Instead of testing whether smaller trials yielded different treatment effect estimates than did larger trials, Ioannidis and Trikalinos proposed testing for an excess number of trials with statistically significant results in a meta-analysis [ 14].
The reviews covered in excess of 2000 trials.
While the reviews have covered in excess of 2,000 trials, the management of breathlessness remains far from ideal and patients suffer unnecessarily, particularly in the advanced stages of their illness.
The two Swedish studies confirmed the absence of excess of incidence in trials in which the control group was screened at the end of the study period.
The verbal feedback always corresponded to real performance success or failure on the preceding trial (except on the few "trick" trials with equal number of dots on both sides, where a negative "LOST" feedback was given to reduce an excess of correct over incorrect trials).
The test could be useful to document an excess of significant findings in trial networks, providing a signal for potential publication bias or other selective analysis and outcome reporting biases.
The average TC for 27 non-commercial trials was an excess of £431 (range £6393 excess to £6005 saving) and for 26 commercial trials was an average saving of £9294 (range £0 to £71 480).
This effect is impossible to test in any feasibly sized randomized controlled trial (in excess of 100,000 patients would be required for adequate power).
The proposed excess significance test could be useful to provide a statistical signal indicating an excess of significant findings in clinical trial networks.
