hello,

I would like to investigate whether sectors that invest relatively more in computer capital will show a larger rise in non-routine labour input and a larger decline in routine labour input. I have panel data for 12 industries over the time period 2006-2017.
My question is whether I could transform my data to cross-sectional and construct a simple linear regression where the dependent variable is a pre-calculated total change in investment in computer capital over this 11 year period, while the independent variable is a share of routine labour input in the base year 2006? Would that be correct?