[Amani Shayo]

Well, sure. You've already done the hardest part. That is, assuming that states 6, 8, and 9 adopted the policy in 2015, states 10, and 15 did so in 2013, etc., you already have the key variable set up.

To provide more advice, you need to describe your educational outcome variable. And you also need to explain the organization of your data set: is it a panel data set with state level variables, or is it perhaps individual person-level data within states and by years? Are there any covariates ("control variables") you plan to include? Am I correct in assuming the the unit of time in your data is years? Does your data also include some or all of the states that never adopted the policy?

Sure i have described educational outcome and its in my dataset, I will use panel datset with state level variable, i will use one covariate (income). the unit of time is year sure. my data set has both adopted states and never adopted states

[Clyde Schechter]

Well, you haven't described your educational outcome here in this thread, so it's anybody's guess whether it's continuous or discrete, etc. So we make progress, let me assume it's a quasi continuous variables, like, say, proportion of entering students who complete secondary school. Anyway, all that matters here is that it be a continuous variable. I'll just call it education.

xtset state year
xtreg education i.driver income i.year, fe

The coefficient of 1.driver is your generalized DID estimate of the effect of adopting the policy on education.

If you want to use one of the new Stata DID commands, I believe you would use

xtdidregress (education income) (driver), group(statefips) time(year)