Validation of The Mathematical Modeling Attitude Scale For Malaysian Mathematics Teachers 11375
Validation of The Mathematical Modeling Attitude Scale For Malaysian Mathematics Teachers 11375
Validation of The Mathematical Modeling Attitude Scale For Malaysian Mathematics Teachers 11375
ISSN:1305-8223 (online)
OPEN ACCESS Research Paper https://doi.org/10.29333/ejmste/11375
3 Department of Mathematics and Science Education, Faculty Education, Universiti Malaya, 50603, Kuala Lumpur, MALAYSIA
Abstract
This work sets out to examine the validity and reliability of the Mathematical Modeling Attitude
Scale (MMAS), a instrument measuring teachers’ attitude towards mathematical modeling. A
cross-sectional survey research was utilised to describe the validity and reliability of the MMAS.
The population of the present study focused on Malaysian mathematics teacher in primary and
secondary schools (N = 171) and this was achieved using convenience sampling. Exploratory
factor analysis (EFA), confirmatory factor analysis (CFA) and Rasch analysis were utilised in
analysing the data in the present work. EFA revealed that the data from the teachers had a four-
factor structure: constructivism, relevance and real-life, understanding and motivation and
interest. The CFA confirmed that the model fit indices established the four-factor structure of the
first- and second-order model. Although the Rasch analysis generally supported the finding of
EFA and CFA, there was still room for improvement in terms of the rating scale and DIF criterion.
Keywords: attitude, exploratory factor analysis, confirmatory factor analysis, mathematical
modeling, Rasch analysis
abilities and encouraging team project among classmates knowledge in terms of validating the teachers’
when tackling mathematical issues (Hamed et al., 2008). mathematical modeling attitude for the Malaysian
Mathematical modeling approach is seen to be settings. Extant literature proves that a comparative
appropriate to enhance attitudes toward mathematics study towards mathematical modeling attitude scale is
since it involves group activity, the application of real- generally an accepted measure for attitude towards
world situations, a deeper learning experience, and an mathematical modeling. However, content, internal
iterative procedure. A favourable attitude toward structure, and correlation among sub-construct of
mathematics may be created when teaching mathematical modeling attitude scale are important
mathematical applications (Kasmin et al., 2019) and this factors to consider in EFA and CFA. The current
can be done via gamification (Ali et al., 2019). However, investigation focuses on the mathematical modeling
many mathematics and science teachers hold a weak attitude scale using EFA, CFA and employing Rasch
attitude (Tajudin & Abdullah, 2018) and do not believe measurement model to validate in order to identify
modelling is an excellent way to learn mathematics, and deviant response such as person-fit statistics and item-fit
many frequently doubt their own mathematical statistics (Widhiarso & Sumintono, 2016), person
modelling abilities (Albarracín & Gorgorió, 2020). response and instrument quality (Bond & Fox, 2015) and
Hence, it is worthwhile to investigate and establish an also focusing only on item-fit statistics (high
instrument of teachers’ attitudes regarding interrelation among items). As a result, this work sets out
mathematical modelling. to examine the validity and reliability of mathematical
However, the use of instrument of teachers’ attitudes modeling attitude scale (MMAS), an instrument
regarding mathematical modelling is limited. Given the measuring teachers’ attitude towards mathematical
significance of mathematical modelling and its impact modeling adopted from Asempapa and Brooks (2020).
on teachers’ attitude, it is critical to comprehend how to One potential issue that may occur while adopting
apply the most suitable valid instrument. We follow the mathematical modelling attitude is the disparity
idea of Asempapa and Brooks (2020) to measure teacher between urban and rural areas. As a result, the current
attitude mathematical modeling including sub- study was conducted to examine variations in teachers’
dimensions of constructivism, understanding, relevance attitudes towards using mathematical modelling
and real-life and motivation and interest. As many between urban and rural instructors. The current study
scholars routinely adopt measures from one cultural would focus on answering the following research
context to another, numerous scholars provide proof on questions:
reliability and validity challenges. In order to implement 1. Could the mathematical modeling attitude scale
a mathematical modeling attitude scale in Malaysian be successfully adapted in the Malaysian context?
settings, a validated, culturally tailored test in Malaysia 2. Is the Malaysian version of mathematical
is required to measure teachers’ attitude towards modeling attitude scale valid and reliable?
mathematical modeling. Moreover, studies beyond the
United States (US) are needed to confirm and test the LITERATURE REVIEW
instrument, as well as its applicability to teachers in
other countries. On the basis of tests that were skewed Mathematical Modeling
due to cultural background, broad findings of
questionable validity were obtained. As stated by Clarke The goal of mathematical modelling is to show
(2013), a range of cultural roots are becoming more students that the mathematics they are learning can be
apparent. applied to real-world situations. Mathematizing real-
world events and developing mathematical models to
Most of the previous studies focus on using
represent the phenomena investigated are both part of
exploratory factor analysis (EFA) and confirmatory
mathematical modelling (Albarracín, 2021). In
factor analysis (CFA) to examine evidence on validity
Mathematics education, mathematical modelling refers
and reliability problems across cultural background.
