Lecture 6 Validity Accuracy or correctness Can be very narrow. o Applied to a particular variable. Can be very broad. o Applied to an entire study or program of research. Not directly measurable. o Evaluated based on logic and reasoning. Review Construct Validity Target data: ADHD diagnosis Operational definition: Do you think that you have ADHD? Face validity Method match Internal and External Validity Internal Validity o Was it the independent variable that caused a change in the dependent variable? o Was the study conducted well? o Were alternate explanations ruled out? o Were all potential confounds eliminated? External Validity o Does this study reflect what typically happens in the world? o Do the results generalize to other situations? o Do the results generalize to all people? Generally, as one goes up, the other goes down. o Opposing eo. Statistical Validity Drawing valid conclusions based on appropriate statistical analysis. Every time you draw a conclusion, you might make a mistake. o Seeing a relationship that isnt there. o Missing a relationship that is there. How strong is the relationship (effect size)? How large is the margin of error? More thoughts on Reliability and Validity More is better o 20item scales are generally more reliable than 10item scales. o Observations at multiple different times and locations will be more reliable than a single session.