Skip to main content

Research Repository

Advanced Search

Outputs (16)

Significance testing with incompletely randomised cases cannot possibly work (2018)
Journal Article
Gorard, S. (2018). Significance testing with incompletely randomised cases cannot possibly work. International journal of science and research methodology, 11(2), 42-51

This brief paper illustrates why the use of significance testing cannot possibly work with incompletely randomised cases. The first section reminds readers of the logical argument of “denying the consequence”, and the fallacy of trying to affirm the... Read More about Significance testing with incompletely randomised cases cannot possibly work.

Do we really need Confidence Intervals in the new statistics? (2018)
Journal Article
Gorard, S. (2019). Do we really need Confidence Intervals in the new statistics?. International Journal of Social Research Methodology, 22(3), 281-291. https://doi.org/10.1080/13645579.2018.1525064

This paper compares the use of confidence intervals (CIs) and a sensitivity analysis called the number needed to disturb (NNTD), in the analysis of research findings expressed as ‘effect’ sizes. Using 1,000 simulations of randomised trials with up to... Read More about Do we really need Confidence Intervals in the new statistics?.