to the development of activities in a classroom setting in
Since the current research employs Rasch modeling
which learners are active in the search for answers to
analysis, it will generate new insight to the body of
real-world issues using mathematical understanding
2 / 16
EURASIA J Math Sci and Tech Ed
(Araújo & Lima, 2020). Mathematical modelling is often concept of the term attitude, it generally refers to a
concerned with utilising mathematics to analyse, predisposition or tendency to respond to some object,
explain, and comprehend things outside of the situation, concept, or other person (Aiken, 1970). As
mathematical realm (Leung, 2019). As it incorporates the stated by Mcleod (1992), attitude refers to affective
feature of practising mathematics, mathematical responses including positive or negative feelings with
modelling provides a deeper learning experience for the moderate intensity and reasonable stability. Examples of
student (Burkhardt, 2006). However, mathematical attitudes towards mathematics include liking geometry,
modelling procedure is typically seen as a group activity. disliking word problems, and being bored with algebra.
A diverse group of students develops comprehensive However, further definitions of attitudes have been
mathematising skills through the modelling cycle. Every established by current investigators. Attitude is also
learning activity begins with a whole-group defined as the evaluative process of emotions aroused by
conversation to exchange ideas, followed by an the situation, emotions related to the stimulus, expected
individual or small-group exercise, and concluded with consequences, and linking the situation with personal
a whole-group conversation of the analysis (Cobb & values (Hannula, 2002). In addition, to understand the
Gravemeijer, 2008). concept of attitude, the latest model suggests three main
The essence of mathematical modelling is problem dimensions: emotional disposition towards
discovery before problem solving (Pollak, 2011). As a mathematics, mathematical views, and perception of
procedure, mathematical modelling employs sharable, competence in mathematics (Di Martino, 2016).
changeable, and reusable conceptual tools to describe, In line with the conception of attitude mentioned
predict, and regulate real-world circumstances (Doerr et above, Di Martino and Zan (2001) distinguish two
al., 2014), which are iterative procedures (Asempapa & important typologies for the definition of attitudes. First,
Brooks, 2020). Models are interpreted, defined, clarified, the definition of a ‘moderate’ attitude describes it as a
justified, ignored, or modified by learners (English, positive or negative level of feeling related to a particular
2003). Mathematical modeling is an external subject. For example, according to this view, attitudes
representation of the modeling process (Sahin et al., towards mathematical modeling may refer to only
2019). In short, modeling competency refers to the positive or negative emotional tendencies towards
modeling process itself (Blum et al., 2007; Maaß, 2006). modeling involving emotions, associations,
Blum and Leiß (2007) provided the complex definition of expectations, and values. Unfortunately, this type of
mathematical modeling starting from constructing, definition ignores the cognitive component in attitude
simplifying, mathematising, working mathematically, (Hannula, 2002). Second, this concept is closely related
interpreting, validating and exposing. As stated by to other elements that influence the existence of
Maaβ (2006), making assumptions, recognising attitudes. Attitudes according to this typology are
quantities, constructing relationships, and searching for defined as three closely interrelated components in
accessible information are all ways to comprehend the attitudes; emotional responses, beliefs about the subject,
real situation and build a model based on reality. To behavior toward the subject.
create a mathematical model based on the real model, However, in order to capture teachers’ attitudes
students need to mathematize, simplify important about mathematical modelling scale (MMAS), the idea of
values, and select acceptable mathematical equations. Asempapa (2018), and Asempapa and Brooks (2020)
Next, to address mathematical questions within the were employed. Asempapa (2018) defined teachers’
framework of this mathematical model, this enables the attitude towards modeling practices in classroom as a
students to employ heuristic techniques and beneficial influence linked to mathematical modeling
mathematical understanding. At the same time, they are instructions. At the same time, mathematical modelling
also allowed to properly comprehend mathematical can assist in the formation or reinforcement of beliefs
results, generalise solutions, and evaluate solutions. about the value and concreteness of mathematics (Di
Finally, for the validation stage, they are required to to Martino, 2019). Furthermore, mathematical modelling
critically examine and reflect, to evaluate certain aspects can be used to inspire students to complete curriculum
of the model, to consider other approaches, and to requirements and to emphasise the value and relevance
generally challenge the model. of mathematics in resolving significant topics. In brief,
mathematical modeling is one of the ways to offer
Mathematical Modeling Attitude Scale (MMAS) student making connection mathematics with other
Leading researchers have provided many fields and to work professionally with mathematical
conceptions for attitudes available in the current modelling. In the current research we followed the idea
literature (Aiken, 1970; Di Martino & Zan, 2001; of Asempapa and Brooks (2020) involving sub-
Hannula, 2002). They are more likely to consider the dimensions of constructivism, understanding, relevance
appropriateness of the definition than its truth: the and real-life and motivation and interest.
adequacy of the definition depends on the issues studied Constructivism and understanding refer to cognitive
(Di Martino, 2016). Although there is no standard components in the teaching of mathematical modelling.
