Table 4
Testing for Compositional Differences by Treatment Group
| Treatment Definition | Mean Preflood Quantity Index | Mean Postflood Quantity Index | Welch t-Test p-Value |
|---|---|---|---|
 | 5.522 (5.439, 5.606) | 5.570 (5.469, 5.671) | 0.476 |
 | 5.311 (5.262, 5.361) | 5.322 (5.265, 5.380) | 0.781 |
 | 5.296 (5.233, 5.359) | 5.303 (5.230, 5.378) | 0.876 |
 | 5.353 (5.344, 5.362) | 5.343 (5.333, 5.353) | 0.143 |
Note: The first two columns report the mean quantity index for each risk group, before and after the flood; 95% confidence intervals surrounding the means are given in parentheses. The last column reports the p-values from a Welch two-sample t-test comparing the pre- and postflood means. The null hypothesis of the Welch two-sample t-test is that the true difference in means is equal to zero.