In his comment on our literature review of data on the performance of sub-Saharan Africans on Raven's Progressive Matrices, Lynn (this issue) criticized our selection of samples of primary and secondary school students. On the basis of the samples he deemed representative, Lynn concluded that the average IQ of sub-Saharan Africans stands at 67 when compared to UK norms after a correction of the Flynn Effect. We criticize his methods for being unsystematic. Here we select only those samples that were based on stratified or clustered random sampling and were deemed representative by the original authors. We again fail to replicate Lynn's low estimate of the average IQ of Africans. We argue that these scores are hard to interpret in terms of latent cognitive variables such as "g" because of the psychometric incomparability we established and because the Flynn Effect has yet to take hold in sub-Saharan Africa. (Contains 1 table.)