Sparse HP filter: finding kinks in the COVID-19 contact rate

DOI10.1016/J.JECONOM.2020.08.008MaRDI QIDQ2224907zbMATHOpenAlexWikidataFDO

Authors Sokbae Lee, Yuan Liao, Myung Hwan Seo, Youngki Shin

Publication date 4 February 2021

Published in Journal of Econometrics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2006.10555

zbMATH Keywords

COVID-19trend filteringHodrick-Prescott filterknotspiecewise linear fitting

Mathematics Subject Classification ID

Applications of statistics to biology and medical sciences; meta analysis (62P10) Mathematical modeling or simulation for problems pertaining to biology (92-10)

Abstract: In this paper, we estimate the time-varying COVID-19 contact rate of a Susceptible-Infected-Recovered (SIR) model. Our measurement of the contact rate is constructed using data on actively infected, recovered and deceased cases. We propose a new trend filtering method that is a variant of the Hodrick-Prescott (HP) filter, constrained by the number of possible kinks. We term it the $extitsparseHPfilter$ and apply it to daily data from five countries: Canada, China, South Korea, the UK and the US. Our new method yields the kinks that are well aligned with actual events in each country. We find that the sparse HP filter provides a fewer kinks than the $el{l}_1$ trend filter, while both methods fitting data equally well. Theoretically, we establish risk consistency of both the sparse HP and $el{l}_1$ trend filters. Ultimately, we propose to use time-varying $extitcontactgrowthrates$ to document and monitor outbreaks of COVID-19.

Recommendations

• $\ell_1$ Trend Filtering
• Estimating and simulating a SIRD model of COVID-19 for many countries, states, and cities
• Boosting: why you can use the HP filter
• Compositional trend filtering
• Business cycles, trend elimination, and the HP filter

Cites work

• scientific article; zbMATH DE number 6982301 (Why is no real title available?)
• $\ell_1$ Trend Filtering
• Adaptive piecewise polynomial estimation via trend filtering
• Best subset binary prediction
• Best subset selection via a modern optimization lens
• Boosting With theL₂Loss
• Nonparametric inference on structural breaks
• Sparse high-dimensional regression: exact scalable algorithms and phase transitions
• Square-root lasso: pivotal recovery of sparse signals via conic programming
• The mathematics of infectious diseases
• Trend filtering on graphs
• Weak convergence and empirical processes. With applications to statistics

Cited in

(3)

• The spread of COVID-19 in London: network effects and optimal lockdowns
• A Dynamic Interaction Semiparametric Function-on-Scalar Model
• Grouped variable selection with discrete optimization: computational and statistical perspectives

Describes a project that uses

Uses Software

• CVXR
• coronavirus

This page was built for publication: Sparse HP filter: finding kinks in the COVID-19 contact rate

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2224907)