AtlasSession 2L6: Hypothesis Testing and Statistical Testsp.43–47
Beta error and power
- 5 earlier topics
- Test, null and alternate hypotheses
- Alpha error
- Tests, p-values, significance
- CIs and p-values
- Beta error and power
Fig. 1
Difference in mean compressive modulus, crosslinked minus standard hydrogel (MPa)
Fig. 1. Two overlapping humps: the results you would get if there is no real difference, and if there is a real difference of 0.50 MPa. With 30 hydrogels per group, about 49 in 100 studies would spot the real difference and about 51 in 100 would miss it. Spotting it about 80 in 100 needs 63 hydrogels per group.
- Studies that spot it
- about 49 in 100
- Studies that miss it
- about 51 in 100
- hydrogels per group
- 30
- Needed to spot it about 80 in 100
- 63 hydrogels per group
Two-Curve Test Visualiser · First look
Level 1 · First look · Lecture 6 · p.43–47
See how a real effect can be missed and what makes a study better at spotting it.
Explain beta (type II, false negative) error, compute power = 1 − β, and show how sample size and SD change it.
Missed signals (the step you are on)
Through a foggy window you miss a friend who is really in the crowd.
Through a foggy window you can miss a friend who really is in the crowd. With 30 hydrogels per group, about 51 in 100 repeat studies miss the stiffer gel.