Overview
Michael Anderson is a researcher at the Center for the Economics and Demography of Aging (CEDA), University of California, Berkeley. His work focuses on structural time series models for stochastic Social Security forecasting, parameter uncertainty, and infinite horizon actuarial balance estimation.
Key Contributions / Features
- Stochastic trust fund forecasts (Lee, Anderson, and Tuljapurkar 2003): Co-authored fuller treatment of OASDI trust fund stochastic simulation — explicitly modeling income and cost rates as stochastic functions of demographic and economic inputs. Extended the 1998 AER P&P brief application to a complete probabilistic framework showing the SSA intermediate is below the stochastic median and fertility dominates 75-year uncertainty. See Lee Anderson and Tuljapurkar 2003 — Stochastic Forecasts of the Social Security Trust Fund, Ronald Lee, Shripad Tuljapurkar.
- Structural time series and parameter uncertainty (Lee, Miller, and Anderson 2004, Report II): Lead author examining whether structural state-space models and parameter uncertainty for wage growth and fertility substantially change OASDI solvency projections; found that while individual input probability intervals change substantially, the integrated SS solvency distribution is relatively insensitive.
- Stochastic infinite horizon SS forecasts (Lee and Anderson 2004, Report III): Co-authored 500-year stochastic projection yielding infinite horizon actuarial imbalance of −5.15% of payroll; demonstrated that the 75-year AB₇₅ is not a sustainability measure; identified the "Unstable measure" as the best 75-year approximation to the true infinite horizon central estimate.
Related
Sources