Validity and Reliability Matrix

Reference: Cohen, R. J., & Swerdlik, M. E. (2010). Psychological testing and assessment: An introduction to tests and measurements (7th ed.). New York, NY: McGraw-Hill.

Completed by: Deanna Shelby, Shernard Robinson, & Julia Carlson for PSYCH/525

Validity and Reliability Matrix

For each of the tests of reliability and validity listed on the matrix, prepare a description of test’s application and under what conditions these types of reliability would be used as well as when it would be inappropriate.  Then prepare a description of each test’s strengths and a description of each test’s weaknesses.

 

TEST of Reliability	Application and APPROPRIATENESS	Strengths	Weaknesses
Test/retest	Test/retest administrations occur at two different times with the same test presented to the same group (Cohen & Swerdlik, 2010). The reliability of this test is assessed when querying “reaction time or perceptual judgments” (Cohen & Swerdlik, 2010, p. 144). An inappropriate administering of this test occurs when a person’s abilities skew test results (such as data retention, tiredness, repetitive simulated testing, intent) (Cohen & Swerdlik, 2010).	One of the strengths of test/retest is that this tool is able to measure over a stable period of time and gives an estimated stability to the overall picture (Cohen & Swerdlik, 2010). Researchers tend to gravitate towards this method because it refers to consistency within test scores. Scores are measured based on the 1st and 2nd attempt to look at the correlation. Researchers believe this is a strength because they are able to see factual numbers over a period of time (Cohen & Swerdlik, 2010).	Sometimes, characteristics being tested may fluctuate over time, thus rendering the test-retest reliability invalid- since it will not yield the same results on the retest aspect if the testing factor has changed (Cohen & Swerdlik, 2010). Outlying factors can also affect the retest aspect. If a factor completely changes over time, then the retest, although it may be asking the same material, may not apply anymore.
Test of Validity	Application and APPROPRIATENESS	Strengths	Weaknesses
Construct	Construct validity is an idea or variable designed to predict behavior or allow for certain findings to be made based on the test administer or questions being answered (Cohen & Swerdlik, 2010). For instance, a test predicted on the construct of affability. This particular example highlights a participants behavior in a perceived social environment as a means of explaining why a participants reacts a certain way during a particular social setting (Cohen & Swerdlik, 2010). Using this sort of test to prove a particular bias can be seen as an inappropriate approach to determining construct validity.	The test administrator is able to explain the behavior by creating a hypothesis. An example would be a student doing well in school and the construct would be smart or intelligent. Being able to label out of perception/bias can be helpful to the test administrators but also could be seen as a weakness (Cohen & Swerdlik, 2010).	The factors leading up to this test are unobservable and presupposed. Therefore, if factors in the test do not happen or behave as primarily predicted, then the test must be discarded and re-done (Cohen & Swerdlik, 2010). Also, if test takers have a different perspective on the testing information, this can also leave the test unpredictable, which would again render results invalid.