You are on page 1of 15

A Handbook on SEM

Zainudin Awang - Universiti Sultan Zainal Abidin

CHAPTER 9

THE APPLICATION OF AMOS GRAPHIC


IN POSTGRADUATE RESEARCHES

In this chapter, the discussion is focused on analyzing the theoretical model of a research using
Structural Equation Modeling (SEM) with AMOS Graphic. As has been said earlier, the researcher
could convert the exact research model into AMOS Graphic for further analysis.

9.1 MODELING THE LOYALTY OF BANKING CUSTOMERS

The model for the above study is shown in Figure 1. In this study the researcher was trying to
analyze the inter-relationships among four exogenous constructs, two mediating constructs, and
one endogenous construct in a model. The latent constructs involved in this study are:

1. Perceived Service Quality (PSQ). This latent construct is measured using seven items
namely ps1 to ps7. This is an exogenous construct.

2. Perceived Value (PV). This latent construct is also measured using seven items namely pv1
to pv7. This is an exogenous construct.

3. Communication (COM). This latent construct is measured using four items namely co1 to
co4. This is an exogenous construct.

4. Corporate Image (IMG). This latent construct is measured using eight items namely im1 to
im8. This is an exogenous construct.

5. Customer Satisfaction (CS). This latent construct is measured using five items namely cs1
to cs5. This is a mediating construct.

6. Customer Trust (TRUST). This latent construct is measured using five items namely tr1 to
tr5. This is a mediating construct.

7. Customer Loyalty (CL). This latent construct is measured using six items namely cl1 to cl
6. This is an endogenous construct.

The latent constructs and their respective indicators are modeled in Figure 1.

171
A Handbook on SEM
Zainudin Awang - Universiti Sultan Zainal Abidin

Figure 1: The model of Customer Loyalty towards service providers in banking industry

The researcher needs to validate the measurement model for all latent constructs using CFA
before modeling the structural model (SEM). The validation procedure for Unidimensionality,
Validity and Reliability would be carried out using Confirmatory Factor Analysis (CFA). The
Pooled-CFA is more preferred compared to separate CFA for every measurement model.
In this particular study, no pilot test was required, and no EFA was carried out. This is
because the instruments involved have been established and validated by previous researcher and
the present researcher only adapts the instruments. The other reason is because the industry where
the instruments were developed is similar with the present study.

172
A Handbook on SEM
Zainudin Awang - Universiti Sultan Zainal Abidin

9.2 MODELING THE LOYALTY OF UNDERGRADUATES TOWARDS


THEIR UNIVERSITY FOR POSTGRADUATE STUDIES

The schematic diagram of the model is shown in Figure 2, and the conversion of schematic
diagram into AMOS graphic is shown in Figure 3.

In this study, the researcher was trying to analyze the inter-relationships among four latent
constructs namely Service Quality, Corporate Image, Students Satisfaction, and Students Loyalty.
In this case Service Quality and Corporate Image are exogenous constructs, Students Satisfaction
is a mediating construct, and Students Loyalty is the endogenous construct. All constructs in the
model are latent. The hypotheses of interest to be tested by the study are shown in Figure 2.

Figure 2: Modeling the loyalty of outgoing undergraduates towards their university for postgraduates

The Schematic diagram in Figure 2 presents five hypotheses of interest to be tested in the study.
The model in this study has four latent constructs namely Service Quality (34 items), Corporate
Image (16 items), Student Satisfaction (9 items), and Students Loyalty (14 items). The Pilot Study

173
A Handbook on SEM
Zainudin Awang - Universiti Sultan Zainal Abidin

data were collected using the above items. Using data from Pilot Study, the researcher runs the
Exploratory Factor Analysis (EFA) to determine the dimensionality of items measuring every
construct – whether all items fall into one dimension or fall into several dimensions.

