Selected article for: "ARIMAX model and cumulative incidence"
Author: Zaixing Shi; Ya Fang
Title: Temporal relationship between outbound traffic from Wuhan and the 2019 coronavirus disease (COVID-19) incidence in China
  • Document date: 2020_3_17
    • ID: hrrzztt5_22
    Snippet: The copyright holder for this preprint (which was not peer-reviewed) is the . https://doi.org/10.1101/2020.03.15.20034199 doi: medRxiv preprint in which is a covariate at time and is its coefficient. The lag values identified by the crosscorrelation analysis was applied to traffic time series data in the ARIMAX model. The models were fitted using data up to the expected turning point in COVID-19 incidence following the travel ban. We used the med.....
    Document: The copyright holder for this preprint (which was not peer-reviewed) is the . https://doi.org/10.1101/2020.03.15.20034199 doi: medRxiv preprint in which is a covariate at time and is its coefficient. The lag values identified by the crosscorrelation analysis was applied to traffic time series data in the ARIMAX model. The models were fitted using data up to the expected turning point in COVID-19 incidence following the travel ban. We used the median lag time for each cluster to determine the turning points. We used differencing to stationarize the COVID-19 incidence time series and checked stationarity using the augmented Dickey-Fuller test. The fitted ARIMAX model was used to forecast cumulative incidence till the end of February based on migration data during the same period in 2019. The difference between the predicted and observed cumulative incidence is the estimated intervention effect associated with the travel ban.

    Search related documents:
    Co phrase search for related documents
    • ARIMAX model and lag time: 1
    • cumulative incidence and February end: 1, 2
    • cumulative incidence and incidence time series: 1
    • cumulative incidence and intervention effect: 1
    • cumulative incidence and lag time: 1, 2, 3, 4, 5
    • cumulative incidence and lag value: 1
    • February end and intervention effect: 1
    • February end and lag time: 1
    • February end and lag value: 1
    • incidence time series and lag time: 1, 2, 3
    • incidence time series and median lag time: 1
    • intervention effect and lag time: 1, 2, 3, 4
    • lag time and median lag time: 1, 2, 3, 4, 5, 6