Natural Gas Monthly Prices
- Rows
- 358
- Columns
- 2
- Data range
- 1997-01-01 to 2026-10-01
- Auto-refresh
- Re-checks its source every 14 days
- Last refreshed with new data
- 2026-11-08
Monthly Henry Hub natural gas spot prices in USD per MMBtu. Time-series from EIA.
AI analysis
Natural Gas Monthly Prices — Dataset Analysis
1. Dataset Overview & Value for Correlation Studies This dataset captures the Henry Hub natural gas spot price — the primary pricing benchmark for U.S. natural gas markets — on a monthly basis from January 1997 through May 2026, yielding 353 observations spanning nearly three decades. Sourced from the U.S. Energy Information Administration (EIA) via [datahub.io/core/natural-gas](https://datahub.io/core/natural-gas/r/-/data/monthly-processed.csv), a well-regarded open data aggregator, the series is both authoritative and current. The EIA origin ensures methodological consistency over time, making this dataset particularly well-suited for longitudinal economic and energy correlation studies. Its long time horizon captures multiple commodity supercycles, recessionary periods, and structural energy market shifts, offering rich signal for analysts.
2. Data Quality Observations Data quality is exceptionally clean for a time-series of this length. The dataset reports zero null cells across both columns, meaning no missing months disrupt the temporal continuity — a common pain point in commodity price data. With 353 rows and 353 distinct Date values, there are no duplicate records, confirming a well-formed monthly index. The Price column yields 260 distinct values out of 353 rows, which is expected and healthy for a continuous decimal measure (repeated price levels at this granularity are plausible and not a quality concern). No type-mismatch issues are indicated. The only caveat worth noting is that 10 statistical outliers have been flagged in the Price column, which warrants attention before any regression or correlation modeling.
3. Key Column Distributions The Price column tells a compelling story through its statistics. The mean of $4.10/MMBtu sits notably above the median of $3.43/MMBtu, and the distribution carries a positive skew of 1.55 — together these signal a right-tailed distribution driven by episodic price spikes rather than a symmetric market. The interquartile range runs from $2.61 (Q1) to $5.16 (Q3), reflecting a relatively compressed "normal" trading band, while the range from the minimum of $1.49 to the maximum of $13.42 captures extreme stress events (likely the 2005–2008 commodity boom and the 2022 post-invasion energy shock). The 10 flagged outliers almost certainly correspond to these high-price episodes and should be handled carefully — retained for event-study analysis but potentially winsorized for general correlation work to avoid distortion.
4. Recommended Join Key for Cross-Dataset Correlation The Date column is the natural and only join key, and it is ideal: fully populated (nulls=0), perfectly distinct (353 unique values = 353 rows), and formatted as a standard ISO timestamp (YYYY-MM-01T00:00:00). Monthly granularity is a practical sweet spot — fine enough to detect seasonal and cyclical patterns, yet coarse enough to align with most macroeconomic and energy datasets published at monthly or quarterly intervals. When joining, analysts should standardize partner datasets to the first-of-month convention used here and confirm calendar alignment before merging, particularly for datasets that use end-of-month dating.
5. Suggested Datasets for Correlation Analysis Several dataset categories would pair powerfully with this series. Crude oil prices (WTI or Brent monthly spot prices) are the most natural partner — gas-oil price ratios are a fundamental market indicator, and decoupling events carry significant analytical value. U.S. heating and cooling degree days (NOAA climate data) would illuminate the demand-side weather relationship driving seasonal price swings. U.S. electricity generation mix data (also from EIA) could reveal how gas prices influence the coal-to-gas switching dynamic in power markets. On the macroeconomic side, CPI/PPI indices, industrial production figures, and U.S. GDP growth rates (BLS/BEA) would help disentangle demand-driven from supply-driven price movements. Finally, LNG export volume data post-2016 would be highly relevant for studying how U.S. export capacity has increasingly linked domestic Henry Hub prices to global energy markets.
Columns
- Date (date)
- Price (decimal)