What does standard error (SE) represent?
Most common error bar on a mean; shows precision of the mean.
If SE bars overlap, what does it mean?
Means likely do not differ significantly (p<0.05).
If SE bars don’t overlap, what does it mean?
May or may not differ; need a proper statistical test.
What does standard deviation (SD) show?
Shows variability of the data, not significance.
What does a 95% confidence interval (CI) indicate?
Range where the true mean likely lies; no overlap suggests significance.
What is the null hypothesis (H₀)?
States there is no difference or effect.
What is the alternative hypothesis (H₁)?
States there is a difference or effect.
What is a p-value?
Probability of getting these results if H₀ is true.
What does p < 0.05 mean?
Less than 5% chance results occurred randomly (statistically significant).
What is the one-sample t-test formula?
t = (sample mean − hypothesised mean) / SEM.
What are assumptions for a t-test?
Independent data, normal distribution, large enough sample size (>50).
What’s the difference between one-tailed and two-tailed tests?
One-tailed: specific direction; Two-tailed: any difference.
What is a Type I error (α)?
Rejecting H₀ when it’s true (false positive).
What is a Type II error (β)?
Failing to reject H₀ when it’s false (false negative).
What is statistical power?
Probability of detecting a true effect (1−β); should be ≥0.8.
