Skip to content
All library documents

GARCH-MIDAS for Multiple Predictors in R

Article Quant Q&A · Author: Zeeshan Mohammad
Read the original

Summary

The document asks whether R can estimate a GARCH-MIDAS model with several financial and macroeconomic predictors for NIFTY50 returns. The motivation is to combine daily stock returns with macroeconomic variables reported monthly, quarterly, or annually, using the GARCH-MIDAS framework to model volatility across different data frequencies.

The author reports finding several R packages related to GARCH and MIDAS, but believes none support both multiple explanatory variables and GARCH estimation. The text provides no implementation, comparison, or empirical results, and leaves the central question unanswered. It is therefore useful as a concise statement of a modeling and software limitation rather than as a practical estimation guide; package capabilities may also change over time.

Key ideas

  • GARCH-MIDAS can relate daily return volatility to lower-frequency macroeconomic variables.
  • The author seeks to include multiple financial and macroeconomic predictors for NIFTY50.
  • The document reports a perceived lack of an R package supporting both multiple predictors and GARCH estimation.
  • No solution, package comparison, or empirical findings are provided.

Tags

EquitiesVolatilityStatistics
Full text
# Is there any way to implement GARCH-MIDAS model in R for multivariate estimation?


# Is there any way to implement GARCH-MIDAS model in R for multivariate estimation?












I'm writing a research paper in economics, and would like to research the impact of both financial and macroeconomic variables on the NIFTY50 index. My plan was to use a GARCH model. I've stumbled across the GARCH-MIDAS model which seems perfect, since many macrovariables are only in a monthly or quarterly or annual format, while the stock return is daily.

I've searched the internet for a R package that can support the model, but all the packages I find are only univariate, while I have several explanatory variables I want to include.

I've looked at the packages mfGARCH, GarchMidas, mcsGARCH, rumidas, rmgarch and midasr, but it seems that none of them both support multiple variables while still estimating GARCH models.

Shown in full with attribution under the source's licence. Licence: CC BY-SA 4.0 (Stack Exchange)

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.