3 / 16
Hidayat et al. / Mathematical Modeling Attitude
4 / 16
EURASIA J Math Sci and Tech Ed
improved the credibility of research results in a number of items, threshold order for all items and the
of different ways. EFA was used in the first step of the assumption of local independence in item. To ensure its
empirical method to explore the pattern and construct validity, there are some fit statistics to
interconnections of the items using IBM SPSS Statistics consider: (a) the value of accepted infit and outfit mean
Version 23.0. EFA is employed to investigate correlations square (MNSQ): .5 <MNSQ <1,5 (b) the value of accepted
between observed variable and to model these Correlation Points (Pt Mean Corr): .4 <Pt Measure Right
correlations using one or more latent variables (Goretzko <.85 (Boone et al., 2014). Rasch analysis allows the
et al., 2019). The main component of EFA used in this transformation of data. Transformation from the raw
study was varimax rotation and Kaiser criteria, but values to interval values are easier to interpret because
Osbourne (2015) indicated that it was not optimal. As across the scale, each change in one unit has similar
such, in this study the Kaiser-Meyer-Olkin (KMO) value, weight (Alnahdi, 2018).
Bartlett, factor loading, eigen value, scree plot, and Finally, Cronbach’s alpha coefficients (Cohen et al.,
varimax rotation were determined. The Kaiser-Meyer- 2011), composite reliability (CR) and average variance
Olkin Measure of Sampling Adequacy and Bartlett’s Test extracted (AVE) (Zainudin Awang et al., 2018) are used
of Sphericity were employed to determine if the data was to determine reliability, discriminant validity and
suitable for factor analysis. The p score for the Bartlett convergent validity. Construct reliability (CR) (more
test was less than .05, indicating that the data set was not than .60) and average variance extracted (AVE) of more
an identity matrix. KMO has a general acceptability than .50 are acceptable (Zainudin Awang et al., 2018).
value greater than 0.6. Eigenvalues larger than one Convergent validity is achieved when an observed
indicate the presence of separate components. Next, the variable significantly correlates with latent variables
scree plot was inspected again to ensure the number of (Obrad, 2020). Discriminant validity refers to whether
dimensions that should be preserved. For Hair et al. the constructs truly vary from one another (Ab Hamid,
(2010), the overall value of factor loading for each item 2017). Average Variance Extracted (AVE) can be used to
that exceeds .50 is significant for validating the determine convergent validity. A value that is greater
questionnaire meaningfulness. than one .50 is a desirable AVE index. The discriminant
CFA has long been used in mathematics education validity is additionally calculated by AVE scores which
(Asempapa & Brooks, 2020; Hidayat et al., 2021) and are higher than the maximum shared variance (MSV)
psychological study (Hidayat et al., 2018; Yong et al., and average shared variance (ASV) values (Hair et al.,
2020) to describe the theoretical aspects of instruments. 2014).
We used CFA to examine if the original dimension
structure remained true in Malaysian contexts RESULT
employing the IBM SPSS AMOS, version 18. A total of
two models were examined. The model parameters for Descriptive Analysis
the first- and second-order models for the mathematical
The sub-dimensions were computed, as revealed in
modeling attitude scale were conducted. The first-order
Table 1, for Mean, standard deviation (SD), skewness,
model was examined based on Asempapa and Brooks
kurtosis and inter-correlation.
(2020) involving four dimensions. Next, we developed a
second-order model in which the four mathematical Based on Table 1, kurtosis and skewness values for
modeling attitude dimensions worked on a higher-order all sub-dimensions and items fell within −3 and +3
latent variable. To evaluate and compare the overall (Brown & Greene, 2006) when using SEM. An evaluation
model fit of the first and second-order models, different of the multivariate normality analysis as indicated by
goodness-of-fit indicators were employed in this work to Mardia (1970) that the kurtosis score to be 279.38 with a
assess the adequacy of the postulated models. The critical ratio of 44.57, indicated that the study’s collected
following were the requirements for a good fit: chi- data was not normally distributed. We employed
square test (p > 0.05) (Hooper et al., 2008), χ2/degrees of bootstrapping (500 resamples) for this data set to achieve
freedom (<.50), the comparative fit index (CFI) (>.90), the more precise and reliable estimations (Awang, 2012). All
Tucker-Lewis index (TLI) (>.90) (Wang & Wang, 2019), scale items had significant relationships, and the four
the root mean square error of approximation (RMSEA) sub-dimensions had modest to strong associations
(<1.0) (Awang, 2012; Hu & Bentler, 1999). (ranging from r = .46 to r = .81, p < =.01). All associations
were less than .90, indicating that there was no
The research questions were also computed by means
multicollinearity (Kline, 2005). The mean score differed
of Rasch analysis, employing the WINSTEPS version
each sub-dimensions, with M = 4.71 and SD = .75 for
3.73. We provided reliability, separation, fit statistics,
constructivism, M = 4.61 and SD = .73 for relevance and
rating scale, unidimensionality, and item bias in Rasch
real-life, M = 4.17 and SD = .77 for understanding and M
analysis. There are various fit statistics to evaluate in
= 4.42 and SD = .78 for motivation and interest.
