STAT 205 Lecture Notes - Lecture 19: Null Hypothesis, Statistical Parameter, Statistical Hypothesis Testing
Document Summary
Hypothesis testing: inference about how the value of a parameter relates to a specific numerical value. Statistical hypothesis: a statement about the numerical value of a population parameter. Null hypothesis (h0): statement about the specific values of population parameters. It generally represents the status quo, which we adopt until proven false. Generally represents what will only be adopted with sufficient evidence that it"s the truth. Note: h0 & ha should always be complementary (have no overlap) Making a decision about if something"s an outlier: you need a definition of an outlier, compare your sample statistic to ______________ = maximum likelihood you allow yourself to make a type i error. = p(type i error) = p(reject h0|h0 is true) P-value is probability of observing a sample mean that is equal or more extreme than the observed. Decision about whether to reject h0: choose the which is tolerable to the situation, if p-value reject h0. If p-value < do not reject h0.