The Vital Role of Measurement Equivalence in Family Research

Abstract

The most basic building block of any research endeavor is the "construct." A construct is "an abstract idea, underlying theme, or subject matter that one wishes to measure" (Dew, 2008, p. 133). Common constructs for family scientists include relationship satisfaction, relationship status, parenting style, parenting stress, support, conflict, depression, and risk and/or resilience. Central to theoretical models is how constructs relate to each other. For example, parenting theories relate certain child constructs (e.g., School of Family Life, Brigham Young University, Provo, UT 84602 (justindyer@byu.edu).

Measures of Father Engagement for Nonresident Fathers

“…Father engagement was nonequivalent for the most part, which is in concert with prior findings of resident fathers (see Dyer, 2015). Father engagement was nonequivalent for the most part, which is in concert with prior findings of resident fathers (see Dyer, 2015).…”

“…Given this strong similarity in items, we tested for measurement equivalence across early and middle childhood groups (see Dyer, 2015). RSLs were used to determine which items should be eliminated.…”

“…Save for one additional item in the early childhood scale (rough-and-tumble play), this scale was identical across the early and middle childhood groups. Given this strong similarity in items, we tested for measurement equivalence across early and middle childhood groups (see Dyer, 2015). However, for this measurement equivalence test, we forced configural equivalence by dropping the rough-and-tumble play item from the middle childhood scale.…”

Group‐Based Trajectory Modeling of Marital Quality: A Critical Review

“…The use of this many measures makes between‐study comparisons difficult, and it is thus not possible to determine whether differences in findings across reports occur because of sampling, measurement, or other factors. Further, none of the reports reviewed here reported testing for measurement equivalence across time (see Dyer, , for more on the importance of measurement equivalence in family research). Determining that a measure is equivalent across time increases confidence that any change observed is due to true score changes and not changes in the meaning or the measurement of the construct itself (Dyer, ).…”

“…Further, none of the reports reviewed here reported testing for measurement equivalence across time (see Dyer, , for more on the importance of measurement equivalence in family research). Determining that a measure is equivalent across time increases confidence that any change observed is due to true score changes and not changes in the meaning or the measurement of the construct itself (Dyer, ). Last, increased use of GMM would allow for researchers to model trajectories using more than one measure of marital quality.…”