Exact simultaneous location-scale tests for two shifted exponential samples

Amitava Mukherjee; Zhi Lin Chong; Marco Marozzi

Kybernetika (2019)

  • Volume: 55, Issue: 6, page 943-960
  • ISSN: 0023-5954

Abstract

top
The failure time distribution for various items often follows a shifted (two-parameter) exponential model and not the traditional (one-parameter) exponential model. The shifted exponential is very useful in practice, in particular in the engineering, biomedical sciences and industrial quality control when modeling time to event or survival data. The open problem of simultaneous testing for differences in origin and scale parameters of two shifted exponential distributions is addressed. Two exact tests are proposed using maximum likelihood estimators. They are based on the combination of two statistics following a maximum-type and a distance-type approach. The exact null distributions of the respective test statistics are derived analytically. Small sample type-one error rate and power of the tests are studied numerically. We showed that the test based on the maximum type combination (the Max test) should be preferred being generally more powerful than the test based on the distance type combination (the Distance test). An application to a biomedical experiment is discussed.

How to cite

top

Mukherjee, Amitava, Chong, Zhi Lin, and Marozzi, Marco. "Exact simultaneous location-scale tests for two shifted exponential samples." Kybernetika 55.6 (2019): 943-960. <http://eudml.org/doc/297396>.

@article{Mukherjee2019,
abstract = {The failure time distribution for various items often follows a shifted (two-parameter) exponential model and not the traditional (one-parameter) exponential model. The shifted exponential is very useful in practice, in particular in the engineering, biomedical sciences and industrial quality control when modeling time to event or survival data. The open problem of simultaneous testing for differences in origin and scale parameters of two shifted exponential distributions is addressed. Two exact tests are proposed using maximum likelihood estimators. They are based on the combination of two statistics following a maximum-type and a distance-type approach. The exact null distributions of the respective test statistics are derived analytically. Small sample type-one error rate and power of the tests are studied numerically. We showed that the test based on the maximum type combination (the Max test) should be preferred being generally more powerful than the test based on the distance type combination (the Distance test). An application to a biomedical experiment is discussed.},
author = {Mukherjee, Amitava, Chong, Zhi Lin, Marozzi, Marco},
journal = {Kybernetika},
keywords = {hypothesis testing; failure time model; simultaneous testing; shifted exponential; type-one error rate; power},
language = {eng},
number = {6},
pages = {943-960},
publisher = {Institute of Information Theory and Automation AS CR},
title = {Exact simultaneous location-scale tests for two shifted exponential samples},
url = {http://eudml.org/doc/297396},
volume = {55},
year = {2019},
}

TY - JOUR
AU - Mukherjee, Amitava
AU - Chong, Zhi Lin
AU - Marozzi, Marco
TI - Exact simultaneous location-scale tests for two shifted exponential samples
JO - Kybernetika
PY - 2019
PB - Institute of Information Theory and Automation AS CR
VL - 55
IS - 6
SP - 943
EP - 960
AB - The failure time distribution for various items often follows a shifted (two-parameter) exponential model and not the traditional (one-parameter) exponential model. The shifted exponential is very useful in practice, in particular in the engineering, biomedical sciences and industrial quality control when modeling time to event or survival data. The open problem of simultaneous testing for differences in origin and scale parameters of two shifted exponential distributions is addressed. Two exact tests are proposed using maximum likelihood estimators. They are based on the combination of two statistics following a maximum-type and a distance-type approach. The exact null distributions of the respective test statistics are derived analytically. Small sample type-one error rate and power of the tests are studied numerically. We showed that the test based on the maximum type combination (the Max test) should be preferred being generally more powerful than the test based on the distance type combination (the Distance test). An application to a biomedical experiment is discussed.
LA - eng
KW - hypothesis testing; failure time model; simultaneous testing; shifted exponential; type-one error rate; power
UR - http://eudml.org/doc/297396
ER -

