Geodesic
Two families of normality tests based on Polya characterization, and their efficiency
Zapiski Nauchnykh Seminarov POMI, Probability and statistics. Part 9, Tome 328 (2005), pp. 147-159 
V. V. Litvinova; Ya. Yu. Nikitin. Two families of normality tests based on Polya characterization, and their efficiency. Zapiski Nauchnykh Seminarov POMI, Probability and statistics. Part 9, Tome 328 (2005), pp. 147-159. http://geodesic.mathdoc.fr/item/ZNSL_2005_328_a7/
@article{ZNSL_2005_328_a7,
     author = {V. V. Litvinova and Ya. Yu. Nikitin},
     title = {Two families of normality tests based on {Polya} characterization, and their efficiency},
     journal = {Zapiski Nauchnykh Seminarov POMI},
     pages = {147--159},
     year = {2005},
     volume = {328},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/ZNSL_2005_328_a7/}
}
TY  - JOUR
AU  - V. V. Litvinova
AU  - Ya. Yu. Nikitin
TI  - Two families of normality tests based on Polya characterization, and their efficiency
JO  - Zapiski Nauchnykh Seminarov POMI
PY  - 2005
SP  - 147
EP  - 159
VL  - 328
UR  - http://geodesic.mathdoc.fr/item/ZNSL_2005_328_a7/
LA  - ru
ID  - ZNSL_2005_328_a7
ER  - 
%0 Journal Article
%A V. V. Litvinova
%A Ya. Yu. Nikitin
%T Two families of normality tests based on Polya characterization, and their efficiency
%J Zapiski Nauchnykh Seminarov POMI
%D 2005
%P 147-159
%V 328
%U http://geodesic.mathdoc.fr/item/ZNSL_2005_328_a7/
%G ru
%F ZNSL_2005_328_a7

Voir la notice du chapitre de livre provenant de la source Math-Net.Ru

For testing of normality we introduce two families of statistics based on extended Polya characterization of the normal law. The first family depends on parameter $a\in(0,1)$, and for any $a$ its members are asymptotically normal and consistent for many alternatives of interest. We study the local Bahadur efficiency of these statistics as a function of $a$ and find that for common alternatives the Polya case $a=1/\sqrt{2}$ is the worst and the maximum of efficiency is attained for $a$ close to 0 or 1. The second family depends on natural $m$ and the efficiency increases when $m$ grows.

[1] A. M. Kagan, Yu. V. Linnik, S. R. Rao, Kharakterizatsionnye zadachi matematicheskoi statistiki, Nauka, M., 1972 | MR

[2] V. S. Korolyuk, Yu. V. Borovskikh, Teoriya $U$-statistik, Naukova Dumka, Kiev, 1989 | MR

[3] Yu. V. Linnik, “Lineinye statistiki i normalnyi zakon raspredeleniya”, Dokl. AN SSSR, 83:3 (1952), 353–355 | MR | Zbl

[4] Yu. V. Linnik, “Lineinye formy i statisticheskie kriterii, I, II”, Ukr. matem. zh., 5:2–3 (1953), 207–243, 247–290 | MR

[5] V. V. Litvinova, Asimptoticheskie svoistva kriteriev simmetrii i soglasiya, osnovannykh na kharakterizatsiyakh, Kand. diss. SPbGU, 2004

[6] Ya. Yu. Nikitin, Asimptoticheskaya effektivnost neparametricheskikh kriteriev, Nauka, M., 1995 | MR

[7] Ya. Yu. Nikitin, E. V. Ponikarov, “Grubaya asimptotika veroyatnostei bolshikh uklonenii chernovskogo tipa funktsionalov Mizesa i $U$-statistik”, Trudy Sankt-Peterburgskogo matematicheskogo obschestva, 7, 1999, 23–47 | MR

[8] I. A. Ahmad, A. R. Mugdadi, “Testing normality using kernel methods”, J. of Nonparametric Stat., 15 (2003), 273–288 | DOI | MR | Zbl

[9] A. Azzalini, “A class of distributions which includes the normal ones”, Scand. J. Stat., 12 (1985), 171–178 | MR | Zbl

[10] R. R. Bahadur, Some limit theorems in statistics, SIAM, Philadelphia, 1971 | MR | Zbl

[11] W. Bryc, The normal distribution. Characterizations with applications, Lect. Notes Statistics, 100, Springer-Verlag, Berlin, 1995 | MR | Zbl

[12] F. De Helguero, “Sulla rappresentazione analitica delle statistiche abnormali”, Atti del IV Congresso Internaz. dei Matematici, Roma, 8 (1908), 288–289

[13] W. Hoeffding, “A class of statistics with asymptotically normal distribution”, Ann. Math. Stat., 19 (1948), 293–325 | DOI | MR | Zbl

[14] P. L. Janssen, Generalized Empirical Distribution Functions with Statistical Applications, Limburgs Universitair Centrum, Diepenbeek, 1988

[15] A. V. Kakosyan, L. B. Klebanov, J. A. Melamed, Characterization of distributions by the method of intensively monotone operators, Lect. Notes Mathematics, 1088, Springer-Verlag, Berlin, 1984 | MR | Zbl

[16] A. M. Mathai, G. Pederzoli, Characterizations of the Normal Probability Law, Wiley, NY, 1977 | MR | Zbl

[17] P. Muliere, Ya. Nikitin, “Scale-invariant test of normality based on Polya's characterization”, Metron, 60:1–2 (2002), 21–33 | MR | Zbl

[18] G. Polya, “Herleitung des Gauss'schen Fehlergesetzes aus einer Funktionalsgleichung”, Math. Zeitschrift, 18 (1923), 96–108 | DOI | MR | Zbl

[19] C. R. Rao, Linear Statistical Inference and its Applications, Wiley, NY, 1965 | MR | Zbl

[20] O. Vasicek, “A test for normality based on sample entropy”, J. Roy. Stat. Soc. Ser. B, 38 (1976), 54–59 | MR | Zbl