Simulation Model |
κ |
Estimate |
Bias |
MCSE |
Mean of SEs |
MSE |
CP (%) |
Increase+Stable |
1 |
 |
-0.122 |
0.018 |
0.018 |
0.015 |
94.4 |
|
 |
-0.010 |
0.022 |
0.021 |
0.001 |
94.5 |
|
 |
-0.014 |
0.021 |
0.021 |
0.001 |
94.8 |
Increase+Decrease |
1 |
 |
-0.071 |
0.009 |
0.009 |
0.005 |
94.9 |
|
 |
-0.088 |
0.007 |
0.007 |
0.008 |
94.6 |
|
 |
-0.068 |
0.009 |
0.009 |
0.005 |
95.4 |
Decrease+Stable |
1 |
 |
0.049 |
0.079 |
0.079 |
0.009 |
94.8 |
|
 |
-0.026 |
0.064 |
0.063 |
0.005 |
94.4 |
|
 |
-0.009 |
0.065 |
0.064 |
0.004 |
94.5 |
|
Bias and MSE are calculated based on the overall relative rates defined by ζ3, and 95% Coverage probabilities are calculated as the rejection rate for testing the null hypothesis with regard to their perspective definitions of overall relative rates.
Abbreviations: NB=Negative binomial; PWNB=Piecewise negative binomial; MCSE=Monte Carlo standard error; SE=Stand error; MSE=Means square error; CP =95% CI coverage probability; κ=Overdispersion parameter |
Table 4: Comparison of different estimates of the overall relative rate through bias, MCSE, mean of SEs, and MSE of relative rate and 95% CI coverage probability (CP) based on 5,000 Monte Carlo simulations (Non-Constant Relative Rate). |