Instrumental weighted variables under heteroscedasticity. Part I – Consistency

Jan Ámos Víšek

Kybernetika (2017)

  • Volume: 53, Issue: 1, page 1-25
  • ISSN: 0023-5954

Abstract

top
The proof of consistency instrumental weighted variables, the robust version of the classical instrumental variables is given. It is proved that all solutions of the corresponding normal equations are contained, with high probability, in a ball, the radius of which can be selected - asymptotically - arbitrarily small. Then also n -consistency is proved. An extended numerical study (the Part II of the paper) offers a picture of behavior of the estimator for finite samples under various types and levels of contamination as well as various extent of heteroscedasticity. The estimator in question is compared with two other estimators of the type of “robust instrumental variables” and the results indicate that our estimator gives comparatively good results and for some situations it is better. The discussion on a way of selecting the weights is also offered. The conclusions show the resemblance of our estimator with the M -estimator with Hampel’s ψ -function. The difference is that our estimator does not need the studentization of residuals (which is not a simple task) to be scale- and regression-equivariant while the M -estimator does. So the paper demonstrates that we can directly compute - moreover by a quick algorithm (reliable and reasonably quick even for tens of thousands of observations) - the scale- and the regression-equivariant estimate of regression coefficients.

How to cite

top

Víšek, Jan Ámos. "Instrumental weighted variables under heteroscedasticity. Part I – Consistency." Kybernetika 53.1 (2017): 1-25. <http://eudml.org/doc/287938>.

@article{Víšek2017,
abstract = {The proof of consistency instrumental weighted variables, the robust version of the classical instrumental variables is given. It is proved that all solutions of the corresponding normal equations are contained, with high probability, in a ball, the radius of which can be selected - asymptotically - arbitrarily small. Then also $\sqrt\{n\}$-consistency is proved. An extended numerical study (the Part II of the paper) offers a picture of behavior of the estimator for finite samples under various types and levels of contamination as well as various extent of heteroscedasticity. The estimator in question is compared with two other estimators of the type of “robust instrumental variables” and the results indicate that our estimator gives comparatively good results and for some situations it is better. The discussion on a way of selecting the weights is also offered. The conclusions show the resemblance of our estimator with the $M$-estimator with Hampel’s $\psi $-function. The difference is that our estimator does not need the studentization of residuals (which is not a simple task) to be scale- and regression-equivariant while the $M$-estimator does. So the paper demonstrates that we can directly compute - moreover by a quick algorithm (reliable and reasonably quick even for tens of thousands of observations) - the scale- and the regression-equivariant estimate of regression coefficients.},
author = {Víšek, Jan Ámos},
journal = {Kybernetika},
keywords = {weighting order statistics of the squared residuals; consistency of the instrumental weighted variables; heteroscedasticity of disturbances; numerical study},
language = {eng},
number = {1},
pages = {1-25},
publisher = {Institute of Information Theory and Automation AS CR},
title = {Instrumental weighted variables under heteroscedasticity. Part I – Consistency},
url = {http://eudml.org/doc/287938},
volume = {53},
year = {2017},
}

TY - JOUR
AU - Víšek, Jan Ámos
TI - Instrumental weighted variables under heteroscedasticity. Part I – Consistency
JO - Kybernetika
PY - 2017
PB - Institute of Information Theory and Automation AS CR
VL - 53
IS - 1
SP - 1
EP - 25
AB - The proof of consistency instrumental weighted variables, the robust version of the classical instrumental variables is given. It is proved that all solutions of the corresponding normal equations are contained, with high probability, in a ball, the radius of which can be selected - asymptotically - arbitrarily small. Then also $\sqrt{n}$-consistency is proved. An extended numerical study (the Part II of the paper) offers a picture of behavior of the estimator for finite samples under various types and levels of contamination as well as various extent of heteroscedasticity. The estimator in question is compared with two other estimators of the type of “robust instrumental variables” and the results indicate that our estimator gives comparatively good results and for some situations it is better. The discussion on a way of selecting the weights is also offered. The conclusions show the resemblance of our estimator with the $M$-estimator with Hampel’s $\psi $-function. The difference is that our estimator does not need the studentization of residuals (which is not a simple task) to be scale- and regression-equivariant while the $M$-estimator does. So the paper demonstrates that we can directly compute - moreover by a quick algorithm (reliable and reasonably quick even for tens of thousands of observations) - the scale- and the regression-equivariant estimate of regression coefficients.
LA - eng
KW - weighting order statistics of the squared residuals; consistency of the instrumental weighted variables; heteroscedasticity of disturbances; numerical study
UR - http://eudml.org/doc/287938
ER -

