Paired Bootstrap
A statistical resampling method used to estimate confidence intervals and significance for differences in model performance.
Timeline (last 90 days)
Under the paired-bootstrap 95% confidence interval, the lower bounds are 5.0 and 3.1 percentage points respectively, both positive, indicating the improvements are statistically significant.
The paired confidence intervals lie entirely below zero, indicating that at the 5% significance level, the target model's WER is significantly lower than that of the compared models.
All Facts (2)
Under the paired-bootstrap 95% confidence interval, the lower bounds are 5.0 and 3.1 percentage points respectively, both positive, indicating the improvements are statistically significant.
50%UnverifiedThe paired confidence intervals lie entirely below zero, indicating that at the 5% significance level, the target model's WER is significantly lower than that of the compared models.
50%