AtlasSession 2L6: Hypothesis Testing and Statistical Testsp.52–54
One-sample t-test
- 4 earlier topics
- What is a hypothesis
- Test, null and alternate hypotheses
- Alpha error
- Tests, p-values, significance
- One-sample t-test
Fig. 1
Ultimate tensile strength of 15 decellularised porcine pericardium patches against the certified 20 MPa (MPa)
Fig. 1. One hump: the results you would get if the patches really average 20 MPa. The batch average, 18.00 MPa, is marked. Results as far out, or further turn up about 2 in 100 times when nothing is going on.
- This far out, if nothing is going on
- about 2 in 100
- Rarer than 5 in 100?
- yes
Two-Curve Test Visualiser · First look
Level 1 · First look · Lecture 6 · p.52–54
Judge whether a batch's average is out of line with a known standard, allowing for luck.
Compare one sample's mean with a known population mean: compute T, df and the two-sided p-value as Excel does.
Against a known standard (the step you are on)
15 loaves average 780 g against an 800 g label; short-changed, or luck?
Fifteen loaves average 780 g against an 800 g label: short-changed, or just luck? To judge, compare the gap with how much an average of 15 loaves wobbles from batch to batch.