order to verify model fitness in Rasch analysis: the
unidimensionality test, differential item functioning
(DIF), item person separation reliability, Rasch model fit
5 / 16
Hidayat et al. / Mathematical Modeling Attitude
Table 1. Sub-dimensions with their mean values, SD, skewness, and kurtosis
Sub-dimensions Mean SD Skew Kurtosis 1 2 3 4
Constructivism 4.71 .75 -.77 2.81 1 .53** .27** .53**
Relevance and real-life 4.61 .73 .05 -.41 1 .58** .81**
Understanding 4.17 .77 -.20 -.13 1 .46**
Motivation and interest 4.42 .78 -.09 -.05 1
**. Correlation is significant at the 0.01 level (2-tailed).
6 / 16
EURASIA J Math Sci and Tech Ed
7 / 16
Hidayat et al. / Mathematical Modeling Attitude
Table 3. The first- and second-order model comparison Reliability of the Mathematical Modeling Attitude
Model Scale
Goodness-of-
Criterion First-order Second-order
fit We examined the reliability of the mathematical
model model
modeling attitude sub-scales (constructivism, relevance
χ² p > 0.05 864.008 868.834
and real-life, understanding, and motivation and
χ²/df < 5.00 2.512 2.511
CFI > 0.900 .904 .904 interest) and overall mathematical modeling attitude
TLI > 0.900 .900 .900 items for the total respondents (N = 171) (see Table 4). In
RMSEA < 1.00 .094 .094 the present work, internal consistency scores were: a)
constructivism: α = .92, b) relevance and real-life: α = .96,
c) understanding: α = .91, and d) motivation and interest:
understanding (.59) and motivation and interest (.85). As
α = .97. The scale’s mathematical modeling attitude were
a result, the CFA model depicted in Figure 3 is the final
excellent Cronbach alpha coefficient (Hair et al., 2015).
second-order model that depicts the structure of a
The AVE values varied from .67 to .79, all over 0.5,
mathematical modeling attitude scale in the Malaysian
demonstrating that each dimension had satisfactory
context.
internal consistency (Hair et al., 2017) and supporting
The model parameters for the first- and second-order convergent validity (Fornell & Larcker, 1981). Again,
models for the mathematical modeling attitude scale are MSV and ASV scores were smaller than AVE scores,
shown in Table 3. When the two models were compared, indicating the good discriminant validity of the
it was clear that the final first-order model for the mathematical modeling attitude. Finally, composite
mathematical modeling attitude scale fit better than the reliability for the mathematical modeling attitude
second-order one. In other words, the goodness-of-fit ranged from .91 to .97, showing high internal consistency
indices for the second-order model of the mathematical as well.
modeling attitude scale were less favorable. However,
both model parameters met the criteria for excellent
model-data fit.
8 / 16
EURASIA J Math Sci and Tech Ed
9 / 16
Hidayat et al. / Mathematical Modeling Attitude
10 / 16
EURASIA J Math Sci and Tech Ed
had a four-factor structure: constructivism, relevance MMAS (Asempapa & Brooks, 2020). The gap between
and real-life, understanding and motivation and interest. “somewhat disagree” and “disagree” was discovered to
The study’s results were consistent with previous work be less than the acceptable distance. It was also obvious
conducted by Asempapa and Brooks (2020) indicating that the disagree scale did not show as another scale.
that the MMAS were quite excellent for the 4-dimension Therefore, it was possible to modify the rating scale to be
model. The significant correlations discovered between 5 scale which could still provide good psychometric
the MMAS dimensions indicated the domains’ properties (Lee & Paek, 2014; Leung, 2011; Lozano et al.,
interdependence and demonstrated that a 2008) for the Malaysian version of the MMAS. One
multidimensional model was a good match for partial reason was that respondents were given the
investigating these diverse domains. Our work added to option of answering the middle alternative on a 5-point
the body of knowledge by demonstrating the scale. At the same time, the DIF criterion were analysed
repeatability of the MMAS in a diverse cultural to detect item bias based on location (rural and urban
environment. area). The results showed that one item such as E2
The CFA findings confirmed the EFA conclusion, (mathematical modeling enhances classroom discourse in
since the MMAS matched the data quite well. The learning mathematics) did not meet the DIF criterion of
findings of CFA revealed that the model fit indices being in the range of 0.5. This finding supported
established the four-factor structure of the first- and previous investigation in STEM competency in Malaysia
second-order model. At the same time, the MMAS sub- (Khairani, 2017). This was because teachers in rural
dimensions also had an excellent convergent and schools were similarly deficient in terms of talent,
discriminant validity. Constructivism was positively experience, and professional development.
associated to relevance and real-life; and motivation and
interest, with high relationship. Again, constructivism CONCLUSION
was positively linked to understanding with weak Teachers play an important role in developing and
correlation. Relevance and real-life were positively implementing these mathematical modelling objectives.
