EViews.com

Testing for the standard deviation different from zero doesn't make any sense. If the sample standard deviation is different from zero, then so is the true standard deviation.

For the mean, try

Is @expand() supposed to create a category for NAs?

Post the version and build date of your copy of EViews.

Following on what Gareth says, try opening the Excel file and saving it under another name and then try with the new file.

I have an ordered probit model which seems to have some numerical sensitivities. Some specifications won't run. Others run, but the results are somewhat different from what one gets in R.

Is there advice on optimization method or other choices likely to lead to the most accurate estimates?

A quick thing to try is to update your copy of EViews.

something like

If you read in foo.RData into EViews 11, the workfile is named "foo.rdata.wf1." Shouldn't it be just "foo.wf1?" Also, when R, Matlab and other programs use case sensitive variables. When EViews reads in "HBCU" and "hbcu" you are given the option to overwrite, ...

I attempted to load an RData file in 12 (beta) by file/open/EViews workfile menu then choosing Rdata in the dialog and clicking on the file I wanted. Got

EViews 11 worked fine.

Works after restarting.

and if you think that's weird...

My post only had two images, but three appeared!

Also, getting some very odd errors.
Here's my code


and here's the error message. Something seems to be mis-parsing the command.



Current beta, if it matters.

I'm being slow today


gets

It would be nice if there were a way to reference the latest object added to a spool, for purposes of naming and commenting. Right now it seems one has to keep count to reference untitled01, untitled02, etc if the spool is being loaded by a pon statement.

The drop down series menu doesn't seem to show automatically when entering a smpl if statement.