Skip to main content
. 2021 Oct 15;11:20524. doi: 10.1038/s41598-021-99950-1

Table 6.

Evaluation for unmeasured confounding between SLNB groups by E-value analysis.

Analysis 1-Year overall survival 3-Year overall survival
Crude analysis—E value 3.60 2.24
Multivariable analysis—E value 2.86 1.85
Propensity-score analyses
With inverse probability weighting—E value 3.09 1.58
With matching—E value 3.16 1.88

The larger the E-value, the lower the probability that an unmeasured confounder was to explain the entirety of the treatment effect.