Table A2.
Model comparison (see Section 3.4).
| Null model | Initial model | Final model | |
|---|---|---|---|
| Intercept | 0.00417 (0.00062)*** | 0.00520 (0.00434) | 0.00863 (0.00224)*** |
| SQ-R | −0.00007 (0.00003)* | −0.00007 (0.00003)* | |
| EQ | −0.00001 (0.00007) | ||
| IRI-PT | 0.00026 (0.00023) | ||
| AQ-Comm | 0.00006 (0.00035) | ||
| AIC | 337.41 | 336.43 | 332.64 |
| BIC | 341.31 | 348.13 | 338.49 |
| Log Likelihood | −166.70 | −162.21 | −163.32 |
| Num. obs. | 52 | 52 | 52 |
Estimates and standard errors (in brackets).
***
p < 0.001,
**p < 0.01,
*
p < 0.05.
An inverse Gaussian distribution was used as family, negative estimates should be read as positive estimates, and positive estimates as negative ones. Table realized using the R package texreg (Leifeld, 2013).