Goodness of Fit (R-squared) and Trend
The least-squares fitting process produces a value – r-squared (r2) – which is the square of the residuals of the data after the fit. It says what fraction of the variance of the data is explained by the fitted trend line. It does not relate to the statistical significance of the trend line (see graph); statistical significance of the trend is determined by its t-statistic. Often, filtering a series increases r2 while making little difference to the fitted trend.
Read more about this topic: Trend Estimation
Famous quotes containing the words goodness and/or fit:
“If goodness were only a theory, it were a pity it should be lost to the world. There are a number of things, the idea of which is a clear gain to the mind. Let people, for instance, rail at friendship, genius, freedom, as long as they will—the very names of these despised qualities are better than anything else that could be substituted for them, and embalm even the most envenomed satire against them.”
—William Hazlitt (1778–1830)
“... nothing seems completely to differentiate the poor but poverty. We find no adjectives to fit them, as a whole, only those of which Want is the mother. “Miserable” covers many; “shabby” most, and I am sadly aware that, in a large majority of minds, “disagreeable” includes them all.”
—Albion Fellows Bacon (1865–1933)