Summary of application of Clauset’s method using the poweRlaw package on the full corpora for each language.
| Language . | Number of sub-samples receiving p-value > 0.05 . | Number of sub-samples receiving p-value =< 0.05 . | Measures of alpha across sub-samples (mean (SD)) . |
|---|---|---|---|
| British English | 37 | 32 | 1.769 (0.064) |
| Dutch | 3 | 8 | 1.703 (0.039) |
| French | 15 | 4 | 1.748 (0.052) |
| German | 6 | 15 | 1.69 (0.067) |
| Hebrew | 3 | 0 | 1.937 (0.04) |
| Japanese | 7 | 7 | 1.769 (0.084) |
| Portuguese | 2 | 1 | 1.717 (0.059) |
| Spanish | 5 | 1 | 1.797 (0.075) |
| Swedish | 3 | 0 | 1.793 (0.012) |
| Language . | Number of sub-samples receiving p-value > 0.05 . | Number of sub-samples receiving p-value =< 0.05 . | Measures of alpha across sub-samples (mean (SD)) . |
|---|---|---|---|
| British English | 37 | 32 | 1.769 (0.064) |
| Dutch | 3 | 8 | 1.703 (0.039) |
| French | 15 | 4 | 1.748 (0.052) |
| German | 6 | 15 | 1.69 (0.067) |
| Hebrew | 3 | 0 | 1.937 (0.04) |
| Japanese | 7 | 7 | 1.769 (0.084) |
| Portuguese | 2 | 1 | 1.717 (0.059) |
| Spanish | 5 | 1 | 1.797 (0.075) |
| Swedish | 3 | 0 | 1.793 (0.012) |