Estimating installed-base effects in product adoption: Borrowing IVs from the dynamic panel data literature

Estimating installed-base effects for product adoption in the presence of unobserved heterogeneity is challenging since the typical solution of including fixed effects leads to inconsistent estimates in models with installed base. Narayanan and Nair (2013) highlight this problem and propose a bias correction method as a solution to the problem. This research note proposes an alternative solution: Borrowing IVs from the dynamic panel data literature. As lags and lagged differences of the installed base are used as instruments after first-differencing, this approach does not require external instruments and therefore has the key advantage of being easily accessible in many settings. I present Monte Carlo results to demonstrate the performance of the proposed approach.