This preview shows pages 1–7. Sign up to view the full content.
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 DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: Stat231 William Marshall Stat231 William Marshall July 6, 2010 Stat231 William Marshall Week 10 Goals: CLT based hypothesis test Relative likelihood based hypothesis test Summary Stat231 William Marshall CLT based Steps are the same for CLT based hypothesis tests Discrepancy measure D = ¯ Y E ( Y ) SE ( ¯ Y ) Sampling distribution  For large values of n ¯ Y E ( Y ) SE ( ¯ Y ) ∼ G (0 , 1) Calculation and interpretation of pvalues is the same p val = P ( D > d obs ) Stat231 William Marshall Example 18 A standard treatment for a plant disease has a success rate of 75%. To test a new treatment, 100 plants with the new treatment are exposed to the virus that causes the disease and 82 survive. Is there any evidence that the new treatment has a different survival rate than the standard? Model: Y ∼ Binom (100 ,π ) Data: y=82 Stat231 William Marshall Ex18 continued H : π = 0 . 75 ˆ π = y n = 0 . 82 Discrepancy measure  ˜ π π  SE (˜ π ) The pvalue P ( D ≥ d obs ) There is weak evidence against the hypothesis The new treatment may have a different survival rate than the standard treatment Stat231 William Marshall Example 19 Under severe conditions, the effective life (in hours) of a...
View
Full
Document
This note was uploaded on 11/21/2011 for the course MATH STAT 231 taught by Professor Marsh during the Spring '10 term at Waterloo.
 Spring '10
 Marsh

Click to edit the document details