Variance Ratio Test

Family: Microstructure

What it computes

Emits VarianceRatioTestTick ticks carrying lag_q, variance_ratio, z_statistic, var_r1, var_rq, n_intraday_bars off stock trade tape (1m bars).

Available on the live, historical, and replay drives.

Methodology

Lo / MacKinlay (1988) random-walk test VR(q) = Var(r_q) / (q · Var(r_1)) with the overlapping-sample null variance 2(2q−1)(q−1)/(3qN) (eq. 14) and unbiased overlap divisor (eq. 12a-12b).

See the methodology overview for the citation index.

Inputs

Stock trade tape (1m bars).

Key outputs

Lag_q, variance_ratio, z_statistic, var_r1, var_rq, n_intraday_bars. The full field set is in the tick table below.

Output schema (VarianceRatioTestTick)

The field / type / description table below is regenerated from the VarianceRatioTestTick Rust source by docs-site/scripts/inject-doc-tables.ts on every npm run docs:build. Do not hand-edit between the sentinels.

Field	Type	Description
symbol	Arc<str>	Underlying symbol (interned).
date	i32	Trading-session date (YYYYMMDD) at emission time.
ms_of_day	i32	Milliseconds since midnight ET at emission time.
lag_q	i32	Lag q the variance ratio was fit against.
variance_ratio	f64	Variance ratio VR(q) = Var(r_q) / (q · Var(r_1)). NaN with fewer than q + 1 bars or on a degenerate flat-tape window.
z_statistic	f64	Asymptotic Lo / MacKinlay z-statistic under the homoscedasticity-adjusted variance. NaN whenever variance_ratio is.
var_r1	f64	Per-bar return sample variance Var(r_1). Surfaced even on the cold-start regime so the consumer can read the rolling-window intraday vol directly.
var_rq	f64	q-bar overlapping return variance Var(r_q), estimated with the Lo / MacKinlay (1988) unbiased overlap divisor (N − q + 1)(1 − q/N) and deviations measured against q · μ̂ (their eq. (12a)-(12b)). NaN with fewer than q + 1 bars.
n_intraday_bars	i32	Count of intraday bars currently inside the rolling window.

Configuration (VarianceRatioTestParams)

Regenerated from the VarianceRatioTestParams Rust source — see the note above.

Field	Type	Description
contracts	SecurityFilter	Contracts the subscription tracks. Stocks only — the analytic silently ignores option / index trades at the on_tick entry point.
conditions	ConditionPolicy	Trade-condition admission policy applied to every print.
venues	ExchangeFilter	Exchange / venue admission policy.
bar_interval_ms	i32	Per-bar cadence in milliseconds. Defaults to [DEFAULT_BAR_INTERVAL_MS] (60_000 ms / 1 min).
lag_q	i32	Lag window q — the multi-bar horizon over which the variance ratio is fit. Defaults to [DEFAULT_LAG_Q] (4).
window_bars	i32	Rolling-window length in bars. Defaults to [DEFAULT_WINDOW_BARS] (128).
min_emit_interval_ms	i32	Minimum interval between consecutive emissions per symbol, in milliseconds. Defaults to [DEFAULT_MIN_EMIT_INTERVAL_MS] (60_000 ms). Set to 0 to publish on every sealed bar.

Example

Python

import kairos_thetadata as kt

client = kt.Client.connect(kt.Credentials.from_env())

def on_event(row):
    print(row)

sub = client.live().variance_ratio_test(["QQQ"]).on_event(on_event)
sub.wait(timeout_seconds=60.0)

TypeScript

import { Client, Credentials } from "kairos-thetadata";

const client = await Client.connect(Credentials.fromEnv());

await client
  .live()
  .varianceRatioTest(["QQQ"])
  .onEvent((tick) => {
    console.log(tick);
  });

Rust

// Cargo.toml:
//   kairos = "0.1"

use kairos::{Client, VarianceRatioTestRow};

# fn run() -> Result<(), Box<dyn std::error::Error>> {
let client = Client::connect(("me@example.com", "secret"))?;

let sub = client
    .live()
    .variance_ratio_test(["QQQ"])
    .on_event(|row: &VarianceRatioTestRow| println!("variance_ratio={} z_statistic={}", row.variance_ratio, row.z_statistic))?;
// ... later ...
sub.unsubscribe();
# Ok(())
# }