associated to understanding and motivation and Many mathematics instructors, on the other hand, do not
interest, with high relationship. Finally, understanding feel modelling is a great method to learn mathematics,
was positively related to motivation and interest, with and many regularly doubt their own mathematical
high relationship. We also discovered that all sub- modelling talents. As a result, it is beneficial to research
dimensions had acceptable internal consistency (.92 to and develop a tool for teachers’ attitudes towards
.97), person reliability (.96), item reliability (.94) and mathematical modelling including understanding,
Cronbach’s alpha (.97), which corresponded to constructivism, relevance and real-life, and motivation
Cronbach’s alpha in the US version. Hence, we may infer and interest. A validated, culturally adapted test in
that the four-dimensional structure and the diverse Malaysia was necessary to assess teachers’ attitudes
dimensions of constructivism, relevance and real-life, towards mathematical modelling in order to deploy the
understanding and motivation and interest as attitude scale in Malaysian contexts. The results of this
characterised by the MMAS emerged applicable to the study revealed that the items in the MMAS
Malaysian teacher population. The implementation of questionnaire were generally acceptable and
the EFA and CFA to the MMAS contributed to the transferable for measuring teachers’ attitude in
confirmation of the correctness and usefulness of the mathematical modeling. EFA outputs revealed that the
MMAS questionnaire. The Malaysian version of the data from the teachers had a four-factor structure:
MMAS may be used to assess teachers in mathematical constructivism, relevance and real-life, understanding
modeling attitude in Malaysia. and motivation and interest. The findings of CFA
The Rasch analysis provided additional support for revealed that the model fit indices established the four-
these results by examining the quality of each item and factor structure of the first- and second-order model.
answer category on the MMAS questionnaire. The Although the Rasch analysis generally supported the
findings of the Rasch analysis revealed that the MMAS finding of EFA and CFA there was still room for
had satisfactory item and person reliability. Again, improvement. For example, in terms of the rating scale
according to the Rasch evaluation, all of the MMAS and DIF criterion, the current work contributed to the
items had appropriate infit and outfit MNSQ statistics, body of knowledge by providing valid instrument for
indicating the alignment between student’s attitudes evaluating teachers’ attitudes toward mathematical
and responses to the item. Although Rasch analysis modeling, which was then analysed using EFA, CFA and
generally supported the finding of EFA and CFA, there a strong Rasch model. Lastly, future studies might look
was still room for improvement. The Rasch analysis at cultural variables influencing survey design and
revealed that the successive answer categories for all implementation. This implies that the tool may be
sub-domains in the Malaysian version of the MMAS utilised extensively independent of the grouping factors.
were not situated in the predicted direction. These
findings differ from those of the US version of the
11 / 16
Hidayat et al. / Mathematical Modeling Attitude
LIMITATIONS AND FUTURE Adams, D., Chuah, K. M., Sumintono, B., & Mohamed,
DIRECTIONS A. (2021). Students’ readiness for e-learning during
the COVID-19 pandemic in a South-East Asian
Although the MMAS might be used widely in the university: A Rasch analysis pandemic. Asian
Malaysian context and the instrument has the potential Education and Development Studies.
to be utilised for study and practise in this specific https://doi.org/10.1108/AEDS-05-2020-0100
setting, we admit that this study has several drawbacks.
Aiken Jr, L. R. (1970). Attitudes toward mathematics.
First, the most evident limitation was the tiny data set,
Review of Educational Research, 40(4), 551-596.
which reduced the validity of the inferences derived
https://doi.org/10.3102/00346543040004551
from the data. The data analysis used in this study was
based on a sample of data gathered only in two states in Albarracín, D., Johnson, B. T., & Zanna, M. P. (Eds.).
Malaysia with limited number of respondents (N = 171), (2005). The handbook of attitudes (pp. 223-271).
which had an impact on generalisation to other groups Lawrence Erlbaum.
in Malaysia. In future research, the repetition of the Albarracín, L. (2021). Large number estimation as a
current findings using bigger random samples from vehicle to promote mathematical modeling. Early
other cultural background can provide more support for Childhood Education Journal, 49(4), 681-691.
the findings’ generalizability. Again, future research https://doi.org/10.1007/s10643-020-01104-x
should focus on both pre-service and experienced Albarracín, L., & Gorgorió, N. (2020). Mathematical
instructors. Second, convenience sampling (non- modeling projects oriented towards social impact
probability sampling) was utilised in this research and as generators of learning opportunities: A case
this was dependent on proximity and accessibility of study. Mathematics, 8(11), 2034.
participants due to the Covid situation. This method https://doi.org/10.3390/math8112034
may not yield a true picture of the people in the research Ali, A. R., Endut, A., & Embong, R. (2019). Attitude of
regions. Data was collected via an online tool, which undergraduate students towards gamification: A
may have excluded those who did not have internet case study of Northwest Geo-Political Zone,
access. Future studies should attempt to obtain data Nigeria. Journal of ICT in Education, 5, 9-13.
