Journal of College & University Student Housing Volume 48, No. 1 - 65

research questions using Rasch measurement
(Bond & Fox, 2015) to determine the
quality of items that form a meaningful variable.
To our knowledge, no other study has
applied Rasch analysis to RA self-efficacy.
Rasch techniques allow us as researchers
to use item-level and instrument-level diagnostic
information to optimize the measurement
of latent constructs like self-efficacy to
differentiate levels of RA self-efficacy. Practitioners
(e.g., university and student housing
administrators, residence hall directors), on
the other hand, can use Rasch findings to inform
hiring, training, and evaluation.
Our study was guided by the following
research questions (RQs):
1. Do items that represent RA duties support
a unidimensional interpretation of the
construct?
2. If unidimensional, can the new
instrument reliably differentiate distinct
groups of RAs?
3. Do the response categories support
varying degrees of endorsement
regarding RAs' perceptions to perform
duties?
METHOD
Sample and Procedure
Participants were from a large university
in the southeastern United States. Data
were collected in fall 2018 as part of a larger
project in partnership with staff in housing
and residence life. A total of 215 RAs were
administered the measure in this study
prior to RA training, about three weeks before
fall semester started. The response rate
was 80%, with 171 RAs completing the instrument.
New RA hires (newly hired, first
semester as an RA) made up 43% and female
RAs made up 52% of the sample. The racial
and ethnic identities of the sample included
White or Caucasian at 59%; Black or African
American at 21%; Spanish, Hispanic,
or Latinx at 8%; Asian American or Pacific
Islander at 4%; Native American or Alaskan
Native at 1%; two or more races at 3%; and
undisclosed at 4%.
Resident Advisor Self-Efficacy Instrument
The Resident Advisor Self-Efficacy Instrument
(RASE) was developed after a review
of the RA job description and self-efficacy
literature and was guided by general instrument
development principles recommended
by Bandalos (2018). The research team
originally developed 33 items based on the
RA job description. RAs rated their ability to
fulfill their expected job duties on a 4-point
Likert-type response scale ranging from
1 (I cannot do this) to 4 (I can definitely do this).
Prior to finalizing the RASE, items were
subjected to expert reviews with residence
life staff to ensure that they would be interpreted
as intended. Administrators from the
host institution (n = 7) and direct supervisors
of RAs (n = 32) were sent the instrument and
corresponding job description by email. Experts
were asked to provide informal (qualitative)
feedback on the alignment of items
with the original job description and recommendations
for improving the item phrasing
(e.g., clarifying, collapsing, expanding,
or deleting items). This process resulted in
23 items that were subjected to data analysis
(see Table 1).
DATA ANALYSIS
The analysis for this study was guided by
Rasch measurement theory (Rasch, 1960)
to determine the measurement properties
and functioning of the RASE. The research
team used Winsteps 4.7.1 (Linacre, 2020)
to fit data to the Rasch rating scale model
(RSM; Andrich, 1978). This model is used
for rating scale data where each item format
is the same across the instrument. The RSM
Volume 48, No. 1 * 2021
65
Journal of College & University Student Housing Volume 48, No. 1

Table of Contents for the Digital Edition of Journal of College & University Student Housing Volume 48, No. 1
