TSLA's Jul 22 earnings miss, re-tested against high-beta growth peers instead of automakers

Follow-up to tsla_earnings_miss_auto_peers, which failed the fit-quality gate — pure Detroit automakers (F, GM) don't move with TSLA day-to-day at all. Treated: TSLA. Donors: RIVN, LCID (EV-specific, still auto but more growth-multiple-priced than F/GM), PLTR, COIN (retail-favorite high-beta momentum names with no automotive exposure, included on the theory that TSLA trades more on 'high-beta retail-momentum growth' factor exposure than on 'automaker' exposure most days). Same Jul 22 earnings-miss treatment date. Result: improved (relative RMSE 1.29x, down from 1.78x with pure automakers) but still fails the fit-quality gate — TSLA doesn't reconstruct cleanly from either peer group tried so far. Read as: TSLA is genuinely idiosyncratic (Musk/narrative -driven) rather than a donor-pool-selection failure specifically — a case where the honest answer is 'this method can't cleanly isolate an effect here,' not a forced conclusion either way.

Actual vs. synthetic counterfactual

Actual Synthetic (counterfactual)

Fit quality

Fit-window RMSE6.7895

RMSE ÷ fit-window std dev1.29×

Fit-window days125

Confound-window mean gapn/a (fit-end = treatment date)

Post-period mean gap-14.52

Placebo test — same method run on every unit, treated one highlighted

Unit	Mean post-period gap	Max abs. gap
RIVN	+29.71%	29.71%
LCID	-16.78%	16.78%
TSLA (treated)	-14.52%	14.52%
PLTR	-2.85%	2.85%
COIN	-0.71%	0.71%

Verdict

Do not trust the gap below. The fit-window RMSE is 1.29× this unit's own fit-window standard deviation — the donor pool literally cannot reconstruct TSLA's pre-period path at all, which usually means the donor pool is the wrong choice for this unit (e.g. TSLA moved for reasons entirely disconnected from the donors' own drivers), not that a real effect was found. Pick a different/better-correlated donor pool before drawing any conclusion from this run.