I run a series of regressions based on a forward stepwise-selection model which selects which variable to add at each step based on which potential newly added variable has the smallest p-value. I add in the few variables which are not statistically significant all at once.
##
## Stepwise Selection Summary
## ---------------------------------------------------------------------------------------------------
## Added/ Adj.
## Step Variable Removed R-Square R-Square C(p) AIC RMSE
## ---------------------------------------------------------------------------------------------------
## 1 `Pre-CovCov` addition 0.505 0.499 52.0620 -8.9381 0.2239
## 2 `Digital registration` addition 0.644 0.635 17.2740 -34.2834 0.1910
## 3 `EAP dummy` addition 0.675 0.663 11.0240 -39.8843 0.1836
## 4 log_deaths addition 0.711 0.696 3.5080 -47.6148 0.1743
## ---------------------------------------------------------------------------------------------------| Dependent variable: | |||||
| Coverage | |||||
| (1) | (2) | (3) | (4) | (5) | |
Pre-CovCov
|
1.147*** | 0.849*** | 0.731*** | 0.673*** | 0.637*** |
| (0.126) | (0.120) | (0.123) | (0.118) | (0.127) | |
| rGDPg2020 | -0.005 | ||||
| (0.004) | |||||
| digIDcov | 0.069 | ||||
| (0.070) | |||||
Digital registration
|
0.262*** | 0.267*** | 0.204*** | 0.195*** | |
| (0.047) | (0.045) | (0.047) | (0.053) | ||
| FSI | 0.006 | ||||
| (0.015) | |||||
EAP dummy
|
0.164*** | 0.279*** | 0.277*** | ||
| (0.060) | (0.068) | (0.073) | |||
| log_deaths | 0.040*** | 0.035** | |||
| (0.013) | (0.014) | ||||
| Constant | 0.131*** | 0.055* | 0.046 | -0.070 | -0.144 |
| (0.032) | (0.030) | (0.029) | (0.047) | (0.155) | |
| Observations | 83 | 83 | 83 | 83 | 82 |
| R2 | 0.505 | 0.644 | 0.675 | 0.711 | 0.717 |
| Adjusted R2 | 0.499 | 0.635 | 0.663 | 0.696 | 0.690 |
| Residual Std. Error | 0.224 (df = 81) | 0.191 (df = 80) | 0.184 (df = 79) | 0.174 (df = 78) | 0.176 (df = 74) |
| F Statistic | 82.746*** (df = 1; 81) | 72.416*** (df = 2; 80) | 54.771*** (df = 3; 79) | 48.029*** (df = 4; 78) | 26.751*** (df = 7; 74) |
| Note: | p<0.1; p<0.05; p<0.01 | ||||
The following regressions include only one of the variables digital ID coverage, digital ID registration, and FSI each.
| Dependent variable: | ||||
| Coverage | ||||
| (1) | (2) | (3) | (4) | |
Pre-CovCov
|
0.739*** | 0.735*** | 0.735*** | 0.637*** |
| (0.128) | (0.136) | (0.136) | (0.127) | |
| rGDPg2020 | -0.004 | -0.004 | -0.004 | -0.005 |
| (0.004) | (0.004) | (0.004) | (0.004) | |
| digIDcov | 0.139** | 0.069 | ||
| (0.065) | (0.070) | |||
Digital registration
|
0.195*** | |||
| (0.053) | ||||
| FSI | -0.019 | -0.019 | 0.006 | |
| (0.014) | (0.014) | (0.015) | ||
EAP dummy
|
0.318*** | 0.287*** | 0.287*** | 0.277*** |
| (0.072) | (0.079) | (0.079) | (0.073) | |
| log_deaths | 0.052*** | 0.052*** | 0.052*** | 0.035** |
| (0.013) | (0.014) | (0.014) | (0.014) | |
| Constant | -0.141** | 0.086 | 0.086 | -0.144 |
| (0.057) | (0.138) | (0.138) | (0.155) | |
| Observations | 83 | 82 | 82 | 82 |
| R2 | 0.667 | 0.653 | 0.653 | 0.717 |
| Adjusted R2 | 0.646 | 0.630 | 0.630 | 0.690 |
| Residual Std. Error | 0.188 (df = 77) | 0.192 (df = 76) | 0.192 (df = 76) | 0.176 (df = 74) |
| F Statistic | 30.898*** (df = 5; 77) | 28.559*** (df = 5; 76) | 28.559*** (df = 5; 76) | 26.751*** (df = 7; 74) |
| Note: | p<0.1; p<0.05; p<0.01 | |||