Seasonality in COVID-19 times

Area of Science:

• Econometrics
• Time Series Analysis
• Statistical Modeling

Background:

• The COVID-19 pandemic significantly impacted economic data generation.
• Unprecedented changes in economic series necessitate robust statistical methods.
• Understanding data heterogeneity during crisis periods is crucial for accurate analysis.

Purpose of the Study:

• To compare the performance of various seasonal adjustment methods.
• To assess the impact of outliers and trend/seasonality changes on time series data.
• To identify reliable methods for economic data analysis post-COVID-19.

Main Methods:

• Simulations were conducted to model data generating processes.
• Outliers were introduced into trend and seasonal components.
• Performance metrics were used to evaluate different seasonal adjustment techniques.

Main Results:

• Certain seasonal adjustment methods demonstrated greater resilience to outliers.
• The heterogeneity introduced by the pandemic significantly affected standard adjustment procedures.
• Method performance varied depending on the type and magnitude of introduced anomalies.

Conclusions:

• Standard seasonal adjustment methods may require re-evaluation in light of pandemic-induced data disruptions.
• Simulations with realistic outlier scenarios are vital for method selection.
• Further research is needed to develop adaptive seasonal adjustment techniques for crisis periods.