References

top
  1. Amemiya, T., 10.2307/1912608, Econometrica 50 (1982), 689-711. MR0662726DOI10.2307/1912608
  2. Atkinson, A. C., Riani, M., Cerioli, A., 10.1007/978-0-387-21840-3_2, Springer Series in Statistics 2004, 31-88. Zbl1049.62057MR2055967DOI10.1007/978-0-387-21840-3_2
  3. Beran, R., 10.1214/aos/1176344125, Ann. Statist. 6 (1978), 292-313. Zbl0378.62051MR0518885DOI10.1214/aos/1176344125
  4. Bowden, R. J., Turkington, D. A., 10.1017/ccol0521262410, Cambridge Univ. Press, Cambridge 1984. Zbl0744.62149MR0798790DOI10.1017/ccol0521262410
  5. Bramati, C. M., Croux, C., 10.1111/j.1368-423x.2007.00220.x, The Econometr. J. 10 (2077), 521-540. Zbl1126.62014DOI10.1111/j.1368-423x.2007.00220.x
  6. Breiman, L., Probability., Addison-Wesley Publishing Company, London 1968. Zbl0753.60001MR0229267
  7. Čížek, P., 10.1016/j.jspi.2015.11.004, J. Statist. Planning Inference 171 (2009), 63-78. Zbl1336.62108MR3458068DOI10.1016/j.jspi.2015.11.004
  8. Cochrane, D., Orcutt, G. H., 10.1080/01621459.1949.10483290, J. Amer. Statist. Assoc. 44 (1949), 32-61. DOI10.1080/01621459.1949.10483290
  9. Cohen-Freue, G. V., Ortiz-Molina, H., Zamar, R. H., A New Robust Instrumental Variables Estimator. 
  10. Cohen-Freue, G. V., Ortiz-Molina, H., Zamar, R. H., 10.1111/biom.12043, Biometrics 69 (2013), 641-650. MR3106592DOI10.1111/biom.12043
  11. Croux, C., Aelst, S. Van, Dehon, C., 10.1007/bf02530499, Ann. Inst. Statist. Math. 55 (2013), 265-285. MR2001864DOI10.1007/bf02530499
  12. Davies, P. L., 10.1214/aos/1176350505, Ann. Statist. 15 (1987), 1269-1292. MR0902258DOI10.1214/aos/1176350505
  13. (1952), M. Donsker, 10.1214/aoms/1177729445, Ann. Math. Statist. 23 (1952), 277-281. MR0047288DOI10.1214/aoms/1177729445
  14. Eicker, F., 10.1214/aoms/1177704156, Ann. Math. Stat. 34 (1963), 447-456. Zbl0111.34003MR0148177DOI10.1214/aoms/1177704156
  15. Eicker, F., Limit theorems for regression with unequal and dependent errors., In: Proc. Fifth Berkeley Symposium on Mathematical Statistics and Probability (L. Le Cam and J. Neyman, eds.), University of California Press, Berkeley 1967. MR0214223
  16. Fabián, Z., 10.1214/aoms/1177704156, Comm. Statist. - Theory and Methods 30 (2001), 537-555. Zbl1009.62534MR1862941DOI10.1214/aoms/1177704156
  17. Fabián, Z., 10.1080/03610920701648987, Comm. Statist. - Theory and Methods 37 (2008), 159-174. Zbl1318.62009MR2412617DOI10.1080/03610920701648987
  18. Field, C. A., (1990), E. M. Ronchetti, Small Sample Asymptotics., Institute of Mathematical Statistics Monograph Series, Hayward 1990. MR1088480
  19. Fisher, R. A., 10.1093/mnras/80.8.758, Monthly Notes Royal Astronomical Society 80 (1920), 758-770. DOI10.1093/mnras/80.8.758
  20. Fisher, R. A., Statistical Methods for Research Workers. Second edition, (1928). MR0346954
  21. Galton, F., 10.2307/2841583, J. Anthropol. Inst. 15 (1886), 246-263. DOI10.2307/2841583
