Estoy buscando una referencia donde se pruebe que la media armónica
minimiza (en ) la suma de los errores relativos al cuadrado
Estoy buscando una referencia donde se pruebe que la media armónica
minimiza (en ) la suma de los errores relativos al cuadrado
Respuestas:
¿Por qué necesitas una referencia? Este es un problema de cálculo simple: para que el problema, tal como lo ha formulado, tenga sentido, debemos suponer que todo . Luego defina la función f ( z ) = n ∑ i = 1 ( x i - z ) 2 Luego calcule la derivada con respecto az: f′(z)=-2⋅n ∑ i=1(1-z
En cuanto a una referencia, tal vez https://en.wikipedia.org/wiki/Fr%C3%A9chet_mean o https://en.wikipedia.org/wiki/Harmonic_mean o referencias allí.
I have renamed "" as "" (the "response") and the parameter to be estimated is instead of . The weights are . It is necessary that they all exceed . The solution is
QED.
The same analysis applies to any positive sets of weights, providing a generalization of the harmonic mean and a useful way to characterize it.
When, as in a controlled experiment, the are viewed as fixed (and not random), the machinery of weighted least squares provides confidence intervals and prediction intervals, etc. In other words, casting the problem into this setting automatically gives you a way to assess the precision of the harmonic mean.
Viewing the harmonic mean as the solution to a weighted problem provides insight into its nature and, especially, to its sensitivity to the data. It is now clear that the most important contributors are those with the smallest values of --and their importance has been quantified by the weights matrix .
Douglas C. Montgomery, Elizabeth A. Peck, and G. Geoffrey Vining, Introduction to Linear Regression Analysis. Fifth Edition. J. Wiley, 2012. Section 5.5.2.