References

top
  1. J., Ahmadi,, K., MirMostafaee, S. M. T., 10.1016/j.spl.2008.12.002, Stat. Probab. Lett. 79 (2009), 977-983. MR2509490DOI10.1016/j.spl.2008.12.002
  2. A., Baklizi,, 10.1080/00949655.2013.816307, J. Stat. Comput. Simul. 84 (2014), 2670-2679. MR3250965DOI10.1080/00949655.2013.816307
  3. A., Chaturvedi,, V., Sharma,, 10.1080/02331880902760629, Statistics 44 (2010), 73-75. MR2674408DOI10.1080/02331880902760629
  4. C., Cohen, A., R., Helm, F., 10.1080/00401706.1973.10489054, Technometrics 15 (1973), 415-418. MR0375603DOI10.1080/00401706.1973.10489054
  5. N., Ebrahimi,, 10.1016/0378-3758(86)90163-1, J. Stat. Plan. Inference 14 (1986), 255-261. MR0852530DOI10.1016/0378-3758(86)90163-1
  6. M., Engelhardt,, J., Bain, L., 10.1080/00401706.1978.10489615, Technometrics 20 (1978), 37-39. DOI10.1080/00401706.1978.10489615
  7. A., Ganguly,, S., Mitra,, D., Samanta,, D., Kundu,, 10.1016/j.jspi.2011.08.001, J. Stat. Plan. Inference 142 (2012), 613-625. MR2853570DOI10.1016/j.jspi.2011.08.001
  8. S., Huang,, A., Mukherjee,, J., Yang,, 10.1002/qre.2314, Qual. Reliab. Eng. Int. 34 (2018), 6, 1158-1173. DOI10.1002/qre.2314
  9. L., Johnson, N., S., Kotz,, Distributions in Statistics, Vol. 1: Continuous Univariate Distributions., Houghton Mifflin, Boston 1970. MR0270475
  10. C., Kao, S., 10.1080/02664760802571333, J. Appl. Stat. 37 (2010), 1067-1087. MR2751922DOI10.1080/02664760802571333
  11. K., Krishnamoorthy,, Y., Xia,, 10.1080/03610926.2017.1313983, Commun. Stat. Theory Methods 47 (2018), 935-952. MR3750706DOI10.1080/03610926.2017.1313983
  12. K., Krishnamoorthy,, S., Mukherjee,, H., Guo,, 10.1007/s00184-006-0074-7, Metrika 65 (2007), 261-273. MR2299551DOI10.1007/s00184-006-0074-7
  13. J., Li,, W., Song,, J., Shi,, 10.1016/j.spl.2015.07.002, Stat. Probab. Lett. 106 (2015), 39-45. MR3389968DOI10.1016/j.spl.2015.07.002
  14. A., Mukherjee,, K., McCracken, A., S., Chakraborti,, 10.1016/j.spl.2015.07.002, J. Qual. Technol. 47 (2015), 176-192. DOI10.1016/j.spl.2015.07.002
  15. M., Pal,, A., Masoom, M., J., Woo,, 10.1080/02331880500274031, Statistics 39 (2005), 415-428. MR2207457DOI10.1080/02331880500274031
  16. Z., Raqab, M., 10.1007/s10260-004-0084-4, Stat. Methods Appl. 13 (2004), 43-54. MR2081964DOI10.1007/s10260-004-0084-4
  17. A., Roy,, T., Mathew,, 10.1016/j.jspi.2003.11.012, J. Stat. Plan .Inference 128 (2005), 509-517. MR2102773DOI10.1016/j.jspi.2003.11.012
  18. S., Sangnawakij,, S., Niwitpong,, 10.1080/03610918.2016.1208236, Commun. Stat. Simul. Comp. 46 (2017), 6618-6630. MR3740801DOI10.1080/03610918.2016.1208236
  19. N., Schenk,, M., Burkschat,, E., Cramer,, U., Kamps,, 10.1016/j.jspi.2010.11.009, J. Stat. Plan. Inference 141 (2011), 1575-1587. MR2747926DOI10.1016/j.jspi.2010.11.009
  20. P., Singh,, A., Abebe,, 10.1007/s10260-008-0092-x, Stat. Methods Appl. 18 (2009), 359-374. MR2529262DOI10.1007/s10260-008-0092-x
  21. A., Tanis, E., 10.1214/aoms/1177703749, Ann. Math. Stat. 35 (1964), 270-276. MR0158481DOI10.1214/aoms/1177703749
  22. van, Zyl, R., der, Merwe, A. J. van, 10.1080/03610926.2018.1440307, Commun. Stat. Theory Methods DOI:10.1080/03610926.2018.1440307. MR3960394DOI10.1080/03610926.2018.1440307
  23. D., Varde, S., 10.1080/01621459.1969.10501000, J. Amer. Stat. Assoc. 64 (1969), 621-631. MR0246475DOI10.1080/01621459.1969.10501000
  24. Z., Wang,, T., Ng, H. K., 10.1007/s10985-006-9026-9, Lifetime Data Anal. 12 (2006), 505-522. MR2338964DOI10.1007/s10985-006-9026-9
  25. I., Weissman,, 10.1016/j.spl.2017.05.018, Stat. Probab. Lett. 129 (2017), 147-154. MR3688527DOI10.1016/j.spl.2017.05.018
  26. H.-M., Lee, J.-W. Wu., C.-L., Lei,, 10.1016/j.amc.2007.01.010, Appl. Math. Comput. 190 (2007), 116-125. MR2335434DOI10.1016/j.amc.2007.01.010
  27. S.-F., Wu,, 10.1007/s11135-008-9187-6, Qual. Quant. 44 (2010), 181-189. DOI10.1007/s11135-008-9187-6

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.