Measuring aggression in older adults: a latent variable modeling approach

This cross-sectional measurement study demonstrates a technique for combining information from several aggression scales into one aggression score using latent variable modeling. Participants included male patients (n = 49) with a DSM-IV diagnosis of dementia at The Veterans Affairs Medical Center Outpatient Geriatric Psychiatry Clinic. Data from seven aggression scales were used to indicate the latent aggression variable. Results provided evidence that a unidimensional latent variable model of aggression adequately represented the data. Reliability of the aggression latent variable was estimated as 0.90, whereas reliability of the separate scales estimated with this sample were less than 0.84. Our findings suggest that combining multiple scales into one aggression score using latent variable modeling results in comprehensive and reliable aggression scores that offer researchers several advantages over current methods for measuring aggression.