Reliability and Validity Case

Human services professionals seek to deliver the best care and services for their clients. In human services information and data is collected and analyzed to make decisions regarding the best interest of those clients through research and testing. It is imperative that the tests conducted are reliable and valid. The purpose of this paper is to define and describe validity and reliability, as well as the methods and instruments used to collect data that is most appropriate for human services researchers.

Reliability

When the word "reliable" comes to mind one may think in terms of a "reliable car" or a "reliable source," meaning that these things are dependable and trustworthy. In research reliability means "repeatability" or "consistency." Reliability is defined by Merriam-Webster's Dictionary as "the extent to which an experiment, test, or measuring procedure yields the same results on repeated trials" (2013). There are five types of reliability: alternate-form, internal-consistency, item-to-item, judge-to-judge, and test-retest reliability.

Alternate-form reliability, also known as equivalent or parallel form reliability, is basically when two versions of the same test or instrument produce similar/consistent results. An example would be giving a participant two versions of the same test, same questions only worded differently, one would expect the participant would answer both forms similarly.

Internal-consistency reliability, also called reliability of components, is comparing all measurements of the same construct or "the internal consistency of a set of items is an indicator of how well the items measure the same variable or construct' (NSSE, 2011). Cronbach's Alpha is most commonly used to measure internal consistency Trochim, 2008). An example, "an English test is divided into vocabulary, spelling, punctuation and grammar. The internal consistency reliability test provides a measure that each of these particular aptitudes is measured correctly and reliably" (Shuttleworth, 2009. p. 1).

Test-retest reliability is used to assess the consistency of a measure from one instance to another (Trochim, 2008). Meaning "the extent to which a measurement method produces the same score for the same case under the same conditions" (Prince & Oswald, 2008. para. 1). An example might be giving some people an IQ test today and then give the same test to the same people a week later, one would expect to find the results or scores to be quite similar.

Item-to-Item Reliability: The reliability of any single item on average. Judge-to-Judge Reliability: The reliability of any single judge on average (Rosnow & Rosenthal, 2008).

Validity

Validity is the extent to which a test measures what it purports to measure. "It is vital for a test to be valid in order for the results to be accurately applied and interpreted" (Cherry, 2012. para. 1).

Construct validity traditionally has been defined as the experimental demonstration that a tool (e.g., a survey, test, etc) is measuring the construct it claims to be measuring.

Content validity refers to how well a test measures the behavior for which it is intended.

Convergent and discriminant validity: The grounds established for a construct based on the convergence of related tests or behavior (convergent validity) and the distinctiveness of unrelated tests or behavior (discriminant validity) (Rosnow & Rosenthal, 2008). To establish convergent validity, one will need to show that measures that should be related are in reality related. To establish "discriminant validity, one will need to show that measures that should not be related are in reality not related" (Trochim, 2006. para. 3).

Criterion validity can ascertain whether a test reflects a certain set of abilities. It also "refers to the extent to which one measure estimates or predicts the values of another measure or quality. The first measure is often called the estimator or the predictor variable. The second measure is called the criterion variable in cases when a decision must be made or when the measure is regarded as valid" (Eaves & Woods-Groves, 2010. para. 1). An example would be giving a participant a personality test and taking the score to predict future behavior.

External validity "the degree to which the conclusions in a study would hold for other persons in other places and at other times" (Trochim, 2008. para. 2). It involves the extent to which the results of a study can be generalized (applied) beyond the sample. An example could be a study of ninth graders in a rural school found one method of teaching algebra was better than another method may not be applicable with seventh graders in an urban school.

Internal validity refers to the extent to which one can accurately state that the independent variable produced the observed effect (Trochim, 2008). "If a study has internal validity, then one can be confident that the dependent variable was caused by the independent variable and not some other variable. Thus, a study with high internal validity permits conclusions