Error when estimating a VAR on log data (infinite values) in Matlab

When trying to use the estimate command (https://se.mathworks.com/help/econ/varm.estimate.html) to estimate a VAR using log data. This error does not occur when i use this command on data that has not been log transformed. The specific error message i get is the following:

Error using statcheckmvnr (line 65)

One or more infinite values found in Y.

Error in mvregress (line 251)

statcheckmvnr(Data, Design, Param0, Covar0, isequal(EstMethod,3));

Error in varm/estimate (line 429)

sigma(solve,solve), logL] = mvregress(D, R, 'covtype' , 'full' , 'varformat',

'beta' , ...

Can anyone help me understand why this is happening or how to solve it? I don't see why taking logs to a dataset should result in this. The specific code that results in this is the following (not that there is much to it, as i'm simply estimating a var on a section of a dataset):

EstMdl_e = estimate(var,zest_e);

Answer 1

[Carl Kier]

I figured out that i needed to add 1 to my dataset (which consisted of growth rates) to avoid taking logs to negative numbers.