Dataset Information

Time series analysis of COVID-19 infection curve: A change-point perspective.

ABSTRACT: In this paper, we model the trajectory of the cumulative confirmed cases and deaths of COVID-19 (in log scale) via a piecewise linear trend model. The model naturally captures the phase transitions of the epidemic growth rate via change-points and further enjoys great interpretability due to its semiparametric nature. On the methodological front, we advance the nascent self-normalization (SN) technique (Shao, 2010) to testing and estimation of a single change-point in the linear trend of a nonstationary time series. We further combine the SN-based change-point test with the NOT algorithm (Baranowski et al., 2019) to achieve multiple change-point estimation. Using the proposed method, we analyze the trajectory of the cumulative COVID-19 cases and deaths for 30 major countries and discover interesting patterns with potentially relevant implications for effectiveness of the pandemic responses by different countries. Furthermore, based on the change-point detection algorithm and a flexible extrapolation function, we design a simple two-stage forecasting scheme for COVID-19 and demonstrate its promising performance in predicting cumulative deaths in the U.S.

SUBMITTER: Jiang F

PROVIDER: S-EPMC7392157 | biostudies-literature | 2020 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Time series analysis of COVID-19 infection curve: A change-point perspective.

Jiang Feiyu F Zhao Zifeng Z Shao Xiaofeng X

Journal of econometrics 20200730 1

In this paper, we model the trajectory of the cumulative confirmed cases and deaths of COVID-19 (in log scale) via a piecewise linear trend model. The model naturally captures the phase transitions of the epidemic growth rate via change-points and further enjoys great interpretability due to its semiparametric nature. On the methodological front, we advance the nascent self-normalization (SN) technique (Shao, 2010) to testing and estimation of a single change-point in the linear trend of a nonst ...[more]

PMID: 32836681

Similar Datasets

Project description:Background In March 2020, the government of Uganda implemented a strict lockdown policy in response to the COVID-19 pandemic. We performed an interrupted time series analysis (ITSA) to assess whether major changes in healthcare seeking behavior, malaria burden, and case management occurred after the onset of the COVID-19 epidemic. Methods Individual level data from all outpatient visits occurring from April 2017 through March 2021 at 17 facilities were analyzed. Outcomes included total outpatient visits, malaria cases, non-malarial visits, proportion of visits with suspected malaria, proportion of patients tested using rapid diagnostic tests (RDTs), and proportion of malaria cases prescribed artemether-lumefantrine (AL). Pre-COVID trends measured over a three-year period were extrapolated into the post-COVID period (April 2020- March 2021) using Poisson regression with generalized estimating equations or fractional regression. Effects of COVID-19 were estimated over the 12-month post-COVID period by dividing observed values by the predicted values and expressed as ratios. Results A total of 1,442,737 outpatient visits were recorded. Malaria was suspected in 55.3% of visits and 98.8% of these had a malaria diagnostic test performed. ITSA showed no differences in the observed versus predicted total outpatient visits, malaria cases, non-malarial visits, or proportion of visits with suspected malaria. However, in the second six months of the post-COVID period, there was a smaller mean proportion of patients tested with RDTs compared to predicted (Relative Prevalence Ratio (RPR) = 0.87, CI [0.78, 0.97]) and a smaller mean proportion of malaria cases prescribed AL (RPR = 0.94, CI [0.90, 0.99]. Conclusions There was evidence for a modest decrease in the proportion of RDTs used for malaria diagnosis and the proportion of patients prescribed AL in the second half of the post-COVID year, while other malaria indicators remained stable. Continued surveillance will be essential to monitor for changes in trends in malaria indicators so that Uganda can quickly and flexibly respond to challenges imposed by COVID-19.

Dataset Information

Time series analysis of COVID-19 infection curve: A change-point perspective.

Publications

Time series analysis of COVID-19 infection curve: A change-point perspective.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure