Skip to content

Reporting delays and day-of-week effects

Real surveillance data is rarely a clean count of infections on the day they occur. Cases are reported after a delay — an incubation period followed by a reporting lag — and the number reported depends on the day of the week. Tools for real-time estimation such as those of Abbott et al. [3] build these features into the observation model so that the latent infection signal is estimated free of reporting artefacts.

This case study keeps the renewal infection core of the previous example but replaces the simple observation model with a layered one: infections are convolved through two delay distributions and then modulated by a day-of-week reporting pattern. It also shows the latent process as an ARIMA-style differenced process broadcast to a weekly timescale, and assembles everything with IDProblem. The model follows the configuration of the EpiNow2 package [3] and is fit to daily confirmed COVID-19 cases from Italy's first wave in 2020.

The model

where is the incubation-period pmf, the reporting-delay pmf, and a day-of-week reporting multiplier.

A weekly latent process

The latent process is an ARIMA(2,1,1): an AR/MA combination (arma) wrapped in a DiffLatentModel to difference it once. Differencing makes the level a random walk rather than mean-reverting, which suits a reproduction number that can drift.

julia
using ComposableTuringIDModels, Distributions, Random, Turing, Mooncake
using ADTypes: AutoMooncake
Random.seed!(20240601)

arma21 = arma(
    init = [Normal(0, 0.2), Normal(0, 0.2)],
    damp = [truncated(Normal(0.1, 0.2), 0, 1), truncated(Normal(0.1, 0.05), 0, 1)],
    θ = [truncated(Normal(0.0, 0.2), -1, 1)],
    ϵ_t = HierarchicalNormal(std_prior = HalfNormal(0.1)))

arima211 = DiffLatentModel(; model = arma21, init_priors = [Normal(0.3, 0.3)])

broadcast_weekly makes the process piecewise-constant by week: a new value is drawn each week and held for seven days. This models as changing weekly rather than daily, which both regularises the estimate and cuts the number of latent parameters.

julia
weekly_latent = broadcast_weekly(arima211)

The infection process

As before, a Renewal process driven by a discretised generation interval. Here we use a generation time. The weekly process built above is folded into the renewal model's rt slot.

julia
data = IDData(gen_distribution = Gamma(1.4, 1 / 0.38))
renewal = Renewal(data;
    rt = weekly_latent, initialisation_prior = Normal(log(1.0), 1.0))

A layered observation model

We start from the NegativeBinomialError link and build outward. ascertainment_dayofweek wraps it with a partially pooled day-of-week multiplier, so reporting can be systematically higher or lower on particular weekdays.

julia
negbin = NegativeBinomialError(cluster_factor_prior = HalfNormal(0.1))
dayofweek_negbin = ascertainment_dayofweek(
    negbin; latent_model = HierarchicalNormal(std_prior = HalfNormal(1.0)))

LatentDelay convolves the expected observations with a delay distribution (discretised by double interval censoring). Two layers compose sequentially: an incubation period from infection to symptom onset, then a reporting delay from onset to report.

julia
incubation = LogNormal(1.6, 0.42)   # infection -> symptom onset
reporting = LogNormal(0.58, 0.47)   # symptom onset -> report

observation = LatentDelay(LatentDelay(dayofweek_negbin, incubation), reporting)

That single observation object now carries, from the inside out: a negative binomial link, a day-of-week ascertainment modifier, an incubation-delay convolution, and a reporting-delay convolution — assembled entirely by composition.

The data

We fit the model to the daily confirmed COVID-19 cases from Italy's first wave (the example series shipped with the EpiNow2 package), stored with the docs.

julia
using CSV, DataFrames
datapath = joinpath(pkgdir(ComposableTuringIDModels),
    "docs", "src", "case-studies", "data", "italy_data.csv")
italy = CSV.read(datapath, DataFrame)
n = 42
y_obs = italy.confirm[1:n]
(n = n, total_cases = sum(y_obs), from = italy.date[1], to = italy.date[n])
(n = 42, total_cases = 115239, from = Dates.Date("2020-02-22"), to = Dates.Date("2020-04-03"))

Assemble and fit

IDProblem ties the latent, infection, and observation models to a time span. Its as_turing_model method takes data as a named tuple with a y_t field (passing missing values would instead simulate from the prior).

