Translate research question into parameter of linear model.
- Why so many hypothesis specified in terms of the mean?
Distribution of the mean?
- Unbiased
- SE
- SD vs SE in function of sample size
- Normal data
- Mean vs median
Hypothesis testing
- Reseach question
- Modelling data
- Translation research question to model parameters
- H0 vs H1
- Test statistic
- One sided vs two sided
- P-value
- Errors
- Accepting vs rejecting H_0
- Importance of Assumptions?
Different tests
- One sample T-test
- Paired T-test
- Two sample T-test
What if assumptions are not met?
What affects the power of a test?
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