BS161: Lecture 3 - Comparing 2 Samples
Studied by 0 people
Call Kai
Learn
Practice Test
Spaced Repetition
Match
Flashcards
Knowt Play1/20
There's no tags or description
Looks like no tags are added yet.
Name | Mastery | Learn | Test | Matching | Spaced |
|---|
No study sessions yet.
21 Terms
How can we ensure the means of a sample are normally distributed?
Repeat sampling many times
How should the means and SDs of 2 samples from the same population compare?
Similar, not identical due to sampling noise
What does the sample statistic t measure?
Deviation from 0 of the means of 2 samples
What should the average of the sample statistic t be?
~0, values may differ due to sampling noise
What does a large t value mean?
Less likely both samples come from sample from population
What is the benefit of using appropriate t distribution?
We can compute probability of wrongly rejecting Ho
When is a Student T Test used?
If 2 samples come from same population
What is the Null Hypothesis of a Student T-Test?
Mean population estimations from both samples are equal
How do you calculate the degrees of freedom in a Student T Test?
n1 + n2 - 2
What is the Alternative Hypothesis in a 2 tailed test?
Means are different
What is the Alternative Hypothesis in a 1 tailed test?
1 mean is greater
How do 1 tail tests compare to 2 tailed?
1 tailed are more powerful
How do the p values of 1 tail tests compare to 2 tailed?
1 tail p value = 2 tail p value / 2
What are the assumptions of T Tests? (3)
Independence of sample measurements, equal variances, normality
What is Statistical Independence?
Occurrence of 1 event has no effect on probability of another event occurring
What is the relationship between T Tests and Variance?
T Test in most programs is robust to unequal variances
What would happen to T Tests if sample’s populations aren’t normally distributed?
Won’t work
What are the 2 possibilities of T tests if not Normal Distribution?
Data transformation, non-parametric test
What is the Mann-Whitney U Test based on?
Ranks rather than measurements
When does the Mann-Whitney U Test work well?
Samples aren’t normally distributed
How does the Mann Whitney U Test compare to T test?
Power
p Value
When’s it used?
Less powerful, higher p value, only used when T Test isn’t available