The EFA employed to the Pilot Study data found that every latent construct consist of a few
dimensions where each dimension has certain number of items. Items having low factor loading
(less than 0.6) as well as cross-loading items (factor loading greater than 0.6 for more than one
dimension) were deleted. Now, based on the dimensions and their respective items, the
measurement models for the constructs are developed as shown in Figure 3. At this stage, the
researcher could rename the dimensions accordingly.
For example Service Quality construct has three dimensions - the researcher renamed them as People, Academic, and
Infrastructure – meaning, the quality of the people, quality of academic facilities , and quality of infrastructure
facilities in the university system. In this case, the Service Quality construct is considered a second order construct
since it consists of three sub-constructs.

174
A Handbook on SEM
Zainudin Awang - Universiti Sultan Zainal Abidin

Figure 3: The Measurement Model for every construct based on the outcome of EFA
The items for every construct were rearranged in a dimension based on the measurement model in
Figure 3. Using the data from the field study, the researcher would run the Confirmatory Factor
Analysis (CFA) to validate the measurement model (Figure 3). As has been explained in Chapter
3, the CFA procedure is carried out to assess the Unidimensionality, Validity, and Reliability of
the measurement model. Once the above requirements have been achieved, the researcher could
proceed into Structural Equation Modeling or SEM. The structural model for SEM is shown in
Figure 4.

Figure 4: The structural model for running SEM once the CFA is completed.
Note: In some study, the researcher only interested to validate the measurement model of the constructs using CFA,
and the objective of the study does not include modeling using SEM. This is especially true if the researcher is only
developing the measurement model for certain constructs, and has no intention to examine the inter-relationships
among these constructs since the theoretical framework is not yet developed.

175
A Handbook on SEM
Zainudin Awang - Universiti Sultan Zainal Abidin

Question: What if, the researcher did not carry out pilot study. He collected all 400 data required
for the project during field study. How he should go about doing EFA and CFA?

Answer: In this case, he needs to split these 400 data randomly into two separate data files – let
name the files as dataset1 and dataset2. Dataset1 consist of 100 data - supposedly from pilot study
and Dataset2 consist of 300 data – supposedly from field study. He could run EFA procedure using
dataset1 to obtain the dimensions and to develop measurement model of the construct, and then to
run the CFA procedure using dataset 2 to validate the measurement model of the construct. Thus,
dataset 2 should contain the variables resulted from EFA.

Caution: The data that has been used to analyze EFA cannot be re-used for analyzing CFA. In
other words, data cannot be recycled. The rationale being – the EFA is assessed based on the Pilot
Study data whereas CFA is assessed based on Field Study data. In reality, the time lapse between
pilot study and field study is too long. On top of that, EFA is carried out with the purpose to
determine the dimensionality of items measuring the construct, whereas CFA is carried out with
the purpose to validate the measurement model of a construct.

176
A Handbook on SEM
Zainudin Awang - Universiti Sultan Zainal Abidin

9.3 MODELING THE REPURCHASE INTENTIONS TOWARDS A


PARTICULAR SERVICE PRODUCT

Figure 5: The Standardized Regression Weights

Table 1: The Correlations between Exogenous Constructs in the model

Construct Construct Estimate


Spiritual_Intelligence <--> Spiritual_Congruence -.427
Spiritual_Congruence <--> Product_Image .377
Product_Image <--> Product_Involvement .569
Spiritual_Intelligence <--> Product_Image -.662
Spiritual_Intelligence <--> Product_Involvement -.652
Spiritual_Congruence <--> Product_Involvement .336
Perceived_Control <--> Subjective_Norm .588
Spiritual_Intelligence <--> Perceived_Control -.640
Spiritual_Intelligence <--> Subjective_Norm -.689

177
A Handbook on SEM
Zainudin Awang - Universiti Sultan Zainal Abidin

Construct Construct Estimate


Spiritual_Congruence <--> Perceived_Control .552
Spiritual_Congruence <--> Subjective_Norm .587
Product_Involvement <--> Perceived_Control .497
Product_Involvement <--> Subjective_Norm .614
Product_Image <--> Perceived_Control .434
Product_Image <--> Subjective_Norm .473
Note: All correlation between Exogenous Constructs are below 0.85 which indicate no redundancy among constructs
in the model.

