Information Technology Reference
In-Depth Information
In other words, Bayes' Theorem might prove applicable if regardless of
the form of the a priori distribution, one came to more or less the same
conclusion.
Courts in California,
14
Illinois, Massachusetts,
15
Utah,
16
and Virginia
17
also have challenged the use of the 50-50 assumption. In State v.
Jackson,
18
the expert did include a range of prior probabilities in her testi-
mony, but the court ruled the trial judge had erred in allowing the expert
to testify as to the conclusions of Bayes' Theorem in stating a conclusion,
that the defendant was 'probably' the father of the victim's child.
In Cole v. Cole,
19
a civil action, the Court rejected the admission of an
expert's testimony of a high probability of paternity derived via Bayes'
formula because there was strong evidence the defendant was sterile as a
result of a vasectomy.
“The source of much controversy is the statistical formula gener-
ally used to calculate the provability of paternity: the Bayes
Theorem. . . . Briefly, the Bayes Theorem shows how new statistical
information alters a previously established probability....When a
laboratory uses the Bayes Theorem to calculate a probability of
paternity it must first calculate a 'prior probability of paternity'.
. . . This prior probability usually has no connection to the case at
hand. Sometimes it reflects the previous success of the laboratory at
excluding false fathers. Traditionally, laboratories use the figure
50% which may or may not be appropriate in a given case.”
“Critics suggest that this prior probability should take into
account the circumstances of the particular case. For example if
the woman has accused three men of fathering her child or if there
are reasons to doubt her credibility, or if there is evidence that the
husband is infertile, as in the present case, then the prior proba-
bility should be reduced to less than 50%.”
20
The question remains as to what value to assign the prior proba-
bility. And whether absent sufficient knowledge to pin down the
prior probability with any accuracy we can make use of Bayes'
Theorem at all. At trial, an expert called by the prosecution in
14
State v. Jackson, 320 NC 452, 358 S.E.2d 679 (1987).
15
Commonwealth v. Beausoleil, 397 Mass. 206 (1986).
16
Kofford v. Flora 744 P.2d 1343, 1351-2 (1987).
17
Bridgeman v. Commonwealth, 3 Va. App 523 (1986).
18
320 N.C. 452 (1987).
19
74 N.C. App. 247,
aff'd
. 314 N.C. 660 (1985).
20
Id. 328.
