Page 23 - (function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){ (i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new Date();a=s.createElement(o), m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m) })(window,document,'script','//www.google-analytics.com/analytics.js','ga'); ga('create', 'UA-38829602-2', 'my-thesis.nl'); ga('send', 'pageview');

stratification factors and main covariates. Secondly, an interaction term evaluating a possible effect modification of the treatment effect by the major covariates (see table 5: covariates for sub analysis) is pre-specified as being part of proper statistical modelling of the primary treatment effect. In the presence of severe interaction, the treatment effect will be presented as a function of the effect modifiers. In addition, an explorative subgroup analysis is conducted to investigate whether treatment effect varies over specific subgroups of patients (table 6: subgroups). Data will be stored via the internet-based secure data management system ProMISe of the department of Medical Statistics and Bioinformatics. The analyses will be carried out using appropriate statistical software (e.g. SPSS, version 17).
Figure 1. Sample Size
Felix: Design and protocol
Sample size per group vs Difference by Power P2=0.64 A=0.05 N2=Sample size per group 2-Sided L.R Test
200
180
160
140
120
100
80
60
0.150 0.161
Difference
Power
0.90 0.80
0.172 0.183
0.194 0.205
N1: number of patients needed in the IPD group, P1: the chosen success rate of the IPD group; P2: the suc- cess rate of the decompression group (0.64); N2: number of patients needed in the decompression group (equal to N1); A: the alfa is two sided 0.05.
63
4
Sample size per group