I totally agree with you the thing is that many paper reports summary statistics and they get appropriately defined quantiles of asset volatility distribution i.e. no negative asset volatilities. Do you think in my cases it could be directly related to sample I use

here is the link R code

What do you thin about it?

Thank you a lot for explanation. I have a question. Let say I use Merton default probability and estimate asset value and asset volatility using two equations approach. And as you know in asset volatility equation we use equity volatility as an input parameter. I came up with new regression model which assumes that the annualized equity volatility of the following month can be explained by two factors by today annualized equity volatility and some other factor. However, I think my model does not make sense as I scaled my first factor using square-root-of-time rule.