{[ promptMessage ]}

Bookmark it

{[ promptMessage ]}

# hw4 - 9.10(a The percent \$ho have laslinr waking symptolns...

This preview shows pages 1–2. Sign up to view the full content.

9.10. (a) The percent \$ho have laslinr waking symptolns is the total of the lirst column divided bv the grand total: fr : 51 .98c/(.. (b) The per- cent rvho have both t'aking and bedtime symp- toms is the count in the upper left divided bv the .crrrnd lotrrl. ,,0 lo:S';. {c) fo le.l H, Therc is no relationship between naking and bcdtime svnptonls vs. 11,,: Thcre is a relationship. uc find .Yr - 2.275 (df : l) and P : 0.132. We do not havc enough evidence to conclude that thete is a relationship. 9.18. (a) The best numerical summary would note that we view target au- dience ("magazine readership") as explanatory, so we sbould com- pute the conditional distribution of model dress for each audience. This table and graph are shown below. (b) N{initab output is shown on the right: X2 : 80.9. df : 2. and P 's very small . We har e r er1 slrorrg evidence that target audience affects motlcl dres.. (c) fhc:.ample i. nor rn Minitab output l{akeYes WakeNo Total BedYes 36 33 69 40 .01 28 . 99 BedNo 33 17 50 28.99 21 .01 Total 69 50 119 Chisq = 0.402 + 0.554 + 4.554 + 4.765 = 2.2Ts df=1,p=6.132 Women 351 424 .

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}