Reliability and Validity in Psychological

¶ … reliability and validity in psychological testing. Why are reliability and validity important when choosing assessment instruments?

In testing, reliability is another synonym for consistency "the degree to which an instrument measures the same way each time it is used under the same condition with the same subjects" or the "repeatability" of a measurement (Colosi 1997). A test is temporally reliable if it produces the same response in two or more different instances, and shows form equivalence if it produces similar results with different versions of the test, with similar testers. A test must also be internally consistent: for example if someone answers 'yes' to a question deemed to be associated with manic depression, he or she should respond similarly to other questions designed to measure bipolarity.

However, a test can be reliable yet not necessarily valid: for example, the SAT tends to produce reliable results (it is rare for someone to raise his or her score several hundred points, and then only with additional coaching) but there are serious questions as to its validity. "Validity is the strength of our conclusions, inferences or propositions…the best available approximation to the truth or falsity of a given inference, proposition or conclusion" (Colosi 1997). The SAT does not measure creativity, for example, and it is arguable that it is invalid to use vocabulary-driven exercises on a test that is supposed to measure aptitude, rather than learned facts.

Discuss situations in which you would choose to use a Millon Clinical Multiaxial Inventory over the MMPI-2.

The MMPI-2 often used as a general assessment of personality and can be used upon non-psychologically 'ill' patients as well as the mentally ill. However, Millon is "normed entirely on clinical samples and is only intended for persons who have psychological symptoms and are being assessed for treatment and evaluation" (Psychological testing, 2009, IPT). Millon himself stated the test is "not a general personality instrument to be used for 'normal' populations or for purposes other than diagnostic screening or clinical assessments" (Psychological testing, 2009, IPT). The test is only for use with subjects who are already known to exhibit psychopathology and personality disorders. It is best to use to refine a diagnosis that is already supported by other evidence and is not suitable as an initial assessment instrument.

On the Rorschach, what is the Lambda? What does a Lambda of .80 indicate?