Using Chi-Square Tests to Assess Market Outcome Frequencies

Summary

This indicator applies a chi-square goodness-of-fit framework to historical market observations. Users can select price fields, RSI, or predefined levels, compare lagged values with chosen inequalities, and combine conditions. The observed outcomes are grouped into configurable categories such as up, down, and equal, with alternative groupings available. A population lookback controls how many observations feed the calculation.

The tool displays the resulting contingency counts, degrees of freedom, chi-square statistic, and a p-value, either calculated directly or estimated from a lookup table. This can help users examine whether outcome frequencies under selected conditions differ from an expected distribution. It is a statistical analysis aid rather than a trading system, and the document offers no worked interpretation or market study. Results depend on the chosen conditions, lookback, category definitions, and assumptions of the test; repeated condition searches and dependent time-series observations can make nominal significance misleading.

Key ideas

• Users define conditions by comparing selected price, RSI, or level series at configurable lags.
• Observed outcomes are sorted into configurable direction categories and tabulated.
• The indicator reports a chi-square statistic, degrees of freedom, and a p-value.
• The output can test frequency differences but does not itself establish predictive value or a profitable strategy.
• Interpretation must account for parameter selection and dependence among market observations.

Tags

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.