ABSTRACT
Quantitative Critical Race Theory (QuantCrit) is a burgeoning field of study seeking to challenge and improve the use of statistical data in social research. It pulls lessons and insights from Critical Race Theory and applies them to understanding social challenges. In this paper, we aim to improve the quality of quantitative research produced by showing examples of how pioneers in this field are effectively enacting QuantCrit. We conducted a systematic review of the literature to include all empirical education studies published since 2010 through 2022. Twenty-seven studies fit the criteria. Our data shows there is room for innovation, experimentation, and exploration. However, the study highlights exemplars of authors who embody QuantCrit principles through their professional and personal positionality statements, cognizance of community, robust racial/ethnic categories, intentionality on not centering whiteness, use of atypical methods, new measurement tools centering Black and Brown students, and innovative interpretations of findings.
Disclosure statement
No potential conflict of interest was reported by the author(s).
Notes
1. T-tests and Chi-squared tests are entry-level methods of statistical analysis commonly found in undergraduate level statistics coursework. They are two methods of determining difference and independence, respectively, which are foundational concepts used in quantitative research. They allow a quant researcher to ‘compare and contrast’ their data.
2. Ordinary Least Squares, or ‘OLS’, is another method of statistical analysis which is generally the capstone topic of a first semester undergraduate statistics class. It is a method that builds upon techniques from t-tests and Chi-squared tests to demonstrate relationships and storytelling within a set of data. ‘OLS’ is often preceded by ‘simple’ to connote its more introductory level of analysis.
3. More information about the above ‘basic’ statistical concepts can be found with DATAtab’s channel on Youtube. They offer clear explanations on a wide variety of quantitative analysis topics.
4. Causal methods, such as Randomized Controlled Trials (RCTs) or quasi-experimental designs, are design frameworks for using the above methods. They are to analysis what a blueprint is to an architect. The basic methods of OLS and t-test, etc, are akin to the construction tools.
5. Logistic regression a type of regression analysis that is used when the dependent variable of interest is a binary variable, and its advantage over OLS regression is that of a ‘better-fit’, or a more precise model for binary variables (e.g. 0,1).
6. A binary variable is a variable that takes one of two values. Survey questions that ask True/False or Yes/No questions are examples of binary variables.
7. A Likert scale ranges from one to five, or sometimes seven, in increments of one. They are commonly used in surveys that ask respondents to agree/disagree with one being ‘Highly Agree’ and five (or seven) being ‘Highly Disagree’.
8. Logistic regressions are like Ordinary Least Squares regressions, albeit with slightly different math behind-the-scenes. They are generally inaccessible to a reader without a background in undergraduate level statistics coursework.