Biometrika Trust

On the Ratio of Two Correlated Normal Random Variables

Author(s): D. V. Hinkley
Source: Biometrika, Vol. 56, No. 3 (Dec., 1969), pp. 635-639
Published by: Oxford University Press on behalf of Biometrika Trust
Stable URL: http://www.jstor.org/stable/2334671
Accessed: 01-10-2015 11:07 UTC

Your use of the JSTOR archive indicates your acceptance of the Terms & Conditions of Use, available at http://www.jstor.org/page/
info/about/policies/terms.jsp

JSTOR is a not-for-profit service that helps scholars, researchers, and students discover, use, and build upon a wide range of content
in a trusted digital archive. We use information technology and tools to increase productivity and facilitate new forms of scholarship.
For more information about JSTOR, please contact support@jstor.org.

Biometrika Trust and Oxford University Press are collaborating with JSTOR to digitize, preserve and extend access to
Biometrika.

http://www.jstor.org

This content downloaded from 139.184.14.159 on Thu, 01 Oct 2015 11:07:04 UTC
All use subject to JSTOR Terms and Conditions
Biometrika(1969), 56, 3, p. 635 635
Printed in GreatBritain

normalrandomvariables
On theratioof twocorrelated
By D. V. HINKLEY
ImperialCollege

SUMMARY
The distribution oftheratiooftwocorrelated normalrandomvariablesis discussed.The
exact distribution and an approximationare compared.The comparisonis illustrated
numerically in the linearmodel
forthe case of the normalleast squaresestimateof cc/,8
E(yj) = ac+,i (i = 1, ..., n) withuncorrelated error
normal terms.

1. INTRODUCTION
In a regression ofinterestto estimatetheratio
analysisofbivariatedata it is sometimes
oftwopopulationparameters. Two examplesare:
(i) The analysisofthe simplelinearmodelyi = ac+,/ui+ ei (i = 1,..., n), wheree], *,en
are independently normallydistributed withzeromeanand variance0.2; then - c/,8is the
interceptoftheregression linewith theu-axis.

Y
{
(ii) The analysisofthetwo-linelinearmodel
cc+/lbiu+i (i = 1,...,n1),
2+fl2Ui+6i (t=n,+ 1, ....,nL+n2),
withnotationas in (i); theratio(c1 - c2)/(,82 -1) is the abscissa of the intersectionof the
two regressionlines.
In each example the maximum likelihood estimate of the ratio is the ratio of two cor-
related normally distributedvariables, themselves estimates. In this paper the general
distributionofratios ofthis type is derivedand comparedwiththe approximationobtained
by assuming the denominatorrandom variable to be of constant sign. This has particular
relevance to the examples above, and a numerical comparisonis given for (i) above.

2. THEORETICAL RESULTS
Let X1 and X2 be normally distributedrandom variables with means Ot,variances ort
(i p, and let W = X1/X2. The exact distributionof W
= 1, 2) and correlationcoefficient

and the standard approximationbased on assuming X2 > 0 are examined in some detail.

2-1. Exact distributionof W

The distributionof W when O. = 02 = 0 was given by Geary (1930). Fieller (1932) and
more recentlyMarsaglia (1965) consideredthe general problem with non-zeromeans. The
latter studied the ratio a + Y1

in our notation,whereY, and Y2are independentN(0, 1) variables. The connexionbetween

Z and W is said (incorrectly)to be that 'It sufficesto study Z; translationsand changes of

This content downloaded from 139.184.14.159 on Thu, 01 Oct 2015 11:07:04 UTC
All use subject to JSTOR Terms and Conditions
636 D. V. HINKLEY
scale will provide the general ratio W.' This assumes there are fourparameters,whereas
thereare five: 0t, 02, o2t,o2 and p. In fact Z has no great advantage over W, since the distri-
butions of both involve the bivariate normal distribution.
If the joint densityof (X1, X2) is g(x,y) and the p.d.f. of W is f(w), then

f(w) = f IyI g(wy,y)dy.

