Dear Stata users,

I am conducting my research about CHINESE FDI IN AFRICA, my main purpose of the study is: Does Chinese FDI bring some technological spillover into African countries? thus my data consist of N=32 African countries in a period of time t=14 years. My 1st dependant variable is y1=TFP (Total Factor Productivity) change of each country, and the main independent variables are x1= Chinese FDI stock, x2= technological difference, x3=human capital, and some control variable as x4=resource rent by an African country, x5=industries output / GDP, x6= economic openness.

First, I executed UNIT ROOT TEST to all my variables using the LLC test and found that x3 and x2 are non-stationary, both are the key independent variables ( I also run the HT test and get the same result). so I am asking how to conduct the COINTEGRATION test for this issue, I used the KAO test and use my y1 as the dependant variable and both x2 and x3 as the independent variable, the KAO test result shows that both variables are cointegrated with my y1 dependant variable.

So my question is, after the UNIT ROOT TEST, y1 is stationary and only x3 and x2 are not, so is it right to include y1 in my KAO test? otherwise how I am supposed to deal with my two non-stationary key independent variables?

Thank you very much.