Skip to contents

The dynamite R package provides easy-to-use interface for Bayesian inference of complex panel (time series) data comprising of multiple measurements per multiple individuals measured in time. The main features distinguishing the package and the underlying methodology from many other approaches are:

  • Support for both time-invariant and time-varying effects modeled via B-splines.
  • Joint modeling of multiple measurements per individual (multiple channels) based directly on the assumed data generating process.
  • Support for non-Gaussian observations: Currently Gaussian, Categorical, Poisson, Bernoulli, Binomial, Negative Binomial, Gamma, Exponential, and Beta distributions are available and these can be mixed arbitrarily in multichannel models.
  • Allows evaluating realistic long-term counterfactual predictions which take into account the dynamic structure of the model by posterior predictive distribution simulation.
  • Transparent quantification of parameter and predictive uncertainty due to a fully Bayesian approach.
  • User-friendly and efficient R interface with state-of-the-art estimation via Stan. Both rstan and cmdstanr backends are supported.

The dynamite package is developed with the support of Academy of Finland grant 331817 (PREDLIFE).


You can install the development version of dynamite from GitHub by running one of the following lines:

# install.packages("devtools")
install.packages("dynamite", repos = "")


A single-channel model with time-invariant effect of z, time-varying effect of x, lagged value of the response variable y and a group-specific random intercepts:

gaussian_example_fit <- dynamite(
  obs(y ~ -1 + z + varying(~ x + lag(y)), family = "gaussian") + 
    random() + splines(df = 20),
  data = gaussian_example, time = "time", group = "id",
  iter = 2000, warmup = 1000, thin = 5,
  chains = 2, cores = 2, refresh = 0, save_warmup = FALSE

Posterior estimates of the fixed effects:


Posterior estimates of time-varying effects

plot_deltas(gaussian_example_fit, scales = "free")

And group-specific intercepts:


Traceplots and density plots:

plot(gaussian_example_fit, type = "beta")

Posterior predictive samples for the first 4 groups (samples based on the posterior distribution of model parameters and observed data on first time point):

pred <- predict(gaussian_example_fit, n_draws = 50)
pred |> dplyr::filter(id < 5) |> 
  ggplot(aes(time, y_new, group = .draw)) +
  geom_line(alpha = 0.5) + 
  # observed values
  geom_line(aes(y = y), colour = "tomato") +
  facet_wrap(~ id) +

For more examples, see the package vignette.

  • The dynamite package uses Stan via rstan and cmdstanr (see also, which is a probabilistic programming language for general Bayesian modelling.

  • The brms package also uses Stan, and can be used to fit various complex multilevel models.

  • Regression modelling with time-varying coefficients based on kernel smoothing and least squares estimation is available in package tvReg. The tvem package provides similar functionality for gaussian, binomial and poisson responses with mgcv backend.

  • plm contains various methods to estimate linear models for panel data, e.g. the fixed effect models.

  • lavaan provides tools for structural equation modelling, and as such can be used to model various panel data models as well.


Contributions are very welcome, see for general guidelines.