termsTerm

Statistical significance (P values, alpha, multiplicity)

aka statistically significant, statistical significance, not statistically significant, did not reach statistical significance, P value, p-value, P<0.05, P = 0.05, one-sided, two-sided, alpha spending, alpha allocation, type I error, multiplicity, multiple comparisons, hierarchical testing, gatekeeping, Bonferroni, powered, underpowered, sample size, statistical power, 80% power, 90% power, numerically, numerical improvement, trend toward, trend towards, clinically meaningful, clinical significance

A result is 'statistically significant' when it would be unlikely (usually under 5%) to arise by chance if the treatment did nothing. It is a threshold, not a measure of importance: a tiny benefit can be significant in a huge trial and a large one non-significant in a small one.

Trials are sized ('powered') to detect a pre-specified effect with 80-90% probability at a 5% two-sided alpha; testing several endpoints or several interim looks would inflate false positives unless alpha is split (allocated) or spent sequentially, so hierarchical testing means a secondary endpoint cannot be claimed if a higher one failed. 'Numerically better', 'trend' and 'nominal P' are phrases for results that did not meet the pre-set bar. Clinical meaningfulness is separate: ASCO and ESMO scales (ESMO-MCBS) grade the size of benefit, and a significant 6-week PFS gain may not matter to patients. Confidence intervals convey both size and uncertainty and are preferred to bare P values.

Connected

8top

Pages like this

not linked directly; found by shared links

fronts

Drug Discovery Platforms

terms

Futility analysis (stopped for futility)Hazard ratio (HR)Interim analysis, readout and data cut-off Non-inferiority trial Pre-specified vs post-hoc analysis Primary, secondary and co-primary endpoints Subgroup analysis (forest plots)