Table 6.
Garshick et al. [3]: Linear regression with fixed effects for log RR with weights proportional to the inverse of the respective variance
| log RR | Coef. | Std. Err. | t | P | 95 % CI | |
|---|---|---|---|---|---|---|
| Dose | 0.00061 | 0.000091 | 6.6 | 0.095 (<0.001) | −0.00055 (0.00042 | 0.00177 0.00078) |
| Constant | 0.244 | 0.013 | 18.6 | 0.034 | 0.078 | 0.411 |
| Garshick (modified) | ||||||
| Dose | 0.00005 | 0.00007 | 0.75 | 0.59 (0.45) | −0.00077 (−0.00008 | 0.00087 0.00017) |
| Constant | 0.159 | 0.009 | 16.87 | 0.038 | 0.039 | 0.279 |
Coefficient (Coef.) of the cumulative exposure (Dose) to DEE in μg/m3-years and absolute term (Constant) with standard deviation (Std.Err.); t-test statistic for the coefficient with the corresponding P-value and a 95 % confidence interval for the coefficient, 95 % CI. The figures in parentheses are the results when using the standard normal distribution. Garshick et al. [3] as used by Vermeulen et al. [1], and Garshick et al. [3] (modified) were evaluated