macroeconomic-uncertainty

This Skill automates measuring macroeconomic uncertainty by fetching public data from Eurostat and ECB, applying stationarity transformations, and estimating factor-based forecast errors with stochastic-volatility models to produce horizon-specific uncertainty indices.

You need public monthly data from Eurostat, ECB, OECD, and BIS for Euro Area economic uncertainty time-series analysis. The pipeline automates fetching these sources, then applies strict cleaning and stationarity transformations before estimating stochastic-volatility models.

Yes, running the macroeconomic uncertainty pipeline requires both Python and R environments. It uses Python packages like pandas and statsmodels alongside R packages like r-stochvol and r-coda to estimate stochastic-volatility models and factor-based forecast errors.

To build and visualize MacroEconomic Uncertainty indices step by step, run `pixi run pytask`. This command automates data fetching, stationarity transformations, stochastic-volatility estimation, and generates final Plotly figures comparing MEU availability across horizons.

Yes, you can use pandas and statsmodels with R packages like r-stochvol and r-coda for time-series analysis in one workflow. The pipeline integrates both environments seamlessly, optimized for reproducibility using the pixi and pytask frameworks to manage dependencies.

A limitation of using factor-based forecast errors for economic uncertainty estimation is that the pipeline requires strictly stationary transformed data and is specifically optimized for the Euro Area context. It depends on continuous monthly data availability from ECB and Eurostat.