| Hand in (All D&V)
Yes, all of these and Day 32's
Hand in all the problems listed on Day 32, + this one adapted from Activstats HW: TRE-396-9: Store Checkout-Scanner Accuracy In a study of store checkout-scanners, 1234 items were checked and 20 of them were found to be overcharges (based on data from "UPC Scanner Pricing Systems: Are They Accurate?" by Goodstein, Journal of Marketing, Vol. 58). Before scanners were used, the overcharge rate was estimated to be about 1% . Based on these results, do scanners appear to give a different rate of overcharges than the old method of keying in the price? (All items had to have individual price tags; scanning is much less labor-intensive.) Do the steps, finding the P-value and stating a conclusion. = = = = = = = = = = "Significance" Ch. 21, p. 404 1 P-value 3, 4 Alpha 5, 6 Significant? |
Read,
to discuss |
Optional |
Continuing with Hypothesis testing (often called Significance testing) Day 32
"Statistically significant" result (p.256): An observed difference is too large for us to believe that it is likely to have occurred naturally (i.e. because of random variation.)
Especially if we must make a decision to Reject Ho
(or retain it)---
Set "benchmark" or "cutoff" level "alpha"
"significance level": (p. 393-4)
If P-value is less
than alpha, we say the test is "significant at level alpha"
(Seeing the result (again) would be rarer than alpha, if the null hypothesis
is true)
Different fields/ questions use different alphas. If rejecting
Ho is startling, or costly, want a smaller alpha.
Usually round numbers: .10 (1 in 10), .05
(1 in 20), .01 (1 in 100),.001 (1 in a thousand) etc.
Smoke detector: P = 0.4% = .004. IS Significant
at .10, .05, .01 levels. NOT significant at .001 level.
Cautions: (p. 394)
P = .0499 "Is significant"
but P = .0501 "is NOT significant" at .05
level. Best to report P-values, whether or not you use an
alpha to base a decision on.
"Statistically significant" difference isn't necessarily either
large or of any importance. (With enough data, you can detect even
small deviations from the null hypothesis.)
| ievers home | Math151-Sp05/Days33.htm | 2:30pm | 4/22/05 |