Latent inhibition (LI) is demonstrated when a previously unattended/inconsequential stimulus is less effective in a new learning situation than a novel stimulus. In rats and humans, LI is reduced by dopamine agonists and increased by dopamine antagonists. In addition, LI is attenuated in actively psychotic schizophrenia patients, thus conferring strong predictive validity to the animal LI preparation for schizophrenia. However, the validity of the attentional construct in the LI model of schizophrenia dysfunction depends on confirming two assumptions: that animal and human LI share a common process, and that the process is related to selective attention. Evidence to support both assumptions is presented, followed by a description of a conditioned attention theory that emphasizes the role of initial levels of attention elicited by repeated relevant and irrelevant stimuli, and the differences between these levels in schizophrenia and normal groups.