11. |
Book Review |
|
Statistics,
Volume 18,
Issue 3,
1987,
Page 378-378
K. Henschke,
Preview
|
PDF (275KB)
|
|
摘要:
N. Keyfitz, John A. Beekman: Demography through problems. Springer-Verlag, Berlin-Heidelberg - New York - Tokyo 1984, VIII, 141 S., 22 Abb., DM 78,-.
ISSN:0233-1888
DOI:10.1080/02331888708802033
出版商:Akademie-Verlag
年代:1987
数据来源: Taylor
|
12. |
On the type-B integral equation and the distribution of wilks statist for testing independence of several groups of variables |
|
Statistics,
Volume 18,
Issue 3,
1987,
Page 379-387
Jen Tang,
A.K. Gupta,
Preview
|
PDF (1880KB)
|
|
摘要:
In this paper, WILKS'type-B integral equation is solved in the general form of a series of beta functions and a series of weighted gamma functions as proposed by WALD and BROOKNER 1941. The coefficients in both representations can be obtained by explicit recurrence relartions, therefore the results solve many distributional problems and have the fewest computational difficulties of any representation that has surfaced to date. The radius of convergence of the second series representation is given, whereas the convergence property of the first series representation is given, whereas the convergence property of the first series representation was studied by WALD and Brookner. The exact null distributions of WILKS' statistic A for testing the independence of several groups of variables and of V = -log A are given. The coefficients in all the series representration can be computed recursilvely and hence can be obtained easily with the help of modern computatinal facilities
ISSN:0233-1888
DOI:10.1080/02331888708802034
出版商:Akademie-Verlag
年代:1987
数据来源: Taylor
|
13. |
Book Review |
|
Statistics,
Volume 18,
Issue 3,
1987,
Page 388-388
W. Jahn,
Preview
|
PDF (295KB)
|
|
摘要:
Victor Pan: How to Multiply Matrices Faster. Lecture Notes in Computer Science 179. Springer-Verlag, Berlin - Heidelberg - New York - Tokyo 1984, xi, 312 pp., DM 32,-
ISSN:0233-1888
DOI:10.1080/02331888708802035
出版商:Akademie-Verlag
年代:1987
数据来源: Taylor
|
14. |
an approximation for multivariate normal probabilities of rectangular regions |
|
Statistics,
Volume 18,
Issue 3,
1987,
Page 389-400
Thomas Royen,
Preview
|
PDF (2809KB)
|
|
摘要:
The multivariate normal probability of a given rectangular region as a function of correlations is approximated by TAYLOR polynomials. Because of the poor convergence properties of the classical tetrachoric expansion the center of this series is shifted to a correlation matrix Romnear the given matrix R, where Ro has a simple m-factirial structure. For computiations only m≦2 is used. For the convergence of this expansion a sufficient condition is proved. Especially for the distribution of the maximum modulus satisfying results are obtained for larger probabilities using only TALYLOR polynomials of 2nd degree with m=1
ISSN:0233-1888
DOI:10.1080/02331888708802036
出版商:Akademie-Verlag
年代:1987
数据来源: Taylor
|
15. |
On the validity of the perturbation method in asymptotic theory |
|
Statistics,
Volume 18,
Issue 3,
1987,
Page 401-414
Jeanne fine,
Preview
|
PDF (3994KB)
|
|
摘要:
The perturbation methods and the Taylor expansions are very often used to obtain test statistics approximations in multivariate analysis (Specially in Principal Component and Canonical Analyses). These approximations are then used to obtain formal Edgeworth expransions of the distribution functions of the statistics. BHATTACHARYA and GHOSH 1978 have justified these practices under suitable assumptions. In this paper a non classical perturbation problem is solved in order to obtain almost surely expansions of test statistics
ISSN:0233-1888
DOI:10.1080/02331888708802037
出版商:Akademie-Verlag
年代:1987
数据来源: Taylor
|
16. |
On quantile processes for m-dependent Rv's |
|
Statistics,
Volume 18,
Issue 3,
1987,
Page 423-435
Eman-Eldin A.A.Aly,
Preview
|
PDF (2894KB)
|
|
摘要:
We obtain strong and weak approximations for quantile processes for m-dependent random variables. We apply our results in the two-sample to obtain condidence bands for quantile plots and prove some CHERNOFF-SAVAGE theorems for m-dependent random variables
ISSN:0233-1888
DOI:10.1080/02331888708802039
出版商:Akademie-Verlag
年代:1987
数据来源: Taylor
|
17. |
Book Review |
|
Statistics,
Volume 18,
Issue 3,
1987,
Page 436-436
K. Henschke,
Preview
|
PDF (256KB)
|
|
摘要:
U. Tüshaus: Aggregation binärer Relationen in der qualitativen Datenanalyse, (Mathematical systems in economics, Ed. 82.) Verlagsgruppe Athenäum/Hain/Hanstein,Königsitein/Ts. 1983. 107 S., DM 29,80.
ISSN:0233-1888
DOI:10.1080/02331888708802040
出版商:Akademie-Verlag
年代:1987
数据来源: Taylor
|
18. |
On the anscombe condition for stochastic processes in a separable banach space |
|
Statistics,
Volume 18,
Issue 3,
1987,
Page 437-451
G. Siegel,
Preview
|
PDF (3278KB)
|
|
摘要:
This paper treats the validity of A NSCOMBE-type conditions for special stochastic processes in a BANACH space. Such conditions concern the uniform continuity of sequences of stochastic processes and are useful for proving limit theorems of randomly indexed sums. The first part is devotes to stochastic processes with independent increments. The second part investigates stochastic processes generated by operator normed sums of weakly dependent random variables (strongly mixing or unigorm;y strongly mixing). The special case of operator normed sums of independent random varables in an EUCLIDEAN space was treated in GLESER [4], but these results are incorrect.
ISSN:0233-1888
DOI:10.1080/02331888708802041
出版商:Akademie-Verlag
年代:1987
数据来源: Taylor
|
19. |
Book Review |
|
Statistics,
Volume 18,
Issue 3,
1987,
Page 452-452
K. Fischer,
Preview
|
PDF (193KB)
|
|
摘要:
David s. Salsburg: Understanding Randomness, Exereises for Statisticians, Lecture notes in statistics, vol.6. Marcel Dekker,Inc.New York - Basel 1983, 105 S.
ISSN:0233-1888
DOI:10.1080/02331888708802042
出版商:Akademie-Verlag
年代:1987
数据来源: Taylor
|
20. |
A new fast method for computer generation of gamma and beta random variables by transformations of uniform variables |
|
Statistics,
Volume 18,
Issue 3,
1987,
Page 453-464
GH Barbu,
Preview
|
PDF (2059KB)
|
|
摘要:
The Paper presents a fundamental lemma which is used for computer generation of a random variable by transforming of a uniform random vector. The lemma is used to build-up perormant algorithms for generating gamma and beta random variables. Some computer tests and comparisons with other known methods are reported
ISSN:0233-1888
DOI:10.1080/02331888708802043
出版商:Akademie-Verlag
年代:1987
数据来源: Taylor
|