Levels of gene expression underpin organismal phenotypes(1,2), but the nature of selection that acts on gene expression and its role in adaptive evolution remain unknown(1,2). Here we assayed gene expression in rice (Oryza sativa)(3), and used phenotypic selection analysis to estimate the type and strength of selection on the levels of more than 15,000 transcripts(4,5). Variation in most transcripts appears (nearly) neutral or under very weak stabilizing selection in wet paddy conditions (with median standardized selection differentials near zero), but selection is stronger under drought conditions. Overall, more transcripts are conditionally neutral (2.83%) than are antagonistically pleiotropic(6) (0.04%), and transcripts that display lower levels of expression and stochastic noise(7-9) and higher levels of plasticity(9) are under stronger selection. Selection strength was further weakly negatively associated with levels of cis-regulation and network connectivity(9). Our multivariate analysis suggests that selection acts on the expression of photosynthesis genes(4,5), but that the efficacy of selection is genetically constrained under drought conditions(10). Drought selected for earlier flowering(11,12) and a higher expression of OsMADS18 (Os07g0605200), which encodes a MADS-box transcription factor and is a known regulator of early flowering(13)-marking this gene as a drought-escape gene(11,12). The ability to estimate selection strengths provides insights into how selection can shape molecular traits at the core of gene action. Phenotypic selection analysis is used to estimate the type and strength of selection that acts on more than 15,000 transcripts in rice (Oryza sativa), which provides insight into the adaptive evolutionary role of selection on gene expression.