KILLED · turn-of-month
Hypothesis
Recurring inflows around month-end/start (DCA buyers, payday) create a turn-of-month bullish drift.
Math
$$ \bar r_{\text{ToM}} \text{ over days } \{-1,+1,+2,+3\}\ \text{around month boundary, bootstrap CI} $$
Method
Turn-of-month window returns vs rest-of-month, block bootstrap, stability across years.
Results
| Equities-style ToM effect | present pre-2021 |
| Crypto, recent years | not significant |
| 24/7 market dilution | likely cause |
The equities turn-of-month effect does not robustly transfer to a 24/7, globally-distributed, no-payday-cycle market. Faint and unstable; not significant in recent data. Killed.
Calendar effects borrowed from equities assume equity-market plumbing (paydays, month-end rebalancing, closed weekends). Crypto has none of it.