Statistics Week 4

Statistics Week 4

1. Hypothesis testing

   • 1. Formulate hypothesis
     • 2. Measure data on the variables involved
       • 3. Calculate the conditional probability of having obtained this pattern of data if the null hypothesis were true
         • 4. If this probability is sufficiently small, we assume that the pattern of data is unlikely to have happened by chance so we reject the null hypothesis in favour of the research hypothesis
           • 5. Interpret the decision in step 4 in terms of your hypothesis

2. P-values

   • The conditional probability associated with having obtained your data assuming that the null hypothesis is true
     • Not the same thing as the probability that the null hypothesis is true
   • 5% or 0.05 - if the null is true, if I were to conduct an experiment 20 times, only once would I expect to see results of the extreme values I have observed