Redistributive effects of different pension systems when longevity varies by socioeconomic status

Abstract

We propose a general analytical framework to model the redistributive features of alternative pension systems when individuals face ex ante differences in mortality. Differences in life expectancy between high and low socioeconomic groups are often large and have widened recently in many countries. Such longevity gaps affect the actuarial fairness and progressivity of public pension systems. However, behavioral responses to longevity and policy complicate analysis of possible reforms. Here we consider how various pension systems would perform in an OLG setting with heterogeneous longevity and ability. We evaluate redistributive effects of three Notional Defined Contribution plans and three Defined Benefit plans, calibrated on the US case. Compared to a benchmark non-redistributive plan that accounts for differences in mortality, US Social Security reduces regressivity from longevity differences, but would require group-specific life tables to achieve progressivity. Moreover, without separate life tables, despite apparent accounting gains, lower income groups would suffer welfare losses and higher income groups would enjoy welfare gains through indirect effects of pension systems on labor supply.

Keywords: E24; H55; Human capital; Inequality; J10; J18; Life cycle; Longevity; Pension; Progressivity.

Figure 1:

Stylized evolution of the relative value of a dollar contributed to the pension system at age x for an individual who plans to retire at age R_i, P_i(t). Case: when $\tilde{\text{r}}$ = r.

Figure 2:

Internal rate of return of each pension system by income quintile (in percentage). US males, with mortality regime of birth cohorts 1930 (Panel a) and 1960 (Panel b) Notes: Horizontal lines depict the internal rate of return of the NDC-III system. The numbers at the bottom of each column report the internal rate of return for each income quintile group.

Figure 3:

Relative value of investing an additional dollar in the pension system, ${\overline{\mathcal{P}}}_i(x),$ from age 30 to 55 by income quintile relative to NDC-III. US males, with mortality regime of birth cohorts 1930 (Panel a) and 1960 (Panel b)

Figure 4:

Effects of each pension system and mortality regime on human capital and Social Security wealth by income quintile (measured in percentage change with respect to the results in the NDC-III system). US males, mortality regimes of birth cohorts 1930 (Panel a) and 1960 (Panel b). Notes: Bars are plotted in ‘stacked’ format. When bars have opposite signs, lifetime wealth is the difference between both bars. When bars have similar signs, lifetime wealth equals the height of the two bars.

Figure 5:

Impact of each pension system on welfare by income quintile (relative to the NDC-III system). US males, with mortality regime of birth cohorts 1930 (Panel a) and 1960 (Panel b).