algorithmic-trading-anthology-july-2026-enso-in-commodity-currency-fx

Conclusion: Null

No effect. Of 20 tests, 2 fell below the usual threshold individually — about what chance produces over this many attempts — and none survived correction for the size of the search.

Every test, against the significance threshold

persistence-robust p · left is stronger evidence

Filled markers fall below the 0.05 threshold before multiple-testing correction; hollow markers do not. Correction is applied across the whole batch, so an individual marker clearing the line is not a result on its own.

Tests

ticker × horizon

p < 0.05

uncorrected

Best q

0.83

BH-FDR

Survived

q ≤ 0.10

Method

Hypothesis

Agriculture is a small share of Australian exports, but drought years historically coincide with growth downgrades. The AUD/NZD cross is the cleanest expression if the two economies respond with opposite sign.

Rule

signal = soi_3m # 3-month mean SOI

prior = +1 # higher SOI -> higher returns

function test(instrument, horizon h):

y = sum(returns[instrument], t+1 .. t+h) # strictly forward

x = signal[t] # known at t

beta, t_stat = OLS(y ~ x) with Newey-West HAC, lag = h + 1

# null: slide x against y by every admissible offset, so

# persistence appears identically under the null

null = [slope(y, roll(x, k)) for k in all offsets]

p = (count(abs(null) >= abs(beta)) + 1) / (len(null) + 1)

return beta, t_stat, p

reject if Benjamini-Hochberg q <= 0.10 across the whole study

Evaluation

Table 1 · Every test in this hypothesis

forward return regressed on the SOI signal

Instrument	Horizon	n	β	HAC t	Shift p	Sign as predicted
AUD/USD	1m	240	+0.0003	+1.36	0.105	yes
AUD/USD	3m	238	+0.0009	+1.64	0.097	yes
AUD/USD	6m	235	+0.0006	+0.52	0.277	yes
AUD/USD	12m	229	-0.0009	-0.50	0.626	no
NZD/USD	1m	269	+0.0001	+0.40	0.287	yes
NZD/USD	3m	267	+0.0002	+0.31	0.343	yes
NZD/USD	6m	264	+0.0001	+0.07	0.467	yes
NZD/USD	12m	258	-0.0007	-0.35	0.607	no
AUD/NZD	1m	269	+0.0002	+1.44	0.036	yes
AUD/NZD	3m	267	+0.0007	+1.93	0.020	yes
AUD/NZD	6m	264	+0.0005	+1.20	0.149	yes
AUD/NZD	12m	258	-0.0000	-0.07	0.469	no
AUD/JPY	1m	269	+0.0002	+0.83	0.227	yes
AUD/JPY	3m	267	+0.0011	+1.96	0.086	yes
AUD/JPY	6m	264	+0.0012	+1.09	0.178	yes
AUD/JPY	12m	258	+0.0009	+0.49	0.375	yes
USD/BRL	1m	250	-0.0004	-1.09	0.868	no
USD/BRL	3m	248	-0.0015	-1.64	0.876	no
USD/BRL	6m	245	-0.0021	-1.12	0.848	no
USD/BRL	12m	239	-0.0011	-0.33	0.688	no

+ 16 more rows− fewer rows

Shift p is the persistence-robust p-value and is the one that decides. HAC t is shown to demonstrate how far conventional inference overstates the evidence.

Reference

Instruments

last price and one-month change, live from Yahoo Finance

Symbol	Notes
AUD/JPY	AUD/JPY — spot exchange rate.
AUD/NZD	AUD/NZD — spot exchange rate.
AUD/USD	AUD/USD — spot exchange rate.
NZD/USD	NZD/USD — spot exchange rate.
USD/BRL	USD/BRL — spot exchange rate.

Sample

1970–2026 monthly

Sources

Queensland Department of Agriculture and Fisheries. Southern Oscillation Index. The Long Paddock. Monthly, 1876–. www.longpaddock.qld.gov.au/soi/soi-data-files

Yahoo Finance. Historical market prices. Adjusted close, month-end. Retrieved with yfinance. finance.yahoo.com

Revision history

Rev	Stage	Status	Change
01	Draft	—	Direction and criteria fixed before the experiment ran
02	Tested	Null	20 tests; 2 below p=0.05, none surviving FDR