Prenatal testosterone and sexually differentiated childhood play preferences: a meta-analysis of amniotic fluid studies

Sexually differentiated behaviour appears to emerge from a complex interaction of biological and socio-cultural factors, with prenatal exposure to steroid hormones such as testosterone thought to play a key role. Due to large sex differences being present from a very early age, much research has focussed on the influence these hormones may have on play preferences during childhood. We present an overview of the literature and a random-effects meta-analysis linking amniotic testosterone with sexually differentiated play preferences (k = 9, n = 493). The overall effect size estimate was in the theory-consistent direction (i.e., with higher levels of testosterone associated with more male-typical play preferences), though not statistically significant (r = 0.082, p = 0.274). However, after three hypothesised missing studies were imputed via the trim and fill procedure, a significant correlation emerged (r = 0.166, p = 0.014). Nevertheless, one sample was observed to exert a particularly large influence on the outcome of the analysis. Notably this was the second biggest sample and related to the largest effect size estimate. Though far from conclusive, the overall findings are consistent with the idea that individual differences in prenatal testosterone within the typical range predict sexually differentiated play preferences in early life. However, these effects may be small in magnitude and appear to vary considerably across studies.