.1214/aoms/1177698707, The Annals of Mathematical Statistics 38 (1967), 1536–1540. (1967) Zbl0183.20902MR0217954DOI10.1214/aoms/1177698707
  13. Witkovský, V.:, On exact multiple-use linear calibration confidence intervals, In: MEASUREMENT 2013: 9th International Conference on Measurement, Smolenice, Slovakia, 2013, 35–38. (2013) 

NotesEmbed ?

top

You must be logged in to post comments.

To embed these notes on your page include the following JavaScript code on your page where you want the notes to appear.

Only the controls for the widget will be shown in your chosen language. Notes will be shown in their authored language.

Tells the widget how many notes to show per page. You can cycle through additional notes using the next and previous controls.

    
                

Note: Best practice suggests putting the JavaScript code just before the closing </body> tag.