does not fall within this range, it is not a plau-sible value with 95% confidence; thus the hy-pothesis that the true rate is 3 is rejected atα= 0.05.3. There are two equivalent approaches.Letm= 4nbe the total number of trials. Due to independence,we can solve directly formand choose the smallestinteger equal to or larger thanmthat is divisibleby 4.P(atleast1success) = 1−P(0successes) =1−.98m. We wish to choosemso that.98m= 0.20.This can be done by trial and error or, directly, usinglogs.m∗ln(.98) =ln(.20).This results inm=79.66. Rounding up to 80 (and dividing by 4) resultsinn= 20.Equivalently, letYbe the number ofsuccesses out of 4 trials. Then,P(Y= 0) =.984=.92237. Then, withnas the number of ‘sets’ of trials,.92237n= 0.20 using similar reasoning to the above.Trial and error – or logs – again results inn= 20.4.(a) FALSE — The only way one can obtain a neg-ative value of F is if one has made a mistake.Even if all data values are negative, F canneverbe less than 0.(b) FALSE — Since you are in ‘planning’ mode,the underlying variance should be viewed asknown. We knowV ar(ˆb1) =σ2y.x/P(xi−¯x)2.
This is the end of the preview.
access the rest of the document.
Null hypothesis, Bonferroni, null hypothesis states