This preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: 16.34 (a) Margin of error decreases. (b) The Pvalue decreases (the evidence against H ± becomes stronger). ( c) The power increases (the test becomes better at distinguishing between the null and alternative hypotheses). Chapter 18 Chapter 19 19.6 (a) A tdistribution with reasonably large df is quite similar to a standard Normal distribution. So, as long as the samples were not too small, we know that the value t=8.37 would have a very small Pvalue. (b) The smaller sample is 61 students, so we use df=60. . 19.12 We have two small samples (each n=4), so t procedures are not reliable unless both distributions are Normal. Chapter 20...
View
Full Document
 Spring '10
 Kushner
 Statistics, Normal Distribution, Type I and type II errors, standard normal distribution, reasonably large df

Click to edit the document details