About this question
Easy · statistical_analysis · Quant Researcher interview question · durbin_watson, autocorrelation, residuals, regression, statistical_analysis
The Durbin-Watson statistic is a standard diagnostic for first-order serial autocorrelation in regression residuals. In quantitative finance, it is crucial for validating time-series models, as autocorrelation can invalidate standard error estimates and statistical tests. A value near 2 indicates no autocorrelation, while values approaching 0 or 4 suggest positive or negative autocorrelation, respectively. Task Implement the function durbin_watson(residuals: list) -> float to compute the Durbin