I am estimating a regression in MATLAB long hand.
I've got the standard error and coefficient, is there any quick way to get the p-value in MATLAB?
Any tips or tricks would be appreciated?
Usually p-values are from a statistical test, to check the statistical significance of the result, using t-test for example.
Related
I am trying to replicate the standard errors that Eviews calculates in linear regression models forecast. I have used the classical standard error formula, but it is not the same. After some research I found this formula:
I couldn't figure out how to replicate.
I appreciate if someone could help me.
Thanks!
I'm approaching a 4 class classification problem, it's not particularly unbalanced, no missing features a lot of observation.. It seems everything good but when I approach the classification with fitcecoc it classifies everything as part of the first class. I try. to use fitclinear and fitcsvm on one vs all decomposed data but gaining the same results. Do you have any clue about the reason of that problem ?
Here are a few recommendations:
Have you normalized your data? SVM is sensitive to the features being
from different scales.
Save the mean and std you obtain during the training and use
those values during the prediction phase for normalizing the test
samples.
Change the C value and see if that changes the results.
I hope these help.
Which numerical algorithm is used in Matlab for solving set of linear equations when we use x=A\B? for example gauss jordan or LU method etc.?
Thank you
The best one!1
The flow chart from the official documentation below shows how the algorithm is chosen for full matrices. The flow chart is a bit larger for sparse matrices.
1Hopefully this will result in the best algorithm.
I know that fitcsvm is a new command in matlab new version and in the latest document say that svmtrain will be removed. Are the two commands the same? Actually I notice that they are different in result in my recent work. Can anyone help me with this strange problem?
According to my experiments, I found that the two functions are different. fitcsvm takes the empirical distribution into consideration, the distribution is related to the number of positive samples and negatives in the default situation. However, svmtrain just take this distribution as [0.5 0.5], and one can think there's no prior knowledge.
Further, it may be with the data whether they have been standardization, to get more about this, just find the related document about SVM.
from fitcsvm:
fitcsvm and svmtrain use, among other algorithms, SMO for optimization. The software implements SMO differently between the two functions, but numerical studies show that there is sensible agreement in the results.
from Wikipedia Sequential minimal optimization:
SMO is an iterative algorithm for solving the optimization problem ...
I'm trying to do Poisson regression with overdispersed data and so I believe I should be using huber-white robust standard errors.
However, I don't see any option for that in glmfit. And from what I understand, robustfit is only for linear regression. Am I correct in this? Is there a way to do Poisson regression with robust standard errors in Matlab?