Causal-comparative research aims to determine cause-and-effect relationships by forming groups of individuals in whom an independent variable is present or absent - or present at several levels - and comparing the groups on a dependent variable. It involves comparing two or more groups that differ on some independent variable of interest without direct manipulation. Threats to internal validity include subject characteristics and other threats like mortality, instrumentation, and history. Researchers evaluate these threats and aim to control for them to strengthen causal inferences from the research.