STAT 1000Q Lecture Notes - Lecture 19: Null Hypothesis, Medical Test, Test Statistic

• School: UConn
• Department: Statistics
• Course: STAT 1000Q
• Professor: Robert Apruzese

Document Summary

Statistic notes 1000q- lecture #19-chapter 6 wrap up. For a right tailed z-test, the farther right the value of z is, the stronger the evidence is in support of the alternative hypothesis (ha) The smaller the p-value, the stronger the evidence to support the ha. As the z gets bigger, the p-value gets smaller. As the z gets smaller, the p-value gets larger. The p-value is the smallest significance level above which we would reject the h0. If we already conducted a right tailed z-test and z is the value of the test statistic and h0 is true. The test statistic has to be to the right of z. Small p-value leads you to reject the null hypothesis. If you were to run the data 1000 times, the probability that the data would be outside of p-value is 1. A type-1 error occurs when we (incorrectly) reject a true null hypothesis. H0: defendant is innocent vs ha: defendant is guilty.