Page -9-
Statistics for Lawyers
Problem Set # 5– Due /04
Name_________________________________(Please Print)
1. Suppose that a study shows that the rate of childhood cancer mortality increases from
about 1 per 1,000 to 4 per 1,000 when the mothers receive diagnostic x-rays during
pregnancy. Show that the odds ratio for cancer mortality closely approximates the
relative risk for cancer mortality on these data.
Ans.__________________________________________________________________________
2. Show that if Xe is the rate of disease in an “exposed” population (the exposure being good
or bad) and Xu is the rate in the unexposed population, the odds ratio will portray a larger
effect (good or bad) for the exposure than the relative risk.
Ans__________________________________________________________________________
3. (A) If a certain exposure reduces the rate of a disease, the odds ratio for the disease in the
exposed vs. unexposed populations will lie in what range of possible values? (B) Same
question if the exposure increases the rate of disease.
Ans.(A)_______________________________(B)_____________________________________
4. Same questions as in Question (3) above, except that we use the natural logarithm of the
odds ratio.
Ans.(A)______________________________(B)______________________________________

Page -10-
5. Referring to the retrospective study in the Bail/Bench Warrant case (1.5.2), explain
briefly why the probability of a bench warrant currently issuing given previous issuance
is not reasonably estimated by 54/77 = 0.701.
Ans._________________________________________________________________________
______________________________________________________________________________
6. Referring to the same retrospective study, use the table below to show that the
retrospective odds ratio is the same as the prospective odds ratio. (This is quite simple, so
don’t get all wound up.)
                                                                                                                                           

	BW Prev. Issued	No BW Prev. Issued	Total
BW Currently Issued	a	b	a+b
No BW Curr. Issued	c	d	c+d
Total	a+c	b+d	a+b+c+d

        Ans.__________________________________________________________________________

End of Problem Set # 5