In the year 2045, technology was fractured. Each megacity operated on different frequencies, different kernels, and different souls. To travel from the Neo-Tokyo sectors to the London Spires meant carrying a dozen converters just to keep your implants from crashing.
| Test | When to Use | Universal Best Practice | |------|-------------|--------------------------| | | Comparing two classifiers on same test set (paired nominal). | Report exact p-value, not just “significant”. | | Paired t-test / Wilcoxon | Comparing means of cross-validation folds (e.g., RMSE). | Use 5×2CV paired t-test for higher power. | | Friedman + Nemenyi post-hoc | Comparing >3 models across multiple datasets. | Visualize with critical difference diagram. | st mtk universal best