Lecture #5 (Hypothesis Testing) Flashcards
What is a null hypothesis? (H0)
There is no pattern or trend - there is no difference - the accused is innocent
What is a alternative hypothesis? (H1)
there is a pattern or trend - there is a difference - the accused is guilty
Are H1 and H0 mutually exclusive?
Yes sir
What percentage of significance is generally accepted?
95%
Which is considered a more significant error? Type I or Type II?
Type I
What is the difference between a one tailed and two tailed test?
A one tailed test measures both the left and right side of the distribution (5%) while the two tailed uses both sides (2.5% & 2.5%).
What is a type I error?
A type I error is when the innocent is proven guilty
What is a type II error?
A type II error is when the guilty is proven innocent
How do you perform the Z-test?
z-calc = Difference between mean of the sample and the expected mean, divided by standard error of the mean
When do you use a Z-test?
When you are making inference between a sample and it’s population. You are seeing if there is a difference between means of a sample and a population
How do you perform a T-test?
tCalc = x̄− μ𝑜
————
𝑠√𝑛−1
When do you use a T-test?
When you are comparing means of a sample to a population but (n<30)
What is the difference between the Z-test and the T-test?
They both compare the mean of a sample to the mean of the population, however the T-test is for when (n<30) and the Z-test is for when (n>30)
You want to compare the mean height of a random group of hockey players to the mean of the Canadian population. You sample 20 hockey players. What distribution should be used? Why?
T-test because (n<30)
How do you find degrees of freedom in a T-test?
n-1
How do you compare the portions of one sample if (n>30)?
Use the Z-test but include the expected proportion as a decimal in the formula
zCalc = x − n𝑃𝑜
——————
√(𝑛𝑃𝑜 (1−𝑃𝑜))
What is the Z-crit value given a two-tailed test with an alpha value of 0.05?
Z-crit = +/- 1.96
When do you use a paired test or related test?
When you are comparing two samples that are normally distributed and come from the same sample with known variances
When do you use the independent test?
When you compare two separate samples with similar or different variances