  22. Greene, W. H., Econometric Analysis., Macmillam Press, New York 1993. 
  23. Hájek, J., Šidák, Z., Theory of Rank Test., Academic Press, New York 1967. MR0229351
  24. Halmos, P. R., 10.1007/978-1-4613-8127-3_2, In: Mathematics Tomorrow (L. Steen, ed.), Springer Verlag, New York 1981, pp. 9-20. MR0618280DOI10.1007/978-1-4613-8127-3_2
  25. Hampel, F. R., Ronchetti, E. M., Rousseeuw, P. J., Stahel, W. A., 10.1002/9781118186435 MR0829458DOI10.1002/9781118186435
  26. Hansen, L. P., 10.2307/1912775, Econometrica 50 (1982), 1029-1054. Zbl0502.62098MR0666123DOI10.2307/1912775
  27. Harvey, A. C., 10.2307/1913974, Econometrica 44 (1976), 461-465. Zbl0333.62040MR0411063DOI10.2307/1913974
  28. Hausman, J., Newey, W., Voutersen, T., Chao, J., Swanson, N., 10.3982/qe89, Quantitative Economics 3 (2012), 211-255. MR2957106DOI10.3982/qe89
  29. Helland, I. S., Partial Least Squares Regression and Statistical Models., Scand. J. Statist. 17 (1990), 97-114. Zbl0713.62062MR1085924
  30. Hettmansperger, T. P., Sheather, S. J., 10.2307/2684169, Amer. Statist. 46 (1992), 79-83. MR1165565DOI10.2307/2684169
  31. Judge, G. G., Griffiths, W. E., Hill, R. C., Lutkepohl, H., Lee, T. C., The Theory and Practice of Econometrics. Second edition., J. Wiley and Sons, New York 1985. MR1007139
  32. Jurečková, J., Regression quantiles and trimmed least squares estimator under a general design., Kybernetika 20 (1984), 345-357. Zbl0561.62027MR0776325
  33. Kmenta, J., 10.3998/mpub.15701, Macmillan Publishing Company, New York 1986. Zbl0935.62129DOI10.3998/mpub.15701
  34. Krasker, W. S., 10.2307/1391499, J. Business Econom. Statist. 4 (1986), 437-444. DOI10.2307/1391499
  35. Krasker, W. S., Welsch, R. E., 10.2307/1913223, Econometrica 53 (1985), 1475-1488. Zbl0583.62095MR0809921DOI10.2307/1913223
  36. Krishnakumar, J., Ronchetti, E., 10.1016/s0304-4076(97)80014-0, J. Econometr. 78 (1997), 295-314. Zbl0900.62652MR1453482DOI10.1016/s0304-4076(97)80014-0
  37. Lopuhaa, H. P., 10.1214/aos/1176347386, Ann. Statist. 17 (1989), 1662-1683. MR1026304DOI10.1214/aos/1176347386
  38. Maronna, R. A., Morgenthaler, S., 10.1080/03610928608829187, Comm. Statist. - Theory and Methods 15 (1986), 1347-1365. Zbl0639.62023MR0836601DOI10.1080/03610928608829187
  39. Maronna, R. A., Yohai, V. J., 10.1007/bf00536192, Zeitschrift fűr Wahrscheinlichkeitstheorie und verwandte Gebiete 58 (1981), 7-20. MR0635268DOI10.1007/bf00536192
  40. Maronna, R. A., Yohai, V. J., 10.1016/s0378-3758(96)00046-8, J. Statist. Planning Inference 57 (1997), 233-244. Zbl0900.62173MR1440237DOI10.1016/s0378-3758(96)00046-8
  41. Mašíček, L., Optimality of the least weighted squares estimator., Kybernetika 40 (2004), 715-734. Zbl1245.62013MR2120393
  42. Mizon, G. E., 10.1016/0304-4076(94)01671-l, J. Econometr. 69 (1995), 267-288. Zbl0831.62100MR1354668DOI10.1016/0304-4076(94)01671-l
