Exponentially weighted moving average chart using zero-inflated negative binomial distribution
By: Ali Abbas, Sajid Ali, Ismail Shah
Potential Business Impact:
Helps spot problems in data with lots of zeros.
Zero-inflated models are frequently used to deal with data having many zeros. A commonly used model for over-dispersed data containing zeros is known as the zero-inflated Poisson model. However, to account for the heterogeneity of counts that leads to excess variance besides inflation of zeros in the data using a more flexible model than the zero-inflated Poisson model, a zero-inflated negative binomial (ZINB) is suggested. In the present study, Shewhart and exponentially weighted moving average (EWMA) control charts are suggested to monitor the ZINB data. The charts are compared using the average run length and standard deviation of run length by using extensive Monte Carlo simulations. Besides a comprehensive simulation study assuming different settings of parameters of ZINB, a real data set is used to show the practicality of the proposed charts. The results indicate that the EWMA chart is better than the Shewhart chart.
Similar Papers
Flexible model for varying levels of zeros and outliers in count data
Methodology
Better counts for tricky data with many zeros.
Overall marginalized models for longitudinal zero-inflated count data
Methodology
Better understand health data with many zeros.
A stochastic method to estimate a zero-inflated two-part mixed model for human microbiome data
Methodology
Tracks tiny gut bugs changing with health.