Table 2.
Estimates of the linear probability model (LPM) for splenectomy.
| Dependent variable: splenectomy | LPM |
|---|---|
| Age ≥55 years | 0.2717∗ (0.1539) |
| Male | −0.0540 (0.1395) |
| Hypertension | −0.1861 (0.1419) |
| Hemoglobin <10 mg/dl | 0.2795∗∗ (0.1178) |
| Platelets < 50 × 109 | 0.3876∗∗ (0.1493) |
| Spleen rupture | 0.4359∗∗ (0.1579) |
| Hemodynamic instability | 0.4721∗∗∗ (0.1621) |
| Number of cases | 30 |
| R-squared | 0.6752 |
This table reports the estimates of a linear probability model (LMP) for the binary variable splenectomy. The R-squared value of 0.6752 indicates that 67.52% of the variance in the dependent variable (splenectomy) is explained by the regression model. It also has the simple interpretation that it equals the difference between the average predicted probability in the two groups. Because of the well-known heteroskedasticity in the LPM, heteroskedasticity-robust standard errors are reported in parentheses. ∗∗∗p value <0.01, ∗∗p value <0.05, and ∗p value <0.1.