julia
problem = IDProblem(
    infection = renewal,
    observation_model = observation,
    tspan = (1, n))

Fitting conditions on the observed reports, differentiating with the recommended Mooncake backend (see Automatic differentiation backend). We draw two chains in parallel with MCMCThreads(), which gives a cross-chain :

julia
posterior = as_turing_model(problem, (y_t = y_obs,))
chain = sample(
    posterior, NUTS(0.9; adtype = AutoMooncake(; config = nothing)),
    MCMCThreads(), 500, 2; progress = false)
Warning: Only a single thread available: MCMC chains are not sampled in parallel
@ AbstractMCMC ~/.julia/packages/AbstractMCMC/C1aKp/src/sample.jl:544
Info: Found initial step size
  ϵ = 0.0125
Info: Found initial step size
  ϵ = 0.00078125

sample returns a FlexiChains chain, which summarystats summarises directly — no conversion step. The day-of-week scale (DayofWeek.std) and the negative-binomial overdispersion (cluster_factor) appear alongside the latent-process parameters:

julia
using MCMCChains
summarystats(chain)
╭─FlexiSummary (9 statistics) ─────────────────────────────────────────────────
   iter    collapsed
   chain   collapsed
 ↓ stat  = [mean, std, mcse, ess_bulk, ess_tail, rhat, q5, q50, q95]

 Parameters (20) ── AbstractPPL.VarName
  Float64  latent_init[1], ar_init[1], ar_init[2], damp_AR[1], damp_AR[2],    
           θ[1], std, ϵ_t[1], ϵ_t[2], ϵ_t[3], init_incidence, DayofWeek.std,  
           DayofWeek.ϵ_t[1], DayofWeek.ϵ_t[2], DayofWeek.ϵ_t[3],              
           DayofWeek.ϵ_t[4], DayofWeek.ϵ_t[5], DayofWeek.ϵ_t[6],              
           DayofWeek.ϵ_t[7], cluster_factor                                   

 Extras (14)
  Float64  n_steps, is_accept, acceptance_rate, log_density,                  
           hamiltonian_energy, hamiltonian_energy_error,                      
           max_hamiltonian_energy_error, tree_depth, numerical_error,         
           step_size, nom_step_size, logprior, loglikelihood, logjoint        

 Summary
          param     mean     std    mcse   ess_bulk  ess_tail    rhat
   latent_init…   0.9243  0.1876  0.0089   450.7048  558.5930  1.0008
     ar_init[1]  -0.1418  0.1880  0.0071   706.7776  583.5517  0.9993
     ar_init[2]  -0.3726  0.1428  0.0076   350.3172  458.1083  1.0007
     damp_AR[1]   0.3027  0.1633  0.0081   349.3740  312.9884  1.0020
     damp_AR[2]   0.1136  0.0483  0.0017   691.9929  350.3164  1.0034
           θ[1]   0.0243  0.2007  0.0061  1088.9861  645.8307  1.0008
            std   0.1407  0.0733  0.0036   356.6203  273.1070  1.0082
         ϵ_t[1]  -0.8653  0.7637  0.0344   558.9163  429.3167  1.0032
         ϵ_t[2]  -0.8310  0.7876  0.0292   733.5148  473.8707  1.0020
         ϵ_t[3]  -0.0049  0.9837  0.0309  1016.9787  743.4748  1.0046
   init_incide…   4.0730  0.6684  0.0352   367.7801  514.6368  1.0011
   DayofWeek.s…   0.1212  0.0724  0.0049   208.8587  350.3547  1.0000
   DayofWeek.ϵ…   0.1328  0.6604  0.0249   715.6925  516.7136  1.0017
   DayofWeek.ϵ…  -0.1790  0.7330  0.0250   861.8326  558.1844  0.9991
   DayofWeek.ϵ…  -1.2388  0.7603  0.0266   838.5929  740.0623  1.0003
   DayofWeek.ϵ…  -0.1079  0.7231  0.0273   715.9723  593.3069  0.9995
   DayofWeek.ϵ…   0.3989  0.7343  0.0250   866.1375  632.8540  0.9996
   DayofWeek.ϵ…   0.3209  0.7533  0.0227  1075.7754  713.3223  1.0015
   DayofWeek.ϵ…   0.7098  0.7316  0.0296   619.9144  583.8060  1.0003
   cluster_fac…   0.1641  0.0284  0.0013   472.5570  601.2955  1.0001
╰──────────────────────────────────────────────────────────────────────────────╯

