Every analysis here ships its dataset and the code that produced every figure. Nothing on this site is investment advice.
Nelson-Siegel fitted to 11 Treasury yields on 5,171 days misses by 9.4 bp on a median day; since May 2020 the 20-year sits above a curve fitted without it daily.
average miss of the 20-year yield against a Nelson-Siegel curve fitted without it, above the curve on 1,598 of 1,598 trading days since 20 May 2020
Data and code: two CSV files and one Python script, attached to the note.
Average miss by maturity, actual minus fitted, basis points (1M and 20Y in the warm colour)
month-of-year tests survive a 5% false discovery rate, all of them in retail gasoline; 10 passed at p < 0.05 unadjusted
Sixty month-of-year tests on the Nasdaq, Treasuries, oil, gasoline and natural gas: 10 pass at p < 0.05, and a 5% false discovery rate keeps 4, all gasoline.
real change in average hourly earnings by the CPI-U, January 2021 to August 2026; +1.7% by the PCE price index
From January 2021 to August 2026, real hourly pay fell 0.8% by the CPI and rose 1.7% by the PCE price index. How to deflate, checked against the BLS, and six traps.
of the CPI-U basket is shelter in the December 2025 weights; energy is 6.4%
Shelter is 35.6% of the CPI-U basket for 2026 and energy 6.4%, yet energy supplied 38% of the index's rise from December to August. The weights, and how to use them.
mean absolute move in the 2-year yield on statement days, against 3.10 to 3.80 bp on the days either side
Rates, VIX and the Nasdaq in a five-day window around every FOMC statement since 2003, with permutation tests, a multiple-testing correction, and what survives it.
range travelled by the rolling 126-day correlation of 10-year yield changes and Nasdaq returns, from −0.529 to +0.692
Rolling 126-day correlations between the 10-year yield, equities, and the dollar, with a simulation that separates a real regime change from sampling noise.
payroll growth in 2025 by today’s vintage; the twelve first prints summed to 1,208,000
Every payroll and real GDP vintage since 2010, pulled from ALFRED without a key: how far first prints moved, the annual benchmarks, and the level trap.
| Desk | Notes | What it covers |
|---|---|---|
| Data Analysis | 9 | A question, a public dataset, the code, and the answer, with every figure reproducible. |
| Methods | 7 | Time series, risk measures, backtesting discipline, and the statistics that keep an analysis honest. |
| Data Sources | 6 | FRED, SEC EDGAR, BLS, exchange feeds: how to pull them, parse them, and not misread them. |
| LLMs in Finance | 5 | Where language models are used in financial work, what the papers and filings show, and what they get wrong. |
| Briefs | 2 | Short readings of a release, a filing, or a paper, dated and sourced. |