  43. Paige, C. C., Strakoš, Z., 10.1007/s002110100314, Numer. Math. 91 (2002), 117-146. Zbl0998.65046MR1896090DOI10.1007/s002110100314
  44. Phillips, P. C. B., Solo, V., 10.1214/aos/1176348666, Ann. Statist. 20 (1992), 971-1001. Zbl0759.60021MR1165602DOI10.1214/aos/1176348666
  45. Popper, K. R., The Logic of Scientific Discovery., (Logik der Forscung, Springer, Vienna 1935). Hutchinson and co., New York 1952. Zbl1256.03001MR0107593
  46. Portnoy, S., 10.1007/978-1-4615-7821-5_13, In: Robust and Nonlinear Time - Series Analysis (J. Franke, W. Ha̋rdle, and D. Martin, eds.), Springer Verlag, New York 1983, pp. 231-246. Zbl0568.62065MR0786311DOI10.1007/978-1-4615-7821-5_13
  47. Rao, R. C., 10.2307/2283583, J. Amer. Statist. Assoc. 65 (1970), 161-172. MR0286221DOI10.2307/2283583
  48. Rao, R. C., 10.1002/9780470316436, J. Wiley and Sons, New York 1973. Zbl0256.62002MR0346957DOI10.1002/9780470316436
  49. Robinson, P. M., 10.2307/1911033, Econometrica 55 (1987), 875-891. Zbl0651.62107MR0906567DOI10.2307/1911033
  50. Ronchetti, E., Trojani, F., 10.1016/s0304-4076(00)00073-7, J. Econometrics 101 (2001), 37-69. Zbl0996.62026MR1805872DOI10.1016/s0304-4076(00)00073-7
  51. Rousseeuw, P. J., 10.1080/01621459.1984.10477105, J. Amer. Statist. Assoc. 79 (1984), 871-880. MR0770281DOI10.1080/01621459.1984.10477105
  52. Rousseeuw, P. J., Leroy, A. M., 10.1002/0471725382, J. Wiley and Sons, New York 1987. Zbl0711.62030MR0914792DOI10.1002/0471725382
  53. Rousseeuw, P. J., Yohai, V., 10.1007/978-1-4615-7821-5_15, In: Robust and Nonlinear Time Series Analysis (J. Franke, W. Härdle, and R. D. Martin, eds.), Lecture Notes in Statistics 26 Springer Verlag, New York 1984, pp. 256-272. MR0786313DOI10.1007/978-1-4615-7821-5_15
  54. Štěpán, J., Teorie pravděpodobnosti (Probability Theory)., Academia, Praha 1987. 
  55. Huffel, S. Van, 10.1007/978-3-7908-2656-2_44, In: Proc. Computational Statistics, COMPSTAT 2004 (J. Antoch, ed.), Physica Verlag/Springer, Heidelberg 2004, pp. 539-555. MR2173049DOI10.1007/978-3-7908-2656-2_44
  56. Víšek, J. Á., A cautionary note on the method of Least Median of Squares reconsidered., In: Trans. Twelfth Prague Conference on Information Theory, Statistical Decision Functions and Random Processes (P. Lachout, ed.), Academy of Sciences of the Czech Republic, Praha 1994, pp. 254-259. 
  57. Víšek, J. Á., Robust instruments., In: Robust'98 (J. Antoch and G. Dohnal, eds.), Union of Czech Mathematicians and Physicists, Matfyzpress, Praha 1998, pp. 195-224. 
  58. Víšek, J. Á., The robust regression and the experiences from its application on estimation of parameters in a dual economy., In: Proc. Conference Macromodels'99, Wroclaw University 1999, pp. 424-445. 
  59. Víšek, J. Á., Regression with high breakdown point., In: Robust 2000 (J. Antoch and G. Dohnal, eds.), Union of Czech Mathematicians and Physicists, Matfyzpress, Praha 2000, pp. 324-356. 
