Package {MisRepARMA}

Type:	Package
Title:	Misreported Time Series Analysis
Version:	0.2.0
Date:	2026-06-07
Encoding:	UTF-8
Maintainer:	David Moriña Soler <David.Morina@uab.cat>
Description:	Provides a simple and trustworthy methodology for the analysis of misreported continuous time series using either a frequentist (bootstrap-based EM algorithm) or a Bayesian (MCMC via JAGS) approach. The frequentist method is described in Morina et al. (2021) <doi:10.1038/s41598-021-02620-5>. The Bayesian extension fits the same ARMA model with misreporting structure using a full posterior distribution, providing credible intervals and DIC for model comparison, as described in Morina et al. (2024) <doi:10.1101/2024.02.26.24303373>.
Depends:	R (≥ 3.5.0), mixtools, boot, tseries
Imports:	R2jags
Suggests:	coda
License:	GPL-2 | GPL-3 [expanded from: GPL (≥ 2)]
NeedsCompilation:	no
Packaged:	2026-06-07 08:47:03 UTC; dmorina
Author:	David Moriña Soler [aut, cre], Amanda Fernández-Fontelo [aut], Alejandra Cabaña [aut], Pedro Puig [aut], Biel Abarca Galván [aut]
Repository:	CRAN
Date/Publication:	2026-06-07 14:10:28 UTC

Misreported time series analysis

Description

Provides a simple and trustworthy methodology for the analysis of misreported continuous time series. See Moriña, D, Fernández-Fontelo, A, Cabaña, A, Puig P. (2021) <https://arxiv.org/abs/2003.09202v2>.

Details

The package implements function fitMisRepARMA, which is able to fit an ARMA time series model to misreported data, and the function reconstruct which is able to reconstruct the most likely real series.

Author(s)

David Moriña, Amanda Fernández-Fontelo, Alejandra Cabaña, Pedro Puig, Biel Abarca Galván

Mantainer: David Moriña Soler <dmorina@ub.edu>

References

Davison, A.C. and Hinkley, D.V. (1997) Bootstrap Methods and Their Application. Cambridge University Press.

Kunsch, H.R. (1989) The jackknife and the bootstrap for general stationary observations. Annals of Statistics, 17, 1217–1241.

Moriña, D., Fernández-Fontelo, A., Cabaña, A., Puig, P. (2021): New statistical model for misreported data with application to current public health challenges. arXiv preprint (https://arxiv.org/pdf/2003.09202.pdf)

Politis, D.N. and Romano, J.P. (1994) The stationary bootstrap. Journal of the American Statistical Association, 89, 1303–1313.

See Also

MisRepARMA-package, fitMisRepARMA, reconstruct

Internal MisRepARMA functions

Description

Internal MisRepARMA functions not intended to be called directly by the user.

Usage

estimate(data, tol, p_AR, q_MA, covars = NULL, misReport = "U")
estimate_bayes(data, p_AR, q_MA, covars = NULL, misReport = "U",
               n_chains = 3, n_iter = 2000, n_burnin = 500, n_thin = 1,
               q_prior_a = NULL, q_prior_b = NULL,
               w_prior_a = 1, w_prior_b = 1,
               q_init = NULL, w_init = NULL)
ran.genf(data, n, ran.args)
## S3 method for class 'fitMisRepARMA'
summary(object, ...)
## S3 method for class 'fitMisRepARMA'
print.summary(x, ...)

Arguments

Details

estimate implements the frequentist iterative EM algorithm.

estimate_bayes implements Bayesian MCMC estimation via JAGS, called internally by fitMisRepARMA when method = "bayes".

ran.genf generates synthetic replicates for the bootstrap.

summary.fitMisRepARMA and print.summary.fitMisRepARMA provide formatted summaries for both frequentist and Bayesian fits.

See Also

MisRepARMA-package, fitMisRepARMA, reconstruct

Fit ARMA model to misreported time series data

Description

Fits an ARMA model to misreported (underreported or overreported) continuous time series data using either a frequentist bootstrap-based EM algorithm (method = "freq") or a Bayesian MCMC approach via JAGS (method = "bayes").

