Returns attribution · multiple vs earnings

Where did the return come from?

ProductionVerdict · ATTRIBUTION PASSRecall · 0.71

Supporting · Return attribution · anchor metric: multiple-expansion vs EPS-growth split

What it measures

Decomposes an index's return into multiple expansion (paying more per dollar of earnings) versus earnings growth (more dollars to pay for). The split tells you whether a rally is sentiment or fundamentals.

\text{ret} \approx \frac{\Delta(\text{P/E})}{\text{P/E}} + \frac{\Delta(\text{EPS})}{\text{EPS}} \quad\text{\# first-order log decomposition}

\text{multiple\_share} = \Delta(\text{P/E}) \text{ component}

\text{earnings\_share} = \Delta(\text{EPS}) \text{ component}

Of the S&P's +13% YTD, if 9 points is multiple expansion and 3 is earnings, the rally is paying-more-per-dollar — price ran ahead of profits. A re-rating, not an earnings story.

Limitations

First-order — the cross term is small but non-zero at large moves.
Index-level — masks the dispersion underneath (a few names can carry the whole multiple).

In the product

The attribution split-bar in the Returns chapter ("Where did the return come from?"); SUPPORTING return-attribution voice.

Grading & stability

—

Gate rate
loading…

—

Stability / churn
not emitted

—

Mean confidence
loading…

fetching /api/panel/about/goldman_pe_eps/W/all …

Graded on the Tier-1 regime-test harness — curated macro events × 18-yr backfill × recall@K. Verdict ATTRIBUTION PASS (71%).

Charts it reads

Equity risk premium

equity_risk_premium—

ERP spread

equity_risk_premium_spread—

Returns attribution · multiple vs earnings · The Lens methodology← all engines