  60. Víšek, J. Á., The least weighted squares I. The asymptotic linearity of normal equations., Bull. Czech Econometr. Soc. 9 (2002), 31-58. 
  61. Víšek, J. Á., The least weighted squares II. Consistency and asymptotic normality., Bull. Czech Econometr. Soc. 9 (2002), 1-28. MR2208518
  62. Víšek, J. Á., Development of the Czech export in nineties., In: Konsolidace vládnutí a podnikání v České republice a v Evropské unii I. Umění vládnout, ekonomika, politika, Matfyzpress, Praha 2003, pp. 193-220. 
  63. Víšek, J. Á., 10.1007/978-3-7908-2656-2, In: Proc. COMPSTAT'2004 (J. Antoch, ed.), Physica Verlag/Springer, pp. 1947-1954. MR2173224DOI10.1007/978-3-7908-2656-2
  64. Víšek, J. Á., 10.1007/978-3-7908-1709-6, In: Proc. COMPSTAT 2006 (A. Rizzi and M. Vichi, eds.), Physica Verlag/Springer, Heidelberg 2006, pp. 777-786. MR2173224DOI10.1007/978-3-7908-1709-6
  65. Víšek, J. Á., Kolmogorov-Smirnov statistics in multiple regression., In: Proc. ROBUST 2006 (J. Antoch and G. Dohnal, eds.), pp. 367-374. 
  66. Víšek, J. Á., 10.1007/s10463-007-0159-8, Ann. Inst. Statist. Math. 61 (2009), 543-578. Zbl1332.62246MR2529966DOI10.1007/s10463-007-0159-8
  67. Víšek, J. Á., 10.1007/s10463-007-0159-8, In: IMS Collections. Nonparametrics and Robustness in Modern Statistical Inference and Time Series Analysis: Festschrift for Jana Jurečková, 2010, pp. 254-267. MR2808385DOI10.1007/s10463-007-0159-8
  68. Víšek, J. Á., Heteroscedasticity resistant robust covariance matrix estimator., Bull. Czech Econometric Society 17 (2010), 33-49. 
  69. Víšek, J. Á., Consistency of the least weighted squares under heteroscedasticity., Kybernetika 47 (2011), 179-206. Zbl1228.62026MR2828572
  70. Víšek, J. Á., Weak n - consistency of the least weighted squares under heteroscedasticity., Acta Universitatis Carolinae, Mathematica et Physica 2 (2011), 51, 71-82. Zbl1228.62026MR2808296
  71. Víšek, J. Á., 10.1080/02331881003768891, Statistics 45 (2011), 497-508. Zbl1229.62050MR2832181DOI10.1080/02331881003768891
  72. Víšek, J. Á., 10.1007/s11009-014-9432-5, Workshop on Algorithm for Outliers/regressors Selection organized by Bent Nielsen, Nuffield College, Oxford 2013. Methodology and Computing in Applied Probability 17 (2014), 4, 999-1014. DOI10.1007/s11009-014-9432-5
  73. Wagenvoort, R., Waldmann, R., 10.1016/s0304-4076(01)00102-6, J. Econometr. 106 (2002), 297-324. Zbl1038.62061MR1885372DOI10.1016/s0304-4076(01)00102-6
  74. White, H., 10.2307/1912934, Econometrica 48 (1980), 817-838. MR0575027DOI10.2307/1912934
  75. Wooldridge, J. M., Econometric Analysis of Cross Section and Panel Data., MIT Press, Cambridge 2001. (Second edition 2008.) Zbl1327.62009MR2768559
  76. Wooldridge, J. M., Introductory Econometrics. A Modern Approach., MIT Press, Cambridge 2006. (Second edition 2009.) 

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.