from many sources. Third, female instructors https://doi.org/10.37134/jictie.vol5.2.2018
outnumbered male teachers in this research. It is possible
to study gender bias in this instrument since the current Alkhadim, G. S., Cimetta, A. D., Marx, R. W., Cutshaw,
research found the possibility for diversity in C. A., & Yaden, D. B. (2021). Studies in educational
respondents’ responses based on location (rural and evaluation validating the research-based early
urban area). Future studies should continue to look for math assessment (REMA) among rural children in
evidence of different backgrounds. Before reaching any Southwest United States. Studies in Educational
definite conclusions, it appears that this study should be Evaluation, 68(2020), 100944. https://doi.org/
replicated with an equal number of males and females. 10.1016/j.stueduc.2020.100944
Lastly, future studies might benefit from including such Alnahdi, A. H. (2018). Rasch validation of the Arabic
data as a dependant variable to be determined by the version of the lower extremity functional scale.
instructors’ mathematical modelling ability. Disability and Rehabilitation, 40, 353-359.
https://doi.org/10.1080/09638288.2016.1254285
Author contributions: All authors have sufficiently contributed to
the study, and agreed with the results and conclusions. Anderson, E. W., & Mittal, V. (2000). Strengthening the
Funding: No funding source is reported for this study. satisfaction-profit chain. Journal of Service Research,
Declaration of interest: No conflict of interest is declared by 3(2), 107-120. https://doi.org/10.1177/
authors. 109467050032001
Araújo, J. D. L., & Lima, F. H. D. (2020). The
REFERENCES mathematization process as object-oriented actions
A Aziz, N. F., Ahmad, H., & Mat Nashir, I. (2019). of a modelling activity system. Bolema: Boletim de
Validation of technical and vocational teachers’ Educação Matemática, 34(68), 847-868.
competency evaluation instrument using the rasch https://doi.org/10.1590/1980-4415v34n68a01
model. Jurnal Pendidikan Sains Dan Matematik Asempapa, R. S. (2018). Development and initial
Malaysia, 9(1), 18-25. https://doi.org/10.37134/ psychometric properties of the mathematical
jpsmm.vol9.1.3.2019 modeling attitude scale. School Science and
Ab Hamid, M. R., Sami, W., & Sidek, M. M. (2017). Mathematics, 119(1), 14-23. https://doi.org/10.1111
Discriminant validity assessment: Use of Fornell & /ssm.12311
Larcker criterion versus HTMT criterion. Journal Asempapa, R. S., & Brooks, G. P. (2020). Factor analysis
of Physics: Conference Series, 890(1), 012163. and psychometric evaluation of the mathematical
https://doi.org/10.1088/1742-6596/890/1/012163 modeling attitude scale for teachers of
mathematics. Journal of Mathematics Teacher
12 / 16
EURASIA J Math Sci and Tech Ed
13 / 16
Hidayat et al. / Mathematical Modeling Attitude
Hair, J. F. Jr., Sarstedt, M., Ringle, C. M., & Gudergan, S. Education, 14(12), em1648. https://doi.org/
P. (2017). Advanced issues in partial least squares 10.29333/ejmste/99173
structural equation modeling. Sage publications. Hidayat, R., Zulnaidi, H., & Syed Zamri, S. N. A. (2018).
Hair, J. F., Black, W. C., Babin, B. J., & Anderson, R. E. Roles of metacognition and achievement goals in
(2010). Multivariate data analysis (7th ed.). Pearson. mathematical modeling competency: A structural
Hair, J. F., Celsi, M., Money, A., Samouel, P., & Page, M. equation modeling analysis. PloS One, 13(11),
(2015). The essentials of business research method (3rd e0206211.
ed.). 2016 Faculty Bookshelf. 2. https://doi.org/10.1371/journal.pone.0206211
https://doi.org/10.4324/9781315704562 Hooper, D., Coughlan, J., & Mullen, M. (2008). Structural
Hair, J. F., Hult, G. T. M., Ringle, C. M., & Sarstedt, M. equation modelling: Guidelines for determining
M. (2014). A Premier on partial least squares structural model fit. The Electronic Journal of Business Research
equation modeling (PLS-SEM). SAGE Publications. Methods, 6, 53-60.
Hallström, J., & Schönborn, K. J. (2019). Models and Hunt J. (2007). Communicating big themes in applied
modelling for authentic STEM education: mathematics. In P. Haines, W. Galbraith, W. Blum,
Reinforcing the argument. International Journal of & S. Khan (Eds.), Mathematical modeling (ICTMA12):
STEM Education, 6(2), 1-10. https://doi.org/ Education, engineering and economics (pp. 2-24).
10.1186/s40594-019-0178-z Horwood Publishing. https://doi.org/10.1533/
9780857099419.1.1
Hamed, S., Bahari, P., & Abdullah, A. G. K. (2008).
