The Estimation of Age/Earnings Profiles in Wrongful Death and Injury Cases: Author's Reply
针对Bryan和Linke对年龄/收入曲线估计方法的质疑，作者指出其发现的不一致可通过引入年龄/教育交互变量修正，并讨论了两种估计方法的差异与误解来源。
William Bryan and Charles Linke [1] have questioned the methodological approach of estimating age/earnings profiles outlined in our earlier article [2]. Bryan and Linke (B-L) have correctly indentified an inconsistency between the reported identical growth rates in earnings over time of a college educated salesman (SEARNI) and his high school counterpart (SEARN),' as reported in Table 2 of our article, and that derived from the 1980 Census data reported in B-L Table 1. This inconsistency mistakenly leads them to conclude that our approach of estimating age/earnings profiles is seriously flawed. We feel, however, that this inconsistency can easily be corrected using age/education interactive variables, and we therefore do not concur with their assessment of our approach. We discuss the incorporation of the interactive variables introduced to capture the impact of education on the age-education-occupation life cycle of workers' earnings. A general discussion of the two approaches used to estimate earnings growth rates follows. We then address some of the fundamental sources of the misunderstandings between our approach and that outlined in B-L.