On substitutingthe bivariate normal densityforg(x,y), a simple integrationgives

f(w)
_ b(w)d(w)
f)V(27r) oi2a3(w)
(D b(w)
[ (1 -p2) a(w)f
(D b(w)
(1 -p2)a(w)JJ
H
2
p
+ V,(1 expt } (1
7Tf1, f2a2(W) Xp(2(1 _ p2>),1

where a(w) = - 2pw

+-
I

b(w) W P(01 02W) +62

021 1+02 2~
_= 2PI02J+
02 010 2
+ 2
1 2
- ca2(W)1
d(w) = exp ~b2(W)
2(w p2)a2(w)f (2)

Also (D = f 0(fu)du, where 05(u)= e

This resultforthe probability density functionof W was given by Fieller (1932).

The cumulative distributionfunctionF(w) of W is found by direct calculation to be
- o
F(w) = L 01-t92W _ 2. 0,2W-PC1 +L( 02W 02. 02 W -Po-, (3)
F) L
(o2a(w) o2' 12a(w) +L{o2a(w) ' oo102a(w) (

where L(h,lk;y)= 21J2, f exp{_x 2(17 dxdy

is the standard bivariate normal integraltabulated by the National Bureau of Standards

(1959).
It is easy to see from(3) thatas 02/o2-+ oc, i.e. as pr(X2 > 0) - 1,

F(w)-> (D O2Wa w) (4)

a fact which is used in approximatingto F(w).

2*2. ComparisonofF(w) withits approximation

If 0 < 0-2 < 02, the limitin (4) suggeststhat

F*(w) = 1(D 02W-1

a) (5)

will be a useful approximationto F(w). It is then importantto compare F(w) and F*(w) in
some detail.

This content downloaded from 139.184.14.159 on Thu, 01 Oct 2015 11:07:04 UTC
All use subject to JSTOR Terms and Conditions
 Ratio of correlatednormal random variables 637
Now F(w) = pr (X1-wX2 < 0, X2 > O) + pr (X1-wX2 > 0, X2 < 0)
= F*(w) + pr(X2 < 0) {1-2 pr (X1-wX2 < 0 X2 < 0)}, (6)
so that IF(w)-F*(w)I < pr(X2 < 0) = 'D(-62/o2). (7)
This bound on the difference
is attained at w = + oo, for,by the definitionofF*(w) or by (6),
F*(-oo) = (D((-02/o2) and F*(oo) = 1-F(-02/o2), (8)
whereas F(w) is proper.Note that (7), a familiarresult,impliesF* -> F uniformlyas O-2 -> 0.
Further comparison is possible by examination of the derivative of F*(w), which by
(5) and (2) is (w) b )(w)
f*Mw) V2rooa3(w)
= (9)

Clearlyf*(w) < 0 when b(w) < 0, that is forw in the region

w< -- < ?),

W(r2
(10)

or w ?>-- (2 > ?)'

where 3/b1= PO1Oi02-020i and = When b(w) > 0, it is easy to see that
?I2 P620102-l0i2.
f(w) > f*(w). For by (1) and (9)

f(w) ,J b(w) f b(w) |2V(1-p2)a(w)Af b(w)

f
I
_

f*(w) ta(w)(1 -p2) a(w)J(1_ p2)+ b(w) Va(w)(l - 2) J

The inequality (D(- u) < u-1s(u) (u > 0) gives the desired result. Hence f(w) > f*(w) for
all w. That is, F(w)-F*(w) increases monotonically from - D(- 02/o2) at w = -0o to
FD(-02/o2) at w = +oo.
The next step is to determinethe point at which F(w) = F*(w). Now by (6)

(__2) (11)
0 2 _2f_-?? -??
g((x,y)dxdy,
F(w) = F*(w)+D

whereg(x,y) is the bivariate normal density.The double integralin (11) is easily reduced to

Y:2 0(u)D{(wo'2 Pa+( +p2)-1)}

w du, (12)

so that the solutionto F*(w) = F(w) is the solutionto

~(u)du 2 u ( _p2) )
=
f:2 1(l-
When = 0, the solution is wo =
/fr2 P01/02, and in general the solution wo satisfies

wo< PC1if 2< O

wo > P if pb2> 0;
02

in factIWO
- increasesas h2l increases.
(PC1/02)1f

This content downloaded from 139.184.14.159 on Thu, 01 Oct 2015 11:07:04 UTC
All use subject to JSTOR Terms and Conditions
638 D. V. HINKLEY
Finally, moreprecisebounds than (7) can be obtained forfinitew. Startingwith (12) it is
possible to put bounds on the double integral,firstintegratingby parts and then using the
inequality J(D(u)< 5(u)/(- u) fornegative u. The resultingbounds on F(w) - F*(w) are
J < F(w)-F*(w) < J+K(w) (w > PO10C2),

