Linking neurobiology to relatively stable individual differences in cognition, emotion, motivation, and behavior can require large sample sizes to yield replicable results. Given the nature of between-person research, sample sizes at least in the hundreds are likely to be necessary in most neuroimaging studies of individual differences, regardless of whether they are investigating the whole brain or more focal hypotheses. However, the appropriate sample size depends on the expected effect size. Therefore, we propose four strategies to increase effect sizes in neuroimaging research, which may help to enable the detection of replicable between-person effects in samples in the hundreds rather than the thousands: (1) theoretical matching between neuroimaging tasks and behavioral constructs of interest; (2) increasing the reliability of both neural and psychological measurement; (3) individualization of measures for each participant; and (4) using multivariate approaches with cross-validation instead of univariate approaches. We discuss challenges associated with these methods and highlight strategies for improvements that will help the field to move toward a more robust and accessible neuroscience of individual differences.

The Hierarchical Taxonomy of Psychopathology (HiTOP) is an empirical, dimensional model of psychological symptoms and functioning. Its goals are to augment the use and address the limitations of traditional diagnoses, such as arbitrary thresholds of severity, within-disorder heterogeneity, and low reliability. HiTOP has made inroads to addressing these problems, but its prognostic validity is uncertain. The present study sought to test the prediction of long-term outcomes in psychotic disorders was improved when the HiTOP dimensional approach was considered along with traditional (ie, DSM) diagnoses. We analyzed data from the Suffolk County Mental Health Project (N = 316), an epidemiologic study of a first-admission psychosis cohort followed for 20 years. We compared 5 diagnostic groups (schizophrenia/schizoaffective, bipolar disorder with psychosis, major depressive disorder with psychosis, substance-induced psychosis, and other psychoses) and 5 dimensions derived from the HiTOP thought disorder spectrum (reality distortion, disorganization, inexpressivity, avolition, and functional impairment). Both nosologies predicted a significant amount of variance in most outcomes. However, except for cognitive functioning, HiTOP showed consistently greater predictive power across outcomes—it explained 1.7-fold more variance than diagnoses in psychiatric and physical health outcomes, 2.1-fold more variance in community functioning, and 3.4-fold more variance in neural responses. Even when controlling for diagnosis, HiTOP dimensions incrementally predicted almost all outcomes. These findings support a shift away from the exclusive use of categorical diagnoses and toward the incorporation of HiTOP dimensions for better prognostication and linkage with neurobiology.

Marek et al. analyzed three very large magnetic resonance imaging (MRI) datasets and concluded that thousands of participants are necessary to ensure replicable results in “brain-wide associations studies,” which they defined as “studies of the associations between common inter-individual variability in human brain structure/function and cognition or psychiatric symptomatology.” This conclusion overgeneralizes the implications of their findings and is likely to have an unwarranted chilling effect on neuroimaging research focused on individual differences, preventing good research with samples in the hundreds from being funded and conducted. To fend off these negative consequences, we explain why their conclusion is not fully justified, discuss methods that can yield larger effects, and suggest practical guidelines for sample size, recognizing the potential utility of samples in the hundreds.