Determinants of number of people affected (zero-inflated negative binomial model).
| Variable | Number of people affected | |||
|---|---|---|---|---|
| NB model | Logit model | NB model | Logit model | |
| (1) | (2) | (3) | (4) | |
| Development indicators | ||||
| HDI | 2.70 (2.85) | 2.26 (4.69) | – | – |
 | −3.10 (3.49) | −0.69 (5.45) | – | – |
| Ln(PCNSDPC) | – | – | 11.11 (13.55) | 1.03 (25.09) |
 | – | – | −5.91 (6.78) | −0.34 (12.55) |
| Hazard and risk | ||||
| ARAIN | 0.001*** (0.0002) | – | 0.001*** | |
| (0.0002) | - | |||
| AAREA | 9.08*** (1.19) | – | 9.32*** | |
| (1.27) | - | |||
| Disaster-specific adaptation measures | ||||
| NFY | 0.004 (0.062) | −0.66*** (0.09) | 0.006 (0.07) | −0.41*** (0.11) |
| DRR | 0.05 (0.24) | 0.79 (0.41) | −0.06 (0.30) | 0.45 (0.46) |
| Constant | 13.12*** (0.63) | 1.34 (1.12) | 19.98*** (3.33) | −1.05 (4.50) |
| State effects | Y | Y | Y | Y |
| Time effects | Y | Y | Y | Y |
 | 0.2*** (0.05) | 0.204*** (0.050) | ||
 | 1.22 (0.06) | 1.23 (0.06) | ||
| No. of samples | 1,239 | 1,003 | ||
| No. of non-zero samples | 748 | 633 | ||
| No. of states | 21 | 17 | ||
Wald  | 2054.85*** | 890.98*** | ||
| Log pseudo likelihood | − 11724.43 | − 10,102.11 | ||
| Vuong test | 26.61*** | 26.70*** | ||
| Variable | Number of people affected | |||
|---|---|---|---|---|
| NB model | Logit model | NB model | Logit model | |
| (1) | (2) | (3) | (4) | |
| Development indicators | ||||
| HDI | 2.70 (2.85) | 2.26 (4.69) | – | – |
| | −3.10 (3.49) | −0.69 (5.45) | – | – |
| Ln(PCNSDPC) | – | – | 11.11 (13.55) | 1.03 (25.09) |
| | – | – | −5.91 (6.78) | −0.34 (12.55) |
| Hazard and risk | ||||
| ARAIN | 0.001*** (0.0002) | – | 0.001*** | |
| (0.0002) | - | |||
| AAREA | 9.08*** (1.19) | – | 9.32*** | |
| (1.27) | - | |||
| Disaster-specific adaptation measures | ||||
| NFY | 0.004 (0.062) | −0.66*** (0.09) | 0.006 (0.07) | −0.41*** (0.11) |
| DRR | 0.05 (0.24) | 0.79 (0.41) | −0.06 (0.30) | 0.45 (0.46) |
| Constant | 13.12*** (0.63) | 1.34 (1.12) | 19.98*** (3.33) | −1.05 (4.50) |
| State effects | Y | Y | Y | Y |
| Time effects | Y | Y | Y | Y |
| | 0.2*** (0.05) | 0.204*** (0.050) | ||
| | 1.22 (0.06) | 1.23 (0.06) | ||
| No. of samples | 1,239 | 1,003 | ||
| No. of non-zero samples | 748 | 633 | ||
| No. of states | 21 | 17 | ||
| Wald | 2054.85*** | 890.98*** | ||
| Log pseudo likelihood | − 11724.43 | − 10,102.11 | ||
| Vuong test | 26.61*** | 26.70*** | ||
Note: This model has two equations. Columns 2 and 4 report the logit model estimates of the probability that nobody in a given state in a given year reports loss and damage from floods. Columns 1 and 3 report results from the negative binomial model. Robust standard errors are presented in parentheses. In the case of Vuong test, z-value is reported. Likelihood ratio (LR) test is significant in all the models, indicating that zero-inflated negative binomial is better than zero-inflated Poisson regression. Absence of serial correlation as p-value of Wooldridge test for autocorrelation is insignificant. *** p < 0.01, ** p < 0.05, * p < 0.1.
Source: Authors' computation.