1962
DOI: 10.1214/aoms/1177704581
|View full text |Cite
|
Sign up to set email alerts
|

The Numerical Evaluation of Certain Multivariate Normal Integrals

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
36
0
1

Year Published

1964
1964
2017
2017

Publication Types

Select...
5
3
1

Relationship

0
9

Authors

Journals

citations
Cited by 94 publications
(37 citation statements)
references
References 0 publications
0
36
0
1
Order By: Relevance
“…then a computational load to evaluate n dimensional normal probability integrals reduces to be n /2 or( n -1)/2 dimensional probability integrals (12) (13) . However, it consumes still much time to calculate n SO when n is more than 5 because of multiple integrals.…”
Section: Somentioning
confidence: 99%
“…then a computational load to evaluate n dimensional normal probability integrals reduces to be n /2 or( n -1)/2 dimensional probability integrals (12) (13) . However, it consumes still much time to calculate n SO when n is more than 5 because of multiple integrals.…”
Section: Somentioning
confidence: 99%
“…Let the correlation matrix be non-singular and ρ 11 = 1. Under these conditions Curnow and Dunnett [3] derive the following reduction formula…”
Section: The Curnow and Dunnett Integral Reduction Techniquementioning
confidence: 99%
“…Martin and Wilson computed an approximation to the probability of selection due to Curnow and Dunnett (1962). Owing to advances in computation, it is possible to obtain accurate estimates of multidimensional integrals (NAG, 1984) without excessive computer time.…”
Section: Calculationmentioning
confidence: 99%
“…Second, Martin and Wilson employed a form of "soft selection" in which the probability of selection varied in a sigmoid fashion over the range of the character. This selection function was based on a model described by Curnow and Dunnett (1962). In this model, the observed variate, y, comprises a value x on an underlying distribution of liability, and a random error component z. Truncate (hard) selection is applied to the y variate to effect a sigmoid function of selection on the underlying variate, x.…”
Section: Introductionmentioning
confidence: 99%