Explain mathematically why the cumulative sampling of controls yields a case-control odds ratio that is an unbiased estimate of the cohort odds ratio, but a biased estimate of the cohort risk ratio (note: discuss in terms of the fraction g).

Cumulative Sampling Cases Controls where 0

Exposed A gB

Not exposed C gD

6A) Referring to the prior problem, explain what would happen if the fraction g were equal to 1.0. What measure of association could we calculate?