Power calculation for a joint analysis of a two-stage case control design for SNP data

Power calculation for a joint analysis of a two-stage case control design for SNP data.

References

Skol AD, Scott LJ, Abecasis GR, Boehnke M: Joint analysis is more efficient than replication-based analysis for two-stage genome-wide association studies. Nat Genet 38: 209-213, 2006.

See also

http://www.sph.umich.edu/csg/abecasis/CaTS/

Author

Anders Albrechtsen <albrecht@binf.ku.dk>

Examples

# calculate the power under a multiplicative model using a
# two stage design and assuming a relative risk of 1.5
cats(
  freq = 0.2,
  ncases = 500, ncases2 = 500,
  ncontrols = 1000, ncontrols2 = 1000,
  risk = 1.5, multiplicative = 1
)
#> Expected Power is;
#> 
#>      
#> 
#>                    For a one-stage study = 0.94
#>       For first stage in two-stage study = 0.972
#> For second stage in replication analysis = 0.784
#>     For second stage in a joint analysis = 0.929
#>                                       pi = 0.5
#>