I would like to estimate changes in GINI during 15 years. Should I make log transformation of independet varible? Raw data for some independent varibles are not normaly distributed.
If you want to build a parametric model, yes, you probably will need to transform some of your variables. You can even use a more general power transformation with optimal parameters so that the CLNR assumptions would be plausible. I think that the Gini coefficient itself can be transformed in order to ensure better statistical properties of your dependent variable.
However if you are doing regression the independent variables don't need to be normal unless you are using an errors in variables model. See Kutner et al-Applied Linear Statistical Models. Best, D. Booth
The use of a large enough sample can help to soften the need of the assumption of normality of the variable concerned. This is an application of the central limit theorem.