Korelasi antara persekitaran pembelajaran Iseppi, L., Rizzo, M., Gori, E., Nassivera, F., Bassi, I., &
matematik, sikap pelajar terhadap matematik, dan Scuderi, A. (2021). Rasch model for assessing
pencapaian pelajar dalam matematik: Satu kajian propensity to entomophagy. Sustainability, 13(8),
kes [Correlation between mathematics learning 4346. https://doi.org/10.3390/su13084346
environment, students ‘attitudes toward Kasmin, F., Othman, Z., & Syed Ahmad, S. S. (2019).
mathematics, and student achievement in Improving students’ perception towards learning
mathematics: A case study]. ESTEEM, 4(2), 91-103. mathematics: impact of teaching application of
Hannula, M. S. (2002). Attitude towards mathematics: mathematics. EDUCATUM Journal of Science,
Emotions, expectations and values. Educational Mathematics and Technology, 6(1), 29-34.
studies in Mathematics, 49(1), 25-46. https://doi.org/10.37134/ejsmt.vol6.1.4.2019
https://doi.org/10.1023/A:1016048823497 Khairani, A. Z. (2017). Assessing urban and rural
He, J., Sun, S., & Fan, X. (2021). Validation of the 12-item teachers’ competencies in STEM integrated
short form of the eating disorder examination education in Malaysia. In MATEC Web of
questionnaire in the Chinese context: Confirmatory Conferences (vol. 87, p. 04004). EDP Sciences.
factor analysis and Rasch analysis. Eating and https://doi.org/10.1051/matecconf/20178704004
Weight Disorders, 26(1), 201-209. Kline, R. B. (2005). Principles and practice of structural
https://doi.org/10.1007/s40519-019-00840-3 equation modeling. The Guilford Press.
Hennig, C. (2010). Mathematical models and reality: a Kohen, Z., & Orenstein, D. (2021). Mathematical
constructivist perspective. Foundations of Science, 15, modeling of tech-related real-world problems for
29-48. https://doi.org/10.1007/S10699-009-9167-X secondary school-level mathematics. Educational
Hidayat, R., Qudratuddarsi, H., Mazlan, N. H., & Zeki, Studies in Mathematics, 107(1), 71-91.
M. Z. M. (2021). Evaluation of a test measuring https://doi.org/10.1007/s10649-020-10020-1
mathematical modelling competency for Leavy, A., Hourigan, M., & Carroll, C. (2017). Exploring
Indonesian college students. Journal of Nusantara the impact of reform mathematics on entry-level
Studies, 6(2), 133-155. https://doi.org/10.24200/ pre-service primary teachers attitudes towards
jonus.vol6iss2pp133-155 mathematics. International Journal of Science and
Hidayat, R., Zamri, S. N. A. S, Zulnaidi, H., Abdullah, M. Mathematics Education, 15(3), 509-526.
F. N. L., & Adnan, M. (2021). The interrelationships https://doi.org/10.1007/s10763-015-9699-1
between metacognition and modeling competency: Lee, J., & Paek, I. (2014). In search of the optimal number
the moderating role of the academic year. European of response categories in a rating scale. Journal of
Journal of Educational Research, 10(4), 1853-1866. Psychoeducational Assessment, 32(7), 663-673.
https://doi.org/10.12973/eu-jer.10.4.1853 https://doi.org/10.1177/0734282914522200
Hidayat, R., Zamri, S. N. A. S., & Zulnaidi, H. (2018). Leong, K. E., & Tan, J. Y. (2020). Exploring secondary
Exploratory and confirmatory factor analysis of students’ modelling competencies. The Mathematics
achievement goals for Indonesian students in Enthusiast, 17(1), 85-107.
mathematics education programmes. EURASIA
Journal of Mathematics, Science and Technology
14 / 16
EURASIA J Math Sci and Tech Ed
Leung, A. (2019). Exploring STEM pedagogy in the Sabudin, G., & Halim, L. (2020). Kajian sistematik:
mathematics classroom: A tool-based experiment pendekatan pengajaran dan impak khazanah
lesson on estimation. International Journal of Science pengetahuan dalam pembelajaran sains. Jurnal
and Mathematics Education, 17(7), 1339-1358. Pendidikan Sains Dan Matematik Malaysia, 10(1), 21-
https://doi.org/10.1007/s10763-018-9924-9 38.
Leung, S. O. (2011). A comparison of psychometric https://doi.org/10.37134/jpsmm.vol10.1.4.2020
properties and normality in 4-, 5-, 6-, and 11-point Sahin, S., Dogan, M. F., Cavus Erdem, Z., Gurbuz, R., &
likert scales. Journal of Social Service Research, 37(4), Temurtas, A. (2019). Prospective teachers’ criteria
412-421. for evaluating mathematical modeling problems.
https://doi.org/10.1080/01488376.2011.580697 International Journal of Research in Education and
Lozano, L. M., García-Cueto, E., & Muñiz, J. (2008). Effect Science, 5(2), 730-743.
of the number of response categories on the Scoulas, J. M., Aksu Dunya, B., & De Groote, S. L. (2021).
reliability and validity of rating scales. Methodology, Validating students’ library experience survey
4(2), 73-79. https://doi.org/10.1027/1614- using rasch model. Library and Information Science
2241.4.2.73 Research, 43(1), 101071. https://doi.org/10.1016/
Maaβ, K. (2006). What are modeling competencies? j.lisr.2021.101071
Zentralblatt FüR Didaktik Der Mathematik, 38(2), 113- Shahbari, J. A., & Peled, I. (2015). Resolving cognitive
142. https://doi.org/10.1007/BF02655885 conflict in a realistic situation with modeling
Mardia, K. V. (1974). Applications of some measures of characteristics: Coping with a changing reference in
multivariate skewness and kurtosis in testing fractions. International Journal of Science and
normality and robustness studies. Sankhyā: The Mathematics Education, 13(4), 891-907.
