Unbiasedness and small variance are desirable properties of estimators
However, you can imagine situations where a trade-off exists between the two: one estimator may be have a small bias but a much smaller variance than another, unbiased estimator. The concept of "mean square error" estimator combines the two concepts. Let be an estimator of ?. Then the mean square error (MSE) is defined as follows: MSE( ) = E( – ?)2. Prove that MSE( ) = bias2 + var( ). (Hint: subtract and add in E( ) in E( – ?)2.)
What will be an ideal response?
Answer:
MSE ( ) = E( - E( ) + E( ) - μ)2 = E[( - E( )) + (E( ) - μ)]2
= E[( - E( ))2 + (E( ) - μ)2 + 2( - E( ))(E( ) - μ)]
Next, moving through the expectation operator results in
E[ - E( )]2 + E[E( ) - μ)]2 + 2E[( ) - E( ))( E( ) - μ)].
The first term is the variance, and the second term is the squared bias, since
E[E( ) - μ)]2 = [E( ) - μ)]2. This proves MSE ( ) = bias2 + var( ) if the last term equals zero. But
E[( - E( ))(E( ) - μ)] = E[E( ) - μ - (E( ))2 + μE( )]
= E( ) E( ) - μE( ) - (E( ))2 + μE( ) = 0.
You might also like to view...
It is estimated that in 2007, Mexico had a population of 110 million and Brazil had a population of 190 million. At the same time, Mexico's GDP was $1 trillion while Brazil's was $1.31 trillion. These data show that
A) Brazil had a healthier economy than did Mexico. B) Mexico's GDP per person was lower than was Brazil's GDP per person in 2007. C) Mexico's GDP per person was $9090 in 2007. D) Brazil's GDP per person was $5300 in 2007.
Since most banks have positive gaps and negative duration gaps, an increase in market interest rates will
A) increase bank profits and increase bank capital. B) increase bank profits and decrease bank capital. C) decrease bank profits and increase bank capital. D) decrease bank profits and decrease bank capital.