PairScanner

Demonstration frozen on 2026-09-10 at 17:28 (Switzerland). Last close used: 2026-09-09. This page’s figures do not update.

Case study · US equities

Kinder Morgan
/ Williams

Two gas-infrastructure stocks, a statistical relationship and a deviation to examine. A frozen demonstration explaining a Z-score in the entry zone.

Historical snapshot as of
Analysis: PairScanner

Correlation
0.85
Daily returns
P-value
0.0276
Test threshold: 0.05
Closing Z-score
-2.38
Window: 60 sessions
Coefficient β
0.7986
Log-price regression

Period studied : 2021-09-09 → 2026-09-09 · 1255 shared sessions

Why compare these two stocks

Kinder Morgan (KMI) and Williams (WMB) operate natural gas transportation infrastructure in the United States. Their shared sector motivates a comparison, without making their businesses identical or guaranteeing that their share prices will move together.

Compare the paths from the same starting point

Both series start at 100 on the first shared date. A level of 120 represents a 20% increase from that starting point, calculated from closing prices adjusted for dividends and splits. The chart compares changes, not dollar prices.

Price paths normalized to 100
KMI · Kinder MorganWMB · Williams
0.0100.0200.0300.0400.0500.0Price paths normalized to 100Shared dates and starting point. Both curves use the full period shown.
2021-09-092024-03-082026-09-09
Shared dates and starting point. Both curves use the full period shown.

Daily return correlation is 0.85. It describes how day-to-day changes have moved together. It does not establish whether the gap between the two assets returns to a lasting equilibrium.

Test the stability of the relationship

PairScanner estimates β by regression, then constructs the spread S = ln(KMI) − β × ln(WMB). The Engle-Granger test uses log prices. Its null hypothesis is no cointegration; a p-value below 0.05 rejects that hypothesis at the selected level.

Spread centered on its historical mean
Mean
-0.20-0.100.000.100.20Spread centered on its historical meanThe full-period mean is subtracted to place the reference at zero. This retrospective view is not a trading simulation.
2021-09-092024-03-082026-09-09
The full-period mean is subtracted to place the reference at zero. This retrospective view is not a trading simulation.

Here, p = 0.0276. The threshold is met; this ensures neither persistence of the relationship nor a successful trade.

How to read the hedge coefficient

β is 0.7986: it weights WMB’s log price in the spread. It is not directly a number of shares; translating it into quantities also requires prices and the capital allocated.

Locate the gap at the last close

The Z-score measures the spread’s distance from its rolling mean in standard deviations over 60 sessions. Dashed lines at ±2 are reference levels. Z can still be calculated when the cointegration test is inconclusive.

Spread Z-score and reference levels
Reference levels ±2Latest Z: -2.38
-4.0-2.00.02.04.0Spread Z-score and reference levelsThe window includes the observed session. Initial sessions without a complete window are not plotted.Latest Z: -2.38
2021-09-092024-03-082026-09-09
The window includes the observed session. Initial sessions without a complete window are not plotted.

At the study date, Z = -2.38, beyond one of the ±2 reference levels. A large deviation does not validate a mean-reversion hypothesis on its own.

Investigate possible reasons for the spread

In a stock pair’s detail view, PairScanner automatically retrieves recent SEC filings and measures the number of articles recorded for each stock. This context helps investigate company-specific events behind a deviation; it does not establish its cause.

SEC forms (including 8-K and 10-Q) appear with their date and a link to the official document. Some filings also have a summary when available. Article counts come from the provider’s monitored feed, not the entire press.

Context captured on 2026-09-10. It may include information published after the close used for Z. No announcement is identified here as the definite cause of the spread.

KMI · Kinder Morgan

Article flow

13 articles recorded from 2026-09-08 up to this capture.

Provider reference: 4.5 articles per day on average over 28 days, excluding the recent window.

Recent SEC filings

WMB · Williams

Article flow

18 articles recorded from 2026-09-08 up to this capture.

Provider reference: 3.7 articles per day on average over 28 days, excluding the recent window.

Recent SEC filings

The recent window targets roughly 48 hours; its start is a calendar date on the provider’s side. Capped counts are shown with ≥. No press article headline or text is reproduced.

Examine the timeline of filings, any change in news activity, then read the official documents. More articles predict neither price direction nor a return to the mean.

Scope and limits of this reading

Data
Adjusted closing prices used by PairScanner. Shared dates only; missing, non-finite and non-positive observations are excluded. Last observation: 2026-09-09.
Estimation
β and the cointegration test use all 1255 observations in this study. Charts are descriptive and retrospective: β was not known in advance for each session shown.
Out of sample
Software criteria met. A separate β is estimated only on the first 70% (2021-09-09 → 2025-03-10), then frozen. The ADF test uses the spread over the following period (2025-03-11 → 2026-09-09): p = 0.0439, against a threshold of 0.05. Half-life is 48.22 sessions, against a limit of 60. It is estimated over the entire history with this frozen β, not just the test period. This single chronological check is not a profitability backtest.
Multiple testing
The displayed p-value belongs to this individual test. It is not a q-value adjusted across all scanner pairs. A p-value is not the probability of a profitable trade.
Case selection
The pair was selected after reviewing the latest available scan to illustrate two stocks with a validated relationship and a Z-score in the entry zone. The scan matrix’s five-year history is retained. This retrospective choice, separate from the pair of the day, is not a test of a strategy’s performance.
Execution
This demonstration simulates no order, profit or costs. Any potential transaction would require checking both companies’ earnings and announcements, liquidity, availability and cost of borrowing the shorted stock, financing and dividends. The relationship can still break down.

What this example helps you understand

Correlation describes daily changes, cointegration tests a relationship between price levels, and the Z-score locates a deviation. These three readings complement each other. This is a dated study: the application’s figures can change after subsequent closes.

This educational study is independent of the pair of the day, which is selected for its trading relevance.

Another result, the same method

MBB / SPMB complements this reading with two ETFs tracking the same benchmark. Compare the tests, spread and out-of-sample validation at a fixed date.

Read the MBB / SPMB study →

Explore the scanner’s pairs

Find updated analyses and results in PairScanner.

Open PairScanner

Historical results do not determine future outcomes. This study is not an investment recommendation.