Diagonal GARCH Implementation for Prono (2014) Method

This file implements the bivariate diagonal GARCH model used in Prono (2014) for heteroskedasticity-based identification. Uses the modern tsmarch package which replaces the deprecated rmgarch.

Usage

fit_diagonal_garch_prono(
  data,
  garch_order = c(1, 1),
  ar_ma_order = c(1, 1),
  verbose = TRUE
)

Arguments

data

Data frame with Y1 (portfolio) and Y2 (market) returns

garch_order

GARCH(p,q) order, default c(1,1)

ar_ma_order

ARMA order for conditional covariances, default c(1,1)

verbose

Logical. Print fitting progress

Value

List containing:

fit

The fitted multivariate GARCH model

sigma2_sq

Conditional variance of Y2 (market)

sigma12

Conditional covariance between Y1 and Y2

residuals

Matrix of standardized residuals

spec

Model specification object

References

Prono, T. (2014). "The Role of Conditional Heteroskedasticity in Identifying and Estimating Linear Triangular Systems, with Applications to Asset Pricing Models That Include a Mismeasured Factor." Journal of Applied Econometrics. Fit Bivariate Diagonal GARCH Model (Prono Specification)

Fits a bivariate diagonal GARCH model to portfolio and market returns following Prono's exact specification.

Prono, T. (2014). The Role of Conditional Heteroskedasticity in Identifying and Estimating Linear Triangular Systems, with Applications to Asset Pricing Models That Include a Mismeasured Factor. Journal of Applied Econometrics, 29(5), 800-824. doi:10.1002/jae.2387

See also

prono_diagonal_garch for complete estimation fit_dcc_garch_fallback for fallback implementation