Volume weighting and index construction
How components contribute to a Bagonomics index: square-root weights, caps, and a chained Laspeyres-style divisor.
Square-root volume weighting
Each component's weight is proportional to the square root of its trailing 12-month traded volume (in USD). Square-root weighting compresses the gap between the most-traded and least-traded components — pure market-cap weighting would put 60%+ on Birkin 30 alone. Square-root keeps Birkin 30 dominant but lets a Loewe Puzzle still meaningfully contribute.
raw_weight_i = sqrt(volume_i) weight_i = raw_weight_i / sum(raw_weight_j)
Caps
No single component can exceed 12% of the index, and no single brand can exceed 35%. After computing raw square-root weights we apply caps, then re-normalize so the total returns to 100%. This is checked on every quarterly rebalance.
Chained divisor
Each index has a divisor that absorbs corporate-action-style events: component additions/removals at rebalance, methodology changes, discontinuation reclassification. The divisor is recalculated so the index value is continuous across the event — pricing changes drive the index, structural changes do not.
new_divisor = (sum(price_i * weight_i) for new universe) / index_value_before_event
Rebalance cadence
Quarterly. Each rebalance is recorded in index_rebalance_events with the before/after composition and a methodology version bump. The chained divisor preserves continuity.
Other topics
- Median, percentiles and IQR · Why we publish median and percentiles instead of mean prices, and how to read th…
- Compound Annual Growth Rate (CAGR) · How we annualize price changes across 1, 3, and 5 year windows.…
- Premium to retail · Definition of premium-to-retail, the country-of-retail convention, and how to in…
- Confidence labels · What 'low', 'medium', 'high' confidence on an aggregation means and when to use …