At the local bakery, loaves of bread are supposed to weigh 1 pound
Download
Report
Transcript At the local bakery, loaves of bread are supposed to weigh 1 pound
Choosing Significance Level
Section 10.3
Starter 10.3.1
At the local bakery, loaves of bread are
supposed to weigh 1 pound, with standard
deviation 0.13 pounds. You believe that
today’s loaves are too heavy. You want to test
this idea at the α = .05 level. You weigh 20
loaves and find a mean weight of 1.05 pounds.
1. State your null and alternative hypotheses.
2. Find the test statistic (z) and the p-value for
your test by two different methods.
3. State your conclusion clearly in a complete
sentence.
Today’s Objectives
• Students should be able to discuss issues
involved with selecting the α level of a test
• Students should be able to state
shortcomings of P-level as sole criterion
– How do outliers affect P?
– Why might a confidence interval be more
useful than a hypothesis test?
California Standard 18.0
Students determine the P- value for a statistic for a
simple random sample from a normal distribution.
Choose an appropriate level of
significance (alpha)
• How will the conclusion be used?
• How plausible is Ho
• What are the consequences of rejecting Ho?
• Assume SATM scores are N(475,100).
100 students take a prep course that
claims to improve scores.
• State the null and alternative hypotheses.
• If the students mean score is 491.4, is the
result significant at the 5% level?
– Use the calculator Z-Test screen.
• If the mean is 491.5, is the result
significant at the 5% level?
• Conclusion: There is nothing “magic”
about 5%; don’t act as if it were!
There is more to statistical
significance than P-value!
• Plot your data
– Look for outliers
– Is the effect you seek visible in the data?
• Use a confidence interval
– Estimates the size of an effect, not just
presence or absence of the effect
Today’s Objectives
• Students should be able to discuss issues
involved with selecting the α level of a test
• Students should be able to state
shortcomings of P-level as sole criterion
– How do outliers affect P?
– Why might a confidence interval be more
useful than a hypothesis test?
California Standard 18.0
Students determine the P- value for a statistic for a
simple random sample from a normal distribution.
Homework
• Read pages 560-566
• Do problems 61-65