Hypthesis Testing Flashcards
(9 cards)
Binomial distribution assumptions
- Fixed number of trials
- Outcomes of the trials are independent
- There are 2 outcomes, success and failure
- The probability of success is constant
When do you reject hypothesis
P<SL
When do you accept hypothesis
P>SL
If observed value falls inside critical region do you accept or reject null hypothesis
Reject H0 (null hypothesis), accepy alternative hypothesis
If observed value doesnt fall inside critical region do you accept or reject null hypothesis
Accept null hypothesis, reject alternative hypothesis
1 mark
Explain what you understand by a hypothesis
A statement concerning a population parameter
2 marks
Explain what you understand by a critical region.
- A critical region is the range values or a test statistic where the test is significant
- That would lead to the rejection of H0 / acceptance of H1
Define hypothesis test
A hypothesis test is a statistical test that is used to determine whether there is enough evidence in a sample of data to infer that a certain condition is true for the entire population
Can extreme events be ruled out in a Normal distribution?
Why can’t we say there’s no chance of a very rare event (e.g., a hurricane in an unlikely place) if the situation is modeled by a Normal distribution?
Because the tails of a Normal distribution are infinite, meaning there’s always a non-zero probability of extreme events, no matter how unlikely