Detecting changes in mean of Malaria Time Series Using change point analysis
Abstract Background A sequence of observation usually undergoes sudden changes at unknown times. Hence, there is need to find out if a shift has occurred in time series data by identifying set of change points. Change point detection is the identification of abrupt changes in time series (sequential) data. Change point detection can be done using SPC or statistical change point detection methods. The algorithm uses CUSUM plus bootstrapping. Objective To detect points of change in mean of malaria time series using change point analysis Methods CUSUM CPA was used to detect changes in mean within the malaria time series data for Eldoret East district for the period 2010 and 2011. To detect change in mean, the two-step procedures in clued (1) calculating cumulative sums, followed by (2) use of bootstrapping to make inferences. Results The results suggest that most important changes in mean time series for malaria cases occur between May 2010 and December 2011 where the trends of malaria cases have reduced. It is shown that statistically detected changes in the mean of a time series coincide with identifiable period when the interventions were put in place and when there were epidemics, which might have caused these change points Conclusion It is suggested that CUSUM CPA is an effective tool for detecting changes in mean for time series data and should be adopted so as to detect points of change due to epidemics or intervention impact together with the existing methods so as to get meaningful results.