WTI Crude Oil Prices: Daily (DCOILWTICO) – FRED St. Louis Fed (Daily)

Rows: 10,533
Columns: 2

Daily West Texas Intermediate (WTI) crude oil spot price in USD per barrel, sourced from the U.S. EIA. Covers from January 1986 to present. One of the most widely used benchmark crude oil price series.

AI analysis

Dataset Analysis: WTI Crude Oil Prices (DCOILWTICO)

1. Dataset Overview & Analytical Value This dataset captures the daily West Texas Intermediate (WTI) crude oil spot price in USD per barrel, sourced directly from the U.S. Energy Information Administration (EIA) via the Federal Reserve Bank of St. Louis FRED API (https://fred.stlouisfed.org/graph/fredgraph.csv?id=DCOILWTICO). The FRED provenance is significant — it signals institutional reliability, regular automated updates, and alignment with other macroeconomic series published on the same platform, making cross-dataset joins straightforward. Spanning from January 1986 to the present across 10,533 daily observations, this series covers nearly four decades of energy market history, including every major oil shock, geopolitical disruption, and demand cycle in the modern era. Its value for correlation studies is exceptionally high: WTI is a globally recognized benchmark that acts as both a leading and lagging indicator across dozens of economic and financial domains.

2. Data Quality Observations Overall data quality is good but not pristine. The most notable issue is 370 null values in the DCOILWTICO price column (3.5% of all rows), which represents the entirety of the dataset's null burden — the Date column is perfectly complete with zero nulls and 10,533 distinct values, confirming no duplicate dates exist. The price nulls are almost certainly attributable to weekend and federal holiday non-trading days, a well-known structural characteristic of commodity spot price series rather than a data collection failure. However, this should be verified before analysis: if nulls cluster exclusively on weekends and holidays, they can be safely forward-filled or dropped depending on the use case. If any nulls fall on weekdays, those would warrant deeper investigation. Duplicate row counts are flagged as pending recomputation, but the 1:1 ratio of total rows to distinct dates strongly implies zero duplicates. One critical anomaly stands out: the recorded minimum price of -$36.98, which almost certainly corresponds to the extraordinary April 20, 2020 event when WTI futures briefly traded negative due to storage capacity exhaustion during the COVID-19 demand collapse — a real event, not a data error, but one that requires careful handling in any statistical model.

3. Distribution & Key Statistics The price distribution reveals a right-skewed, multi-modal series (skewness = 0.566) consistent with a commodity that spends long periods at moderate levels punctuated by sharp upward spikes. The mean of $48.37/barrel sits meaningfully above the median of $43.11, confirming the rightward pull of high-price episodes. The interquartile range — Q1 at $20.34 to Q3 at $71.37 — spans $51, suggesting substantial long-run volatility. The full range from -$36.98 to $145.31 (the latter likely the 2008 peak near $147) captures two of the most extreme price events in oil market history on opposite ends of the spectrum. With 5,644 distinct price values across ~10,163 non-null observations, the data is effectively continuous with very little rounding, supporting fine-grained time-series modeling. The standard deviation of $29.54 relative to a mean of ~$48 implies a coefficient of variation near 61%, underscoring that oil price volatility is structurally high and any correlation partner dataset must be able to accommodate or model that volatility appropriately.

4. Recommended Join Key The Date column is the unambiguous join key — it is complete (0 nulls), fully unique (10,533 distinct values matching total row count), and typed as a proper Date field. For joining to other daily financial or economic datasets, a direct date match will work cleanly. However, analysts should be aware of the trading-day/calendar-day mismatch: datasets recorded on all calendar days (e.g., weather, shipping) will produce non-matching rows on weekends, while datasets recorded on business days (e.g., stock prices, FX rates) will align more naturally. For lower-frequency datasets (weekly, monthly), the Date column can be aggregated using period-end, period-average, or period-open conventions — monthly averages are particularly recommended when joining to macroeconomic indicators that report at monthly frequency.

5. Recommended Correlation Partner Datasets Several dataset categories would pair powerfully with this series. Energy & commodities: natural gas prices (Henry Hub, also on FRED), gasoline retail prices, heating oil, and Brent crude would reveal spread dynamics and regional divergences. Macroeconomic indicators: U.S. CPI (especially energy sub-components), GDP growth, and industrial production indices would test oil's role as an economic driver vs. laggard. Financial markets: S&P 500 or energy sector ETFs (XLE), the U.S. Dollar Index (DXY — oil is dollar-denominated, so USD strength typically inversely correlates), and 10-year Treasury yields would illuminate monetary and risk-sentiment relationships. Geopolitical & supply-side data: OPEC production volumes, U.S. crude inventory levels (EIA Weekly Petroleum Status Report), and Baker Hughes rig counts are structural supply-side variables with well-documented lagged relationships to WTI. Alternative/demand-side proxies: airline passenger volumes, freight indices (Baltic Dry Index), and U.S. vehicle miles traveled would capture demand-side correlation channels. All of these have date-indexed time series available at daily or monthly frequency, making join execution straightforward against this dataset's clean Date key.

Columns

Date (date)
DCOILWTICO (decimal)