配對交易與共整合：避險比率、價差與 z 分數

WITH
    px AS (
        SELECT
            ticker,
            date,
            toFloat64(any(close)) AS close_px
        FROM global_markets.stocks_daily_aggs
        WHERE ticker IN ('KO', 'PEP', 'HD', 'LOW', 'XOM', 'CVX', 'V', 'MA', 'AAPL', 'MSFT')
          AND date BETWEEN '2024-01-01' AND '2025-12-31'
        GROUP BY ticker, date
    ),
    rets AS (
        SELECT
            ticker,
            date,
            close_px,
            close_px / lagInFrame(close_px) OVER (
                PARTITION BY ticker ORDER BY date
                ROWS BETWEEN 1 PRECEDING AND CURRENT ROW
            ) - 1 AS ret
        FROM px
    )
SELECT
    p.pair                                  AS pair,
    round(corr(a.ret, b.ret), 3)            AS return_corr,
    round(corr(a.close_px, b.close_px), 3)  AS price_corr
FROM
(
    SELECT
        tupleElement(t, 1) AS leg_a,
        tupleElement(t, 2) AS leg_b,
        tupleElement(t, 3) AS pair
    FROM
    (
        SELECT arrayJoin([
            ('KO',   'PEP',  'KO / PEP'),
            ('HD',   'LOW',  'HD / LOW'),
            ('XOM',  'CVX',  'XOM / CVX'),
            ('V',    'MA',   'V / MA'),
            ('AAPL', 'MSFT', 'AAPL / MSFT')
        ]) AS t
    )
) AS p
INNER JOIN rets AS a ON a.ticker = p.leg_a
INNER JOIN rets AS b ON b.ticker = p.leg_b AND b.date = a.date
WHERE isFinite(a.ret) AND isFinite(b.ret)
GROUP BY pair
ORDER BY return_corr DESC

WITH
    daily AS (
        SELECT
            date,
            anyIf(toFloat64(close), ticker = 'PEP') AS pep,
            anyIf(toFloat64(close), ticker = 'KO')  AS ko
        FROM global_markets.stocks_daily_aggs
        WHERE ticker IN ('KO', 'PEP')
          AND date BETWEEN '2023-01-01' AND '2025-12-31'
        GROUP BY date
        HAVING pep > 0 AND ko > 0
    ),
    fitted AS (
        SELECT covarSamp(pep, ko) / varSamp(ko) AS beta
        FROM daily
        WHERE date < '2024-01-01'
    ),
    spread AS (
        SELECT
            daily.date                          AS date,
            daily.pep - fitted.beta * daily.ko  AS spread_usd
        FROM daily
        CROSS JOIN fitted
    ),
    scored AS (
        SELECT
            date,
            (spread_usd - avg(spread_usd) OVER (
                 ORDER BY date ROWS BETWEEN 62 PRECEDING AND CURRENT ROW))
            / stddevSampStable(spread_usd) OVER (
                 ORDER BY date ROWS BETWEEN 62 PRECEDING AND CURRENT ROW) AS z
        FROM spread
    )
SELECT
    toString(toMonday(date))   AS week,
    round(argMax(z, date), 2)  AS z_score
FROM scored
WHERE date >= '2024-01-01'
  AND isFinite(z)
GROUP BY week
ORDER BY week

WITH
    daily AS (
        SELECT
            date,
            anyIf(toFloat64(close), ticker = 'PEP') AS pep,
            anyIf(toFloat64(close), ticker = 'KO')  AS ko
        FROM global_markets.stocks_daily_aggs
        WHERE ticker IN ('KO', 'PEP')
          AND date BETWEEN '2018-01-01' AND '2025-12-31'
        GROUP BY date
        HAVING pep > 0 AND ko > 0
    ),
    spread AS (
        SELECT
            date,
            log(pep / ko) AS log_ratio
        FROM daily
    ),
    scored AS (
        SELECT
            date,
            (log_ratio - avg(log_ratio) OVER (
                 ORDER BY date ROWS BETWEEN 62 PRECEDING AND CURRENT ROW))
            / stddevSampStable(log_ratio) OVER (
                 ORDER BY date ROWS BETWEEN 62 PRECEDING AND CURRENT ROW) AS z
        FROM spread
    ),
    horizon AS (
        SELECT
            date,
            z,
            leadInFrame(z, 20) OVER (
                ORDER BY date ROWS BETWEEN CURRENT ROW AND 20 FOLLOWING
            ) AS z_fwd
        FROM scored
        WHERE isFinite(z)
    )
SELECT
    multiIf(z < -2, 'z below -2',
            z < -1, 'z -2 to -1',
            z <  0, 'z -1 to 0',
            z <  1, 'z 0 to 1',
            z <  2, 'z 1 to 2',
                    'z above 2')  AS z_bucket,
    round(avg(z), 2)              AS avg_z_start,
    round(avg(z_fwd), 2)          AS avg_z_20d_later,
    count()                       AS episode_count
FROM horizon
WHERE date >= '2019-01-01'
  AND date <= '2025-11-15'
  AND isFinite(z_fwd)
GROUP BY z_bucket
ORDER BY avg_z_start

WITH daily AS (
    SELECT
        date,
        anyIf(toFloat64(close), ticker = 'PEP') AS pep,
        anyIf(toFloat64(close), ticker = 'KO')  AS ko,
        anyIf(toFloat64(close), ticker = 'LOW') AS lowes,
        anyIf(toFloat64(close), ticker = 'HD')  AS hd
    FROM global_markets.stocks_daily_aggs
    WHERE ticker IN ('KO', 'PEP', 'HD', 'LOW')
      AND date BETWEEN '2019-01-01' AND '2025-12-31'
    GROUP BY date
    HAVING ko > 0 AND pep > 0 AND hd > 0 AND lowes > 0
)
SELECT
    toYear(date)                                  AS year,
    round(covarSamp(pep, ko) / varSamp(ko), 3)    AS pep_on_ko_beta,
    round(covarSamp(lowes, hd) / varSamp(hd), 3)  AS lowes_on_hd_beta
FROM daily
GROUP BY year
ORDER BY year