Skip to main content
Fig. 9 | BMC Medical Research Methodology

Fig. 9

From: A comparison of residual diagnosis tools for diagnosing regression models for count data

Fig. 9

Comparison of the type I errors and powers of the SW tests for the RQR, MQR, deviance residual and Pearson residual. Response variable is simulated from the true model at varying sample size, n=20,50,100,200,400,600,800,1000 and percentage of excessive zeroes of p=10% (), 30% () and 50% (). True model: ZIP model with mean exp(β0+β1x). Wrong model: Poisson model with mean exp(β0+β1x)

Back to article page