J+K(w) , F(w)-F*(w) , J (w <PO/O2) (13)

where J= (D )
[12' (a J2V(lp2)}]

and K(w) =2(WO-2- ~ l

PO-IL) j'w02 -O ( b(w)
acr102a(w) 6(C c2a(w)) a(w)J(1 _p2)

3. A NUMERICAL ILLUSTRATION
To illustrate the results in the previous section, in particular the new bounds (13) on
F(w) - F*(w), several calculations were carried out for the simple linear regressioncase
mentioned in ? 1. The variables X1 and X2 are respectively& and and specificvaluesAl,
a = 0, ,8 = 02, o-= 1 are used. The covariance matrixof (&(, ) gives the formulaefor o-,
J2 and p. Lastly, O, = acand O2 = fi.
The shorttable given (Table 1) is forthe case n = 10. Values of F(w), F*(w), bounds (13)
and uniformbound (7), are given forseven values of w. The values of F(w) were obtained
by a two-dimensionaliterative Simpson's Rule, and are correctto the number of figures
given.

Table 1. ComparisonofF(w) and F*(w) in theregressioncase with

a = 0,8 = 0-2, o: = I and n = 10
Bounds (13)

w F(w) F*(w) Lower Upper Bound (7)

-15 0*05939 0*09403 - 0.03464 - 0.03462 0.03464
-10 0.08995 0 12458 - 0.03464 - 0.03462
-5 0-16739 0*20203 -0-03464 -O003462
0 0*46536 0*50000 - 0.03464 - 0.03462
5 096445 0.99908 - 0.03463 - 0.03462
10 0-96568 0-99967 -0-03462 -0*03352
15 0*96832 0.99698 - 0.03462 - 0*02495

The value of- 3fr1/If2 is 7 0 and ?f2> 0, SO that by (10) F*(w) is decreasingforw > 7 0,
albeit veryslowly.The precisionof the bounds (13) is quite striking,and it is interestingto
see that the uniformbound is itselfnearly attained over a large part of the range. The
bounds do become slacker in the tails. This and other examples suggest as an improved
approximation to F(w) F**(w) = F*(w) - @((- 02/02), (14)

when F*(w) > F(w) over most of the range; the correctiontermin (14) would be added if
F*(w) < F(w) over most of the range.
The relative simplicityofthe approximationsF*(w) and F**(w) facilitatesextensiveuse
of F(w), particularlyin the two regressionexamples of ? 1, where approximation is very

This content downloaded from 139.184.14.159 on Thu, 01 Oct 2015 11:07:04 UTC
All use subject to JSTOR Terms and Conditions
 Ratio of correlatednormal random variable8 639
accurateformoderatesamplesizes.Foran applicationto thetwo-phaseregressionsituation,
see Hinkley(1969).Approximation maybe usefulevenforcomputing a singlevalueofF(w)
sincecomputation of(3) can ofteninvolvetrivariate fromtablesofL(h,k;y).
interpolation

to MrsE. A. Chambersforthenumericalcomputations.
I am grateful

REFERENCES

FIELLER, E. C. (1932). The distributionof the index in a normalbivariate population. Biometrika24,

428-40.
GEARY, R. C. (1930). The frequencydistributionof the quotient of two normalvariates. J. B. Statist.
Soc. 93, 442-6.
HINKLEY, D. V. (1969). Inference about the intersectionin two-phase regression.Biometrika56,
495-504.
MARSAGLIA, G. (1965). Ratios of normal variables and ratios of sums of uniformvariables. J. Am.
Statist.Ass. 60, 193-204.
NATIONAL BUREAU OF STANDARDS (1959). Tables of theBivariate Normal DistributionFunction and
Related Functions. Applied MathematicsSeries, no. 50. Washington: U.S. GovernmentPrinting
Office.

[ReceivedJanuary 1969. RevisedMay 1969]

This content downloaded from 139.184.14.159 on Thu, 01 Oct 2015 11:07:04 UTC
All use subject to JSTOR Terms and Conditions