Skip to contents

Changelog

Source: NEWS.md

emhawkes 0.9.9

  • Resolve parameter sharing once per fit while preserving coefficient names and order. Validate function parameter defaults and warn about conflicting shared starting values.
  • Share observation and initial-state validation across estimation, likelihood evaluation, and simulation. Check supplied counting processes against event data.
  • Add the named Nc0 argument to hfit. Select declared callback arguments and preserve optional defaults and ....
  • Expand scalar initial excitation consistently. Warn that simulation’s legacy recycling and truncation of other initial values is deprecated.
  • Correct event types for multi-kernel simulation and likelihoods for univariate multi-kernel models.
  • Record state-dependent baselines at the correct side of each event. Return empty residuals for types with fewer than two events.
  • Stop simulation when no further event occurs, preserving only generated rows.
  • Use stable exponential integrals and log-scale residual densities and survival probabilities.
  • Validate decay rates and kernel mappings. Correct stability checks for constant multi-kernel Hawkes models.
  • Correct trapezoid-exponential random generation and validate its parameter domain. Add log and tail options to its distribution functions.
  • Simulation draws can change for the same seed where event selection or random generation was corrected.

emhawkes 0.9.7

CRAN release: 2023-02-02

Fixed some bugs

Breaking changes

  • Flexible residual point process with self/mutually exciting and exponential decay model is available.

emhawkes 0.9.7

CRAN release: 2023-02-02

Fixed some bugs, improved efficiency in this version and several features have been added.

Breaking changes

  • The lambda0 argument name used in previous versions has been changed to lambda_component0 in this version. This is to clearly indicate the meaning of the argument and to avoid confusion.

  • The name of method vol is changed to hvol and this feature is currently experimental.

  • The Vignette file contains more examples and explanations.

emhawkes 0.9.6

Fixed some bugs, improved efficiency in this version and several features have been added.

Breaking changes

  • Slot eta is introduced which represents the constant part of impact.

  • The concepts of rambda and rambda_component are introduced. They are closely related to the right-continuous version of the intensity process.

  • For inference of intensity and goodness of fit, infer_lambda and residual_process functions are implemented.

  • The method vol to measure the volatility is introduced and this feature is currently experimental.