Table 1.
CIC data: Method comparison for estimating the Δ Δ C q-value
| Estimate | se | t-value | df | p-value | LCL | UCL | |
|---|---|---|---|---|---|---|---|
| MGST1 vs GAPDH | |||||||
| EC | –8.62 | 1.62 | –5.31 | 21 | 2.92·10−5 | –12 | –5.24 |
| EC&VA1 | –8.62 | 1.66 | –5.18 | 21 | 3.89·10−5 | –12.1 | –5.16 |
| EC&VA2 | –8.62 | 1.67 | –5.17 | 21 | 4.04·10−5 | –12.1 | –5.15 |
| Bootstrap | –8.66 | 2.06 | 1.00·10−3 | –12.5 | –4.41 | ||
| MGST1 vs ACTB | |||||||
| EC | –8.98 | 1.61 | –5.57 | 21 | 1.57·10−5 | –12.3 | –5.63 |
| EC&VA1 | –8.98 | 1.65 | –5.45 | 21 | 2.08·10−5 | –12.4 | –5.56 |
| EC&VA2 | –8.98 | 1.65 | –5.45 | 21 | 2.10·10−5 | –12.4 | –5.55 |
| Bootstrap | –8.98 | 2.09 | 1.00·10−3 | –12.7 | –4.48 | ||
| MMSET vs GAPDH | |||||||
| EC | 0.679 | 0.585 | 1.16 | 21 | 2.59·10−1 | –0.538 | 1.9 |
| EC&VA1 | 0.679 | 0.587 | 1.16 | 21 | 2.60·10−1 | –0.541 | 1.9 |
| EC&VA2 | 0.679 | 0.589 | 1.15 | 21 | 2.62·10−1 | –0.545 | 1.9 |
| Bootstrap | 0.688 | 0.678 | 3.12·10−1 | –0.656 | 2 | ||
| MMSET vs ACTB | |||||||
| EC | 0.318 | 0.962 | 0.331 | 21 | 7.44·10−1 | –1.68 | 2.32 |
| EC&VA1 | 0.318 | 0.962 | 0.331 | 21 | 7.44·10−1 | –1.68 | 2.32 |
| EC&VA2 | 0.318 | 0.964 | 0.33 | 21 | 7.45·10−1 | –1.69 | 2.32 |
| Bootstrap | 0.342 | 0.987 | 7.05·10−1 | –1.68 | 2.13 |
EC efficiency corrected LMM estimate ignoring the uncertainty of the efficiency estimates. EC&VA1 EC and variance adjusted LMM estimate using the delta method. EC&VA2 EC and variance adjusted LMM estimate using Monte Carlo integration. Bootstrap estimate by the bootstrap described in Section “Inference for ΔΔCq by the bootstrap method” fitting the LMM and using the EC estimate. Bootstrap shows the mean and standard deviation of 2000 bootstrap samples using the EC estimate. The last two columns show the 95 % lower and upper confidence interval limits