Usage

fitMisRepARMA(y, tol, B, p_AR, q_MA, covars = NULL, misReport = "U",
              method = "freq", n_chains = 3, n_burnin = NULL,
              n_thin = 1, w_prior_a = 1, w_prior_b = 1, ...)

Arguments

Details

The model assumes a latent ARMA(p, r) process X_t that is only partially observed through:

Y_t = \begin{cases} X_t & \text{with probability } 1-\omega \\ q \cdot X_t & \text{with probability } \omega \end{cases}

where q is the misreporting intensity and \omega is its frequency.

The frequentist method estimates parameters via an iterative EM algorithm with bootstrap uncertainty quantification.

The Bayesian method samples from the full posterior via JAGS, initialising chains near the frequentist estimates. Convergence should be checked with the Gelman-Rubin statistic (\hat{R} < 1.1) accessible via attr(fit, "jags")$BUGSoutput$summary.

Value

An object of class fitMisRepARMA with elements:

Attributes: q (misreporting intensity), w (frequency), z (misreporting indicator), covars (covariate fit), x_rec (Bayesian latent process), DIC (Bayesian), jags (full JAGS object, Bayesian only).

Author(s)

David Morina, Amanda Fernandez-Fontelo, Alejandra Cabana, Pedro Puig, Biel Abarca Galvan

References

Morina, D., Fernandez-Fontelo, A., Cabana, A., Puig, P. (2021): New statistical model for misreported data with application to current public health challenges. Scientific Reports, 11, 23321. doi:10.1038/s41598-021-02620-5

See Also

MisRepARMA-package, reconstruct

Examples

set.seed(12345)
x   <- arima.sim(model = list(ar = 0.4), n = 100)
ind <- rbinom(100, 1, 0.6)
y   <- ifelse(ind == 0, x, x * 0.3)

mod_freq <- fitMisRepARMA(y, tol = 1e-4, B = 50, p_AR = 1, q_MA = 0,
                          misReport = "U", method = "freq")
summary(mod_freq)
reconstruct(mod_freq)

## Not run: 
mod_bayes <- fitMisRepARMA(y, tol = 1e-4, B = 1000, p_AR = 1, q_MA = 0,
                           misReport = "U", method = "bayes",
                           n_chains = 3, n_burnin = 200)
summary(mod_bayes)

## End(Not run)

Reconstruct the most likely series

Description

Reconstructs the most likely series.

Usage

  reconstruct(object)

Arguments

Value

the function returns a vector of the same length of data containing the reconstruction of the most likely series.

Author(s)

David Moriña, Amanda Fernández-Fontelo, Alejandra Cabaña, Pedro Puig, Biel Abarca Galván

References

D. Moriña, A. Fernández-Fontelo, A. Cabaña, P. Puig (2021): New statistical model for misreported data with application to current public health challenges. arXiv preprint (https://arxiv.org/pdf/2003.09202.pdf)

Davison, A. C. and Hinkley, D. V. (1997) Bootstrap Methods and Their Applications. Cambridge University Press, Cambridge. ISBN 0-521-57391-2

See Also

MisRepARMA-package, fitMisRepARMA

Examples

### Example 1: frequentist reconstruction
set.seed(12345)
x   <- arima.sim(model = list(ar = 0.4), n = 100)
ind <- rbinom(100, 1, 0.6)
y   <- ifelse(ind == 0, x, x * 0.3)

fit  <- fitMisRepARMA(y, tol = 1e-6, B = 50, p_AR = 1, q_MA = 0,
                      covars = NULL, misReport = "U", method = "freq")
x_hat <- reconstruct(fit)
plot(y,     type = "l", col = "black", ylab = "Series",
     main = "Observed (black) vs reconstructed (red)")
lines(x_hat, col = "red", lty = 2)

## Not run: 
### Example 2: Bayesian reconstruction (requires R2jags and JAGS)
fit_b  <- fitMisRepARMA(y, tol = 1e-6, B = 5000, p_AR = 1, q_MA = 0,
                        covars = NULL, misReport = "U", method = "bayes",
                        n_chains = 3, n_burnin = 1000)
x_hat_b <- reconstruct(fit_b)
lines(x_hat_b, col = "blue", lty = 3)
legend("topright", legend = c("Observed", "Freq.", "Bayes"),
       col = c("black","red","blue"), lty = c(1,2,3))

## End(Not run)