Page 45 - Special Topic Session (STS) - Volume 4

STS560 Haniza Yon et al.
2. Methodology
Respondents. We administered our instrument as an online survey. A link
was sent to a sample of the target population (employees in the Malaysian
financial services industry) by bank officers through e-mail. The participants
were given a deadline by which to complete the instrument. The sample, which
was randomly selected, was composed of 211 employees (84 males and 127
females) in the Malaysian financial services industry. The respondents’
experience in the industry ranged from a few months to more than 26 years.
All participants were required to accept a data protection agreement before
participating in the survey.
Questions. The instrument called Work 4.0 which we developed, included
questions about demographic variables such as gender, ethnicity, place of
work, and working experience. In addition, a total of 36 questions were
included to measure behavioural competencies in creativity, innovation,
entrepreneurship, productivity, problem-solving, self-confidence, empathy,
emotional intelligence, and resilience. In the present context “faking” is likely
to occur when using Likert-style items; this problem cannot be resolved using
consistency scales. Therefore, we used a forced-choice (FC) approach to
combat faking (see, e.g., Brown & Bartram, 2009; Bartram & Burke, 2013,
Hontangas et al., 2015, Bartram & Tippins, 2017). FC items are best suited to
high-stakes situations with high demand characteristics, such as in personnel
selection, when applying for bank credit, or when being forced to reveal other
high stakes information – including value measurement (see, e.g., Brown &
Bartram, 2009; Hontangas et al., 2015).
IRT. We analysed our data with Winsteps (Linacre, 2019) software. We used
the one-parameter logistic model to measure psychometric and statistical
properties of our instrument, including its model fit and gender-related biases,
and to assess its construct validity. The one-parameter logistic model is a kind
of item response theory model. According to the Columbia University Mailman
School of Public Health:
The item response theory (IRT), also known as the latent response theory
refers to a family of mathematical models that attempt to explain the
relationship between latent traits (unobservable characteristic or attribute)
and their manifestations (i.e. observed outcomes, responses or
performance). They establish a link between the properties of items on an
instrument, individuals responding to these items and the underlying trait
being measured. IRT assumes that the latent construct (e.g. stress,
knowledge, attitudes) and items of a measure are organized in an
unobservable continuum. (Item Response Theory, n.d.)
For additional information about IRT, we refer the reader to van der Linden
and Hambleton (1995).
Gender Bias. IRT can be used to screen for bias for or against particular
sub-groups of respondents. Bias can occur at the item level and at the test

34 | I S I W S C 2 0 1 9