Here is a list of research papers using respy.
Bhuller, M., Eisenhauer, P. and Mendel, M. (2020). The Option Value of Education. Working Paper.
We provide a comprehensive account of the returns to education using Norwegian population panel data with nearly career-long earnings histories. We use variation induced by a mandatory schooling reform for an instrumental variables strategy as well as the validation of a full structural model. We discuss the trade-offs between the two approaches. Using the structural model, we go beyond the standard return concepts such as Mincer returns and the internal rate of return. This allows us to account for the sequential resolution of uncertainty and nonlinearities in the returns to education. Both give rise to option values as each additional year of schooling provides information about the value of different schooling choices and new opportunities become available. We are thus able to estimate the true return to education and find an important role for option values.
Contact: @peisenha, @mo2561057
Eisenhauer, P. and Suchy, R. (2020). Robust Human Capital Investment under Risk and Ambiguity. Working Paper.
We build on the prototypical life cycle model of human capital investment Keane and Wolpin (1994) and study individual decision-making under risk as well as ambiguity. Individuals fear model misspecification and seek robust decisions that work well over a whole range of models about their economic environment. We describe the individual’s decision problem as a robust Markov decision process. Our Monte Carlo analysis indicates that the empirical finding of large psychic cost of schooling is in part due to model misspecification by econometricians who only analyze individual investment decisions under risk. This changes the mechanisms driving schooling decisions and affects the ex ante evaluation of tuition policies.
Contact: @peisenha, @rafaelsuchy
Eisenhauer, P. (2019). The Approximate Solution of Finite-Horizon Discrete Choice Dynamic Programming Models: Revisiting Keane & Wolpin (1994). Journal of Applied Econometrics, 34 (1), 149-154.
The estimation of finite‐horizon discrete‐choice dynamic programming (DCDP) models is computationally expensive. This limits their realism and impedes verification and validation efforts. Keane and Wolpin (Review of Economics and Statistics, 1994, 76(4), 648–672) propose an interpolation method that ameliorates the computational burden but introduces approximation error. I describe their approach in detail, successfully recompute their original quality diagnostics, and provide some additional insights that underscore the trade‐off between computation time and the accuracy of estimation results.
Contact: @peisenha