timeseries-detrending

What problem does it solve?

Detrending time series is essential for macroeconomic analysis to separate long-run movement from short-term fluctuations, enabling clearer assessment of cycles.

Core Features & Use Cases

• HP filter guidance: Decomposes a series into trend and cyclical components with guidance on choosing lambda by data frequency.
• Log transformations for growth series: Applies log transforms before detrending to stabilize variance and interpret cycles as percentage deviations.
• Correlation and volatility analysis: Enables comparisons of business-cycle dynamics across variables (GDP, consumption, investment) and cross-series correlations.
• Workflow examples: Use cases include analyzing GDP growth dynamics, comparing sectoral cycles, and monitoring turning points in macro data.

Quick Start

Apply the HP filter to your log-transformed GDP series to extract the cycle and trend components.