On some combined control charting schemes for monitoring zero-inflated Poisson processes with applications in public health surveillance

• Main Author: Leong, Robert Neil F.
• Format: text
• Language: English
• Published: Animo Repository 2015
• Subjects: Public health surveillance; Public health surveillance—Philippines; Poisson distribution
• Online Access: https://animorepository.dlsu.edu.ph/etd_masteral/4842
• Institution: De La Salle University

One of the main areas of public health surveillance is infectious disease surveillance. With infectious disease backgrounds usually more complex, appropriate surveillance schemes must be in order. One such procedure is through the use of control charts. However, with most background processes following a ZIP distribution as brought about by the extra variability due to excess zeros, the control charting procedures must properly be developed to address this issue. Hence in this paper, drawing inspiration from the development of combined control charting procedures for simultaneously monitoring each ZIP parameter individually in the context of SPC, several Shewhart-type charts and CUSUM charts were modi ed to properly t the context of disease surveillance. Moreover, to potentially address the shortcomings of both of these charts, several combined EWMA control charting procedures were also developed (Bernoulli-ZIP and CRLZTP EWMA charts). Through an extensive simulation study involving multiple parameter settings and outbreak model considerations (i.e., different shapes, magnitude, and duration), some key results were observed. These include the applicability of performing combined control charting procedures for disease surveillance with a ZIP background, as exemplified by both the Shewhart-type and CUSUM charts having their corresponding properties carry-over to such surveillance context. Moreover, the Bernoulli-ZIP EWMA chart was observed to have addressed the intended improvement over both Shewhart and CUSUM schemes in the sense that it provided a balance of the two (i.e., better sensitivity over Shewhart-type charts while lower sensitivity against CUSUM charts better specificity over CUSUM charts while lower specificity against Shewhart-type charts). Lastly, an actual data demonstration of these charts, using confirmed measles cases in NCR from Jan. 1, 2010 to Jan. 14, 2015, revealed the comparability of the modified CUSUM and the Bernoulli-ZIP EWMA schemes to historical limits method currently in use.