Table 1

Results of different methods of statistical analysis

Invariant feature (AD)
 Invariant feature (MBEV)
 Invariant set
 Global scaling
(a) Mean
 3.55
 2.45
 1.59
 3.37
          Median
 2.09
 1.46
 1.30
 2.12
          Max
 429.01
 667.16
 71.63
 848.28
(b) Mean FC



          F
 15.05
 9.69
 3.06
 10.28
          KW
 18.48
 12.24
 3.35
 12.21
          SAM
 21.91
 13.75
 3.63
 13.08
     Median FC



          F
 5.77
 2.97
 2.08
 3.89
          KW
 7.89
 3.63
 2.25
 4.77
          SAM
 9.20
 4.11
 2.41
 4.92
(c) Mean
 428.71
 750.20
 324.17
 384.47
          Median
 85.52
 259.83
 122.04
 102.37
          Max
 25141.89
 24616.80
 28650.70
 24794.22
(d) Mean difference



          F
 2248.04
 3346.51
 1427.59
 1784.93
          KW
 2545.81
 3881.37
 1655.16
 2044.61
          SAM
 3157.21
 4451.51
 1827.97
 2216.36
     Median difference



          F
 1116.52
 1954.57
 664.49
 954.38
          KW
 1328.38
 2444.28
 815.85
 1138.39
          SAM
 1865.47
 2927.57
 952.92
 1248.04

(a) Mean, median, and maximum fold changes (FC) of all genes on the two array types normalized with different methods. AD, average difference; MBEV, model-based expression values. The averages are given across all genes of the ratio between the maximum and the minimum value across the five different conditions, calculated after averaging replicate arrays. (b) Mean and median fold changes (FC) of genes detected as differentially expressed with 99% confidence by all possible combinations of normalization and statistical analysis algorithms, calculated as in (a). F, F-statistics; KW, Kruskal-Wallis; significance analysis of microarrays (SAM), (c) Mean, median, and maximum signal differences of all genes on the two array types normalized with different methods, calculated by analogy with the ratios in (a). (d) Mean and median signal differences of genes detected as differentially expressed with 99% confidence by all possible combinations of normalization and statistical analysis algorithms, calculated as in (c).

Hoffmann et al. Genome Biology 2002 3:research0033.1   doi:10.1186/gb-2002-3-7-research0033