Indian Journal of Statistics, Series B, 36(2), 115-128. https://doi.org/10.1007/s10763-014-9509-1
McLeod, D. (1992). Research on affect in mathematics Singer, F. M., & Moscovici, H. (2008). Teaching and
education: a reconceptualization. In D. Grows (Ed.), learning cycles in a constructivist approach to
Handbook of research on mathematics teaching and instruction. Teaching and Teacher Education, 24(6),
learning (pp. 575-596). McMillan. 1613-1634.
https://doi.org/10.1016/j.tate.2007.12.002
Obrad, C. (2020). Constraints and consequences of online
teaching. Sustainability, 12(17), 6982. Stillman, G., Kaiser, G., Blum, W., & Brown, J. (Eds,
https://doi.org/10.3390/su12176982 2013). Teaching mathematical modelling: connecting to
research and practice. Springer.
Osbourne, J. W. (2015). What is rotating in exploratory
https://doi.org/10.1007/978-94-007-6540-5
factor analysis? Practical Assessment, Research, and
Evaluation, 20(2), 1-7. Suryadi, B., Hayat, B., Dwirifqi, M., & Putra, K. (2021).
The Indonesian version of the life orientation test-
Pollak, H. O. (2011). What is mathematical modeling?
revised (LOT-R): psychometric properties based on
Journal of Mathematics Education at Teachers College,
the Rasch model The Indonesian version of the life
2(1), 64.
orientation test-revised (LOT-R): Psychometric
Purnami, W., Sumintono, B., & Wahyu, Y. (2021). properties based on the Rasch model. Cogent
Investigation of person ability and item fit Psychology, 8(1), 1869375. https://doi.org/10.1080/
instruments of eco critical thinking skills in basic 23311908.2020.1869375
science concept materials for elementary pre-
Tajudin, A., & Abdullah, N. (2018). Kesediaan guru sains
service teachers. Jurnal Pendidikan IPA Indonesia,
sekolah rendah terhadap pelaksanaan
10(1), 127-137. https://doi.org/10.15294/jpii.v10i1.
pembelajaran abad ke-21 [The readiness of primary
25239
school science teachers towards the
Raykov, T. (2004). Behavioral scale reliability and implementation of 21st century learning]. Jurnal
measurement invariance evaluation using latent Pendidikan Sains Dan Matematik Malaysia, 8(1), 82-
variable modeling. Behavior Therapy, 35, 299-331. 97. https://doi.org/10.37134/jpsmm.vol8.1.7.2018
https://doi.org/10.1037/cou0000192
Tennant, A., & Conaghan, P. G. (2007). The Rasch
Rouquette, A., Hardouin, J. B., Vanhaesebrouck, A., measurement model in rheumatology: What is it
Sébille, V., & Coste, J. (2019). Differential item and why use it ? when should it be applied, and
functioning (DIF) in composite health what should one look for in a Rasch paper ?
measurement scale: Recommendations for Arthritis & Rheumatism, 57(8), 1358-1362.
characterizing DIF with meaningful consequences https://doi.org/10.1002/art.23108
within the Rasch model framework. PLoS ONE,
Tiilikainen, M., Karjalainen, J., Toom, A., Lepola, J., &
14(4), 1-16. https://doi.org/10.1371/journal.pone.
Husu, J. (2019). The complex zone of constructivist
0215073
teaching: a multi-case exploration in primary
15 / 16
Hidayat et al. / Mathematical Modeling Attitude
classrooms. Research Papers in Education, 34(1), 38- Yong, W., Hutagalung, F. D., Hidayat, R., & Zulnaidi, H.
60. (2020). A comparison study of Chinese and
https://doi.org/10.1080/02671522.2017.1402080 Indonesia EFL teachers’ well-being. Psychology and
Van Zile-tamsen, C. (2019). Using Rasch analysis to Education, 57(4), 233-238.
inform rating scale development. Research in Higher Zainudin Awang, Lim, S., & Nur Fairuza Syahira. (2018).
Education, 58(8), 922-933. https://doi.org/10.1007/ Pendekatan mudah SEM (Structural Equation
s11162-017-9448-0 Modelling). MPWS.
Wang, J. & Wang, X. (2019). Structural equation modeling:
applications using mplus (2nd ed.). John Wiley &
Sons Ltd. https://doi.org/10.1002/9781119422730
http://www.ejmste.com
16 / 16