Skip to main content

New answers tagged

1 vote

Expectation of reciprocal residual sum of squares

It depends. Suppose your points fall on a lattice. There's then a (small but) non-zero probability that $r_i$ is zero, so the expectation of $1/\|r_i\|^2$ is definitely infinite. Also, for any ...
Thomas Lumley's user avatar
0 votes

Is the variance of the mean of a set of possibly dependent random variables less than the average of their respective variances?

If the $X_i$ are positively correlated, then the variance of the empirical mean is going to be bigger than in the independent case. If the $X_i$ are negatively correlated, then the variance of the ...
Guillaume Dehaene's user avatar
1 vote

How do I calculate the error on the extrapolation of a double natural log fit?

As @whuber pointed out, although I didn't understand what he meant the first few times, the model was overparameterized and that's why it wasn't returning the covariance matrix. The original equation ...
ohshitgorillas's user avatar
0 votes

Singular covariance matrix in Mahalanobis distance in Matlab

The easy (less mathematically rigorous) way to think about this is to first transform your data to principal components. If all eigenvalues are nonzero, then the Mahalanobis distance in the principal ...
Mark Nh's user avatar
  • 23

Top 50 recent answers are included