Comparison of means across sub-groups
| CAR | Mean difference (%) | Welch t-test | Wilcoxon test | MDE (%) |
|---|---|---|---|---|
| Panel A: King IV | ||||
| 21-day | 3.105 | −0.2216 | 136 | 42.754 |
| 5-day | 2.6502 | −0.6556 | 150 | 11.5653 |
| 3-day | −1.8199 | 0.4903 | 212 | 11.0004 |
| Panel B: Error | ||||
| 21-day | 26.7327 | −0.836 | 89 | 50.659 |
| 5-day | 5.8763 | −1.572 | 73 | 13.918 |
| 3-day | 5.9576 | −1.1289 | 100 | 13.1657 |
| Panel C: Irregularity | ||||
| 21-day | −64.029 | 0.7069 | 66 | 72.9945 |
| 5-day | −4.6111 | 1.4608 | 75 | 21.3387 |
| 3-day | −11.0904 | 0.8996 | 66 | 19.674 |
| Panel D: Policy change | ||||
| 21-day | 1.8619 | −0.2105 | 100 | 62.9183 |
| 5-day | −5.613 | 1.1023 | 107 | 16.9069 |
| 3-day | −1.608 | 0.37 | 89 | 16.2116 |
| Panel E: Repeat | ||||
| 21-day | 19.2064 | 0.9014 | 78 | 68.727 |
| 5-day | −3.063 | −0.5236 | 60 | 18.791 |
| 3-day | 9.6038 | 0.9392 | 65 | 17.304 |
| CAR | Mean difference (%) | Welch | Wilcoxon test | MDE (%) |
|---|---|---|---|---|
| 21-day | 3.105 | −0.2216 | 136 | 42.754 |
| 5-day | 2.6502 | −0.6556 | 150 | 11.5653 |
| 3-day | −1.8199 | 0.4903 | 212 | 11.0004 |
| 21-day | 26.7327 | −0.836 | 89 | 50.659 |
| 5-day | 5.8763 | −1.572 | 73 | 13.918 |
| 3-day | 5.9576 | −1.1289 | 100 | 13.1657 |
| 21-day | −64.029 | 0.7069 | 66 | 72.9945 |
| 5-day | −4.6111 | 1.4608 | 75 | 21.3387 |
| 3-day | −11.0904 | 0.8996 | 66 | 19.674 |
| 21-day | 1.8619 | −0.2105 | 100 | 62.9183 |
| 5-day | −5.613 | 1.1023 | 107 | 16.9069 |
| 3-day | −1.608 | 0.37 | 89 | 16.2116 |
| 21-day | 19.2064 | 0.9014 | 78 | 68.727 |
| 5-day | −3.063 | −0.5236 | 60 | 18.791 |
| 3-day | 9.6038 | 0.9392 | 65 | 17.304 |
Note(s): Table 4 reports the mean differences in 21-, 5- and 3-day CARs across sub-groups defined by the introduction of King IV (Panel A), the reason for the restatement (Panels B–D) and whether the firm has previously issued a restatement (Panel E). For each comparison, the mean difference is computed as the average CAR for observations classified as belonging to that group minus the average CAR for the remaining observations. For each comparison, the table presents results from the Welch t-test and Wilcoxon rank-sum test together with the absolute value of the minimum detectable effect (MDE), which indicates the smallest difference in means that the study has sufficient power to detect at the 5% significance level with 80% power. *, ** and *** indicate significance at the 10%, 5% and 1% levels respectively
Sharing content requires targeting cookies to be enabled. Please update your cookie preferences to use this feature.