ap statistics section 13.2 b. an observed difference between two sample proportions can reflect a...
TRANSCRIPT
AP Statistics Section 13.2 B
An observed difference between two sample proportions can reflect a difference in the
populations or it may just be due to chance variation in random sampling. Significance tests
help us decide if the effect we see in the samples is really there in the populations. The null hypothesis says that _________________
between the two populations: . The alternative hypothesis says what kind of
difference we expect.
difference no is there:0H 021 pp
In a significance test, we always assume___________________. So, if we assume there is no difference in the populations, then all
the observations in both samples really come from _______________. So instead of
estimating separately, we combine the two samples and use the overall sample
proportion to estimate the single population parameter p.
trueis hypothesis null the
population same the
21 p and p
This is called the combined sample proportion. It is
21
21
combined samplesboth in sindividual of #
combined samplesboth in successes of #ˆ
nn
xxpc
Using in place of both in the expression for the standard error
SE of gives
cp̂
21 p̂ and p̂
21 p and p
21
) )ˆ1(ˆˆ1(ˆ
n
pp
n
ppcccc )
11)(ˆ1(ˆ
21 nnpp cc
21
21
11)ˆ1(ˆ
ˆˆ
nnpp
pp
cc
10 all )ˆ1(,ˆ),ˆ1(,ˆ 2211 cccc pnpnpnpn
Example 13.12: The movie A Civil Action tells the following story. A town well that supplied water to East Woburn,
Massachusetts residents was contaminated by industrial chemicals. During the period that residents drank water from this well, a sample of 414 births showed 16 birth defects. On the west side of Woburn, a sample of 228
babies born during the same time period revealed 3 birth defects. The plaintiffs suing the companies responsible for the contamination claimed that these data show that the
rate of birth defects was significantly higher in East Woburn, where the contaminated well water was in use. How strong is the evidence supporting this claim? What
should the judge for this case conclude?
039.414
16ˆ Ep 013.
228
3ˆ Wp 030.
642
19ˆ Cp
Hypothesis:
Conditions: SRS:
Normality:
Independence:
ed.contaminat was well the time theduringburn in West Wo
born babies and East Wournin born babies areinterest of spopulationMy
0:H 0: a0 WEWE ppppH
burnin West Wo defectsbirth with babies of proportionp
nEast Woburin defectsbirth with babies of proportion
W Ep
.population the togeneralizenot willresults
not If SRSs. weresamples assume not toreason No
Normal approx. ison distributi assume tosafe so 5, All
221.16228(.97) 6.84228(.03) 58.401414(.97) 42.12)03(.414
sample. ingcorrespond the times10at bemust population
eacht replacemen without sampling are weSince
Calculations:
Interpretation:
85.1
2281
4141
)97)(.03(.
013.039.
z
85.1
032. valueP
.026. of difference a with sproportion sample twogetting of chance
3.2% a is therern, West Wobuandn East Woburin defectsbirth with
born babies of sproportion in the difference no is thereAssuming
n.East Woburin greater wasdefectsbirth born with babies
of proportion that theevidence strong moderately provides This