time-series-social

What problem does it solve?

Time series analysis helps you turn messy, time-indexed social data into reliable forecasts and effect estimates instead of misleading correlations.

Core Features & Use Cases

• Stationarity & pre-model checks: Runs ADF and KPSS to decide whether to difference, transform, or model long-run relationships.
• Core time-series models for social research: Builds ARIMA, VAR/Granger causality, cointegration tests, and VECM when long-run equilibrium matters.
• Causal-adjacent policy/event evaluation over time: Supports structural break detection and intervention/event study-style analysis (step/pulse/ramp) to quantify temporal impacts.
• Use Case: You have monthly public opinion, media sentiment, and a policy index over several years and want to (1) test temporal predictability (Granger), (2) model co-movements (VAR), and (3) detect regime shifts or policy effects around a known date.

Quick Start

Use this skill to analyze a dataset of social indicators over time and produce stationarity results, an ARIMA/VAR plan, and an intervention-impact assessment around a specified event date.