Test developers and psychometricians have historically examined measurement bias and differential item functioning (DIF) across a single categorical variable (e.g., gender), independently of other variables (e.g., race, age, etc.). This is problematic when more complex forms of measurement bias may adversely affect test responses and, ultimately,…

ETS experts are exploring and defining the standards for responsible AI use in assessments. A comprehensive framework and principles will be unveiled in the coming months. In the meantime, this document outlines the critical areas these standards will encompass, including the principles of: (1) Fairness and bias mitigation; (2) Privacy and…

In spring 2022, WestEd conducted a literature review to summarize the major frameworks used in career intentions research and the evidence supporting each framework, as well as to develop an initial set of constructs to guide the development of a brief, culturally sensitive computing career intentions survey measuring individual, situational, and…

We revisit the empirically observed positive correlation between DIF and difficulty studied by Freedle and commonly seen in tests of verbal proficiency when comparing populations of different mean latent proficiency levels. It is shown that a positive correlation between DIF and difficulty estimates is actually an expected result (absent any true…

Most assessments adopt a one-size-fits-all approach to provide fair testing opportunities to all learners. However, this rigid approach to assessment may limit the ability for some learners to show what they know and can do. The Caring Assessments framework proposed a guide for the design and development of flexible, personalized, and adaptive…

Lesbian, gay, bisexual, transgender, queer, intersex, Two-Spirit, and other sexual and gender minority (LGBTQ+) individuals encounter numerous obstacles to equity across health and healthcare, education, housing, employment, and other domains. Such barriers are even greater for LGBTQ+ individuals who are also Black, Indigenous, and People of Color…

By design, randomized experiments (XPs) rule out bias from confounded selection of participants into conditions. Quasi-experiments (QEs) are often considered second-best because they do not share this benefit. However, when results from XPs are used to generalize causal impacts, the benefit from unconfounded selection into conditions may be offset…

With the advent of big data and advances in technology, psychological assessments have become increasingly sophisticated and complex. Nevertheless, traditional psychometric issues concerning the validity, reliability, and measurement bias of such assessments remain fundamental in determining whether score inferences of human attributes are…

Validity, reliability, and fairness are three prominent indicators for evaluating the quality of assessment processes. Each of the indicators is most often written about and applied in the context of large-scale assessment. As a result, the technical properties of these indicators make them limited in both their practicality and relevance for…

The MAP® Growth™ theory of action describes key features of MAP Growth and its position in a comprehensive assessment system. The basic premise of the theory of action is that all students learn when MAP Growth is situated in a comprehensive assessment system and used for its intended purposes to yield information about student learning and enable…

Educators and researchers strive to build policies and practices on data and evidence, especially on academic achievement scores. When assessment scores are inaccurate for specific student populations or when scores are inappropriately used, even data-driven decisions will be misinformed. To maximize the impact of the research-practice-policy…

In this digital ITEMS module, Dr. Jacqueline Leighton and Dr. Blair Lehman review differences between think-aloud interviews to measure problem-solving processes and cognitive labs to measure comprehension processes. Learners are introduced to historical, theoretical, and procedural differences between these methods and how to use and analyze…

When evaluating the quality of any screening tool, it is important to determine whether or not the assessment is biased against different groups of students. We want to ensure that students do not receive higher or lower scores on an assessment for reasons other than the primary skill or trait that is being tested.

Multilingual children represent a rapidly growing population of students in U.S. schools. However, identification of language and learning disabilities for students from different linguistic backgrounds is complex, leading to frequent misidentification of multilingual learners for special education. This article provides guidance on how special…

Fairness in assessment is seen as increasingly important but there is a need for greater clarity in use of the term 'fair'. Also, fairness is perceived through a range of 'lenses' reflecting different traditions of thought. The lens used determines how fairness is seen and described. This article distinguishes different uses of 'fair' which have…