Psychology Lecture 2: Reliability and Validity

Reliability refers to the test measuring one and only one thing precisely, while validity refers to the test measuring what it is supposed to measure.

Internal consistency, test-retest consistency, and inter-rater reliability.

A statistical framework that looks at all sources of error in assessments to determine reliability.

<p>Evidence from item content, evidence from process/manipulations, evidence from internal structure, evidence from relationship to other variables, and evidence from consequences of test use.</p> Signup and view all the answers

<p>Recommendations for using and interpreting test scores developed by the APA, AERA, and NCME.</p> Signup and view all the answers

<p>Foundations, Operations, and Testing Applications.</p> Signup and view all the answers

<p>Validity, reliability/precision, and fairness in testing.</p> Signup and view all the answers

<p>They represent current consensus, operational guidelines, alternative viewpoints, and psychometric models.</p> Signup and view all the answers

<p>They are currently very difficult to access.</p> Signup and view all the answers

<p>The degree to which evidence and theory support the interpretations of test scores entailed by proposed uses of tests.</p> Signup and view all the answers

<p>A rationale should be presented for each recommended interpretation and use of test scores.</p> Signup and view all the answers

<p>A test is valid for anything with which it correlates.</p> Signup and view all the answers

<p>Tripartite view: Content validity, criterion validity (concurrent &amp; predictive), and construct validity (discriminant &amp; convergent).</p> Signup and view all the answers

<p>Tripartite plus outcomes.</p> Signup and view all the answers

<p>A unitary form of validity based on evidence from multiple sources to support an argument for what test scores actually mean.</p> Signup and view all the answers

<p>Essentially unchanged from 1999, a unitary form of validity based on evidence from multiple sources.</p> Signup and view all the answers

<p>The idea of a nomological network, which is the theoretical framework about what the test should measure.</p> Signup and view all the answers

<p>There may not always be one obvious criterion variable, and various tests may be used for different purposes.</p> Signup and view all the answers

<p>An English-language reading comprehension test and the MMPI for employment selection.</p> Signup and view all the answers

<p>Test purpose and use, and characteristics of the test-takers.</p> Signup and view all the answers

<p>Cronbach &amp; Meehl (1955) and Campbell &amp; Fiske (1959).</p> Signup and view all the answers

<p>Content validity, criterion validity, and construct validity.</p> Signup and view all the answers

<p>Relevance and representativeness.</p> Signup and view all the answers

<p>Evidence should show that the test measures the intended process through various methods such as think-aloud protocols.</p> Signup and view all the answers

<p>The presence of six facets of Conscientiousness from the NEO-PI-R personality model.</p> Signup and view all the answers

<p>Convergent and discriminant evidence, and replication in different situations and for different purposes.</p> Signup and view all the answers

<p>NAPLAN test scores intended to identify progress may lead to consequences like league tables and school flight.</p> Signup and view all the answers