DayofWeek.std is the scale of the partially pooled weekday multipliers (its own block, prefixed because the ascertainment modifier introduces a named sub-process); cluster_factor is the negative-binomial overdispersion. The day-of-week effect, the two delay kernels, and the weekly reproduction number were all estimated jointly — and any of them can be swapped or removed by editing one line of the composition above.

Prior versus posterior

Sampling the same model with Prior gives a prior draw over the same parameters. Overlaying it on the posterior with PairPlots.jl — the FlexiChains extension turns each chain, subset to a few keys, into a PairPlots.Series — shows which parameters the six weeks of Italian data moved.

julia
using CairoMakie, PairPlots

prior_chain = sample(posterior, Prior(), 1000; progress = false)
pp_keys = [@varname(damp_AR), @varname(θ), @varname(std),
    @varname(cluster_factor)]
pairplot(
    PairPlots.Series(chain[pp_keys]; label = "posterior"),
    PairPlots.Series(prior_chain[pp_keys]; label = "prior"))

The innovation scale (std) and the negative-binomial overdispersion (cluster_factor) tighten under the data, while the autoregressive damping (damp_AR) and moving-average (θ) coefficients of the ARIMA process stay close to their weakly informative priors.

Posterior trajectories

  and the infections are generated quantities recovered per draw with generated_observables; the reports are scored element-wise, so their posterior-predictive distribution comes from predict on the model with the observations set to missing. Two small helpers reduce the per-draw trajectories to credible bands.

julia
gens = vec(generated_observables(posterior, (y_t = y_obs,), chain).generated)
Rt = credible_bands(reduce(hcat, (exp.(g.Z_t) for g in gens)))

pred = predict(as_turing_model(problem, (y_t = fill(missing, n),)), chain)
yt = predictive_bands(pred, n)

fig = Figure(; size = (760, 620))
ax1 = Axis(fig[1, 1]; ylabel = "Reproduction number Rₜ")
ci_ribbon!(ax1, 1:size(Rt, 1), Rt; color = :purple, label = "posterior median")
hlines!(ax1, [1.0]; color = :grey, linestyle = :dash)
axislegend(ax1; position = :rt)
ax2 = Axis(fig[2, 1]; xlabel = "Day", ylabel = "Confirmed cases")
ci_ribbon!(ax2, 1:size(yt, 1), yt; color = :teal,
    label = "posterior predictive")
scatter!(ax2, 1:n, y_obs; color = :black, markersize = 7, label = "observed")
axislegend(ax2; position = :lt)
fig

The weekly is piecewise-constant by construction, stepping down through one as the first wave turns over. The posterior-predictive band starts partway into the series — the two delay convolutions leave the earliest reference days without a fully supported expected count — and from there tracks the observed Italian reports, the layered observation model having absorbed the reporting pattern rather than the infection signal.

A time-varying reporting pattern

The day-of-week multiplier above is static: one weekly profile held fixed across the series. Reporting behaviour can itself drift — testing capacity changes, weekend effects strengthen or weaken — and the same composition expresses that. Because the ascertainment modifier takes any latent model, replacing the pooled HierarchicalNormal weekday effect with a BroadcastLatentModel over a process that evolves week to week turns the fixed profile into a time-varying one, at the cost of more latent parameters. The structural change is again local to the observation model; the infection and latent parts are untouched. We keep the static pattern here — it is identifiable from six weeks of data, where a fully time-varying weekday process would not be — and flag the richer variant rather than fit it.

References

  1. S. Abbott, J. Hellewell, R. N. Thompson, K. Sherratt, H. P. Gibbs, N. I. Bosse, J. D. Munday, S. Meakin, E. L. Doughty, J. Y. Chun and others. Estimating the time-varying reproduction number of SARS-CoV-2 using national and subnational case counts. Wellcome Open Research 5, 112 (2020).