Psychometric Properties in a BPD Test

Psychometric Properties in a BPD Test BPD Diagnosis Print Psychometric Properties in a BPD Test By Kristalyn Salters-Pedneault, PhD Kristalyn Salters-Pedneault, PhD, is a clinical psychologist and associate professor of psychology at Eastern Connecticut State University. Learn about our editorial policy Kristalyn Salters-Pedneault, PhD Medically reviewed by Medically reviewed by Steven Gans, MD on July 13, 2016 Steven Gans, MD is board-certified in psychiatry and is an active supervisor, teacher, and mentor at Massachusetts General Hospital. Learn about our Medical Review Board Steven Gans, MD Updated on June 29, 2018 Tim Macpherson/Stone/Getty Images More in BPD Diagnosis Treatment Living With BPD Related Conditions The psychometric properties of a psychological test relate to the data that has been collected on the test to determine how well it measures the construct of interest. In order to develop a good psychological test, the new test is subjected to statistical analyses to ensure that it has good psychometric properties. There are two broad types of psychometric properties that a test must have in order to be considered a good measure of a particular construct: reliability and validity. Reliability as a Psychometric Property The first type of psychometric property is called reliability. This is the psychological tests ability to measure the construct of interest consistently and in a stable manner. A measure of something cannot be more valid than it is reliable. Test-Retest Reliability If the test is reliable, your results on that test should be very similar if you take the test today and again in six months. This is called test-retest reliability. For example, you take a test to determine your likelihood of having borderline personality disorder (BPD) in January, then again in July, and you should have similar results. One problem with the reliability of testing the same person twice using the same test is that the patient could remember the questions from the last time they took the test. This could have a variety of consequences. Parallel Forms for Reliability Parallel forms is another measure of reliability and designed to avoid the issues brought about by using the same exact test twice. To increase the reliability of this psychometric property, clinicians administer parallel forms of a test. In other words, two similar, not exactly the same, versions of a measure. Other Types of Reliability There are other types of reliability. Internal consistency refers to the point that all the items in the test should be measuring the same construct. Inter-rater reliability addresses the protocol to determine if multiple judges have a high degree of consensus. Validity as a Psychometric Property The second broad property that a good test has validity, which refers to how well the test accurately measures the construct of interest. The results should correspond with what the researcher stated was the focus of the study. For example, the results of a good borderline personality test should be highly related to behavior that is typical of borderline personality disorder (for example, someone with a high score on a BPD test should also have a lot of problems with emotion regulation). The two broad categories of validity are internal and external: If the study has external validity, it falls in line with previous findings on the same, or similar, topic.Internal validity is about the degree of confidence the researcher has in his own results and is based on a variety of factors, including characteristics of the sample, measures, and the research design. Face Validity Face validity refers to how valid the person taking the test thinks it is. For example, if the test taker has a bad attitude toward the test, including finding the layout confusing or the thinking the test administrator is a jerk, an otherwise valid measurement might produce an erroneous result.