Hypotheses Testing
Example 1 We have tossed a coin 50 times and we got k = 19 heads Should we accept/reject the hypothesis that p = 0.5 (the coin is fair)
Null versus Alternative Null hypothesis (H 0 ): p = 0.5 Alternative hypothesis (H 1 ): p 0.5
k p(k) 95% EXPERIMENT
Experiment P[ k 32 ] < 0.05 If k 32 then an event happened with probability < 0.5 Improbable enough to REJECT the hypothesis H 0
Test construction 1832 accept reject
k Cpdf(k)
Conclusion No premise to reject the hypothesis
Example 2 We have tossed a coin 50 times and we got k = 10 heads Should we accept/reject the hypothesis that p = 0.5 (the coin is fair)
k cpdf(k)
Significance level P[ k 10 or k 40 ] We REJECT the hypothesis H 0 at significance level p=
Remark In STATISTICS To prove something = REJECT the hypothesis that converse is true
Example 3 We know that on average mouse tail is 5 cm long. We have a group of 10 mice, and give to each of them a dose of vitamin X everyday, from the birth, for the period of 6 months.
We want to prove that vitamin X makes mouse tail longer We measure tail lengths of our group and we get sample = 5.5, 5.6, 4.3, 5.1, 5.2, 6.1, 5.0, 5.2, 5.8, 4.1 Hypothesis H 0 - sample = sample from normal distribution with = 5cm Alternative H 1 - sample = sample from normal distribution with > 5cm
Construction of the test t t 0.95 reject Cannot reject
We do not population variance, and/or we suspect that vitamin treatment may change the variance – so we use t distribution
2 test (K. Pearson, 1900) To test the hypothesis that a given data actually come from a population with the proposed distribution
Data Are these data sampled from population with exponential pdf ?
Construction of the 2 test p1p1 p2p2 p3p3 p4p4
Construction of the test 22 reject Cannot reject
How about Are these data sampled from population with exponential pdf ? 1.Estimate a 2.Use 2 test 3.Remember d.f. = K-2
Power and significance of the test Actual situation decisionprobability H 0 true H 0 false accept Reject = error t. I reject Accept = error t. II 1-a a = significance level b 1-b = power of the test