This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: Introduction to hypothesis tests – Examples (with solutions) 1. A grocery store had an average checkout time of 3 minutes. The management wished to improve this and installed a new checkout system. To test the new performance, they measured the checkout times x 1 ,...,x 942 of a sample of 942 customers who checked out at various times over the course of a week. The observed sample mean checkout time was ¯ x = 2 . 9 minutes and the observed sample standard deviation was s = 1 . 2 minutes. The management would like to know if these data provide statistical evidence at the α = 0 . 05 significance level that μ , the mean of the distribution of checkout time, is less than 3 minutes. (a) State the null and alternative hypotheses. Solution: H : μ = 3 H a : μ < 3 (b) What assumptions must be made about the observations x 1 ,...,x 942 to conduct the hypothesis test. Solution: We must assume that the measurements x 1 ,...,x 942 are a realization of a random sample from N ( μ,σ ); however, since the sample size n is very large, the assumption that this distribution is Normal could be relaxed, which would make this test approximate. (c) What is the rejection region for this test. Solution: This is a leftsided test with α = 0 . 05; we reject H if the test statistic realization t < t 1 α,n 1 = t . 95 , 941 = qt (0 . 95 , 941) = 1 . 646475. (i.e. reject H if t < 1 . 646475). (d) Compute the test statistic realization and pvalue. t = ¯ x μ s/ √ n = 2 . 9 3 . 1 . 2 / √ 942 = 2 . 5577 p value = P ( T ≤ t ) = P ( T ≤  2 . 5577) = pt ( 2 . 5577 , 941) = 0 . 00534621 1 (e) State the conclusion to this hypothesis test. What type of error could we be(e) State the conclusion to this hypothesis test....
View
Full Document
 Spring '08
 Staff
 Statistics, Normal Distribution, Standard Deviation, Null hypothesis, Statistical hypothesis testing

Click to edit the document details