Figure 6: The Regression Weights for the model

Figure 6 presents the regression weights or the effects of all exogenous constructs on their
corresponding endogenous constructs. The output also presents the variance of measurement errors
for every items in the model as well as the variance of residuals of the model itself.

178
A Handbook on SEM
Zainudin Awang - Universiti Sultan Zainal Abidin

Table 2: The Regression Weights and its Significance

Construct Construct Estimate S.E. C.R. P Result


Attitude <--- Spiritual_Intelligence 0.320 0.156 2.050 0.040 Significant
Attitude <--- Spiritual_Congruence 0.100 0.043 2.300 0.021 Significant
Attitude <--- Product_Image 0.892 0.089 10.036 *** Significant
Attitude <--- Product_Involvement 0.515 0.164 3.146 0.002 Significant
Intention_to_Purchase <--- Attitude 0.259 0.082 3.170 0.002 Significant
Intention_to_Purchase <--- Perceived_Control 0.230 0.088 2.608 0.009 Significant
Intention_to_Purchase <--- Subjective_Norm 0.550 0.113 4.873 *** Significant

179
A Handbook on SEM
Zainudin Awang - Universiti Sultan Zainal Abidin

9.4 MODELING THE EFFECTS OF CRISIS RESPONSIBILITY ON


ORGANIZATIONAL REPUTATION

Figure 7: The Standardized Regression weight

Once the output is obtained, the researcher needs to examine whether regression values given
(standardized or unstandardized regression weights) are theoretically correct or not. For example,
theoretically the effects of Crisis Responsibility on Charismatic Leadership, Corporate Credibility,
and Organizational Reputation should be negative. On the other hand, the effects of Charismatic
Leadership and Corporate Credibility on Organizational Reputation should be positive.

180
A Handbook on SEM
Zainudin Awang - Universiti Sultan Zainal Abidin

Figure 8: The Regression weight

Table 3: The Path Analysis and its significance

Construct Construct Estimate S.E. C.R. P Result

Charismatic_Leadership <--- Crisis_Responsibility -0.500 .056 -8.891 *** Significant


Charismatic_Leadership <--- Crisis_Responsibility -0.405 .061 -6.672 *** Significant
Corporate_Credibility <--- Crisis_Responsibility -0.223 .044 -5.037 *** Significant
Organizational_Reputation <--- Charismatic_Leadership 0.533 .082 6.479 *** Significant
Organizational_Reputation <--- Corporate_Credibility 0.147 .039 3.822 *** Significant
Organizational_Reputation <--- Crisis_Responsibility -0.500 .056 -8.891 *** Significant
Charismatic_Leadership <--- Crisis_Responsibility -0.405 .061 -6.672 *** Significant

181
A Handbook on SEM
Zainudin Awang - Universiti Sultan Zainal Abidin
1. Abdullahi, M. S., Awang, Z., Abubakar, A., Umar, K., Umar, M. B., Khalid, S. S., & Abubakar, L. S.
The Influence of Training on Business Success in Nigeria: Case of Registered Small and Medium
Scale Enterprises (SMEs) in Kano State, Nigeria.
2. Abdullahi, M. S., Ghazali, P. L., Awang, Z., Mohd Tahir, I., Ali, M., & Salim, N. A. (2015). The Effect
of Finance, Infrastructure and Training on the Performance of Small and Medium Scale Enterprises
(SMEs) in Nigeria. International Journal of Business and Technopreneurship, 5(3), 421-452.
3. Afthanorhan, A., Ahmad, N., & Sabri, A. (2015). A parametric approach using z-test for comparing 2
means to multi-group analysis in partial least square structural equation modeling (PLS-
SEM). British Journal of Applied Science & Technology, 6(2), 194.
4. Afthanorhan, A., Ahmad, S., & Safee, S. (2014). Moderated mediation using covariance-based
structural equation modeling with amos graphic: volunteerism program. Advances In Natural And
Applied Sciences, 8(8), 108-116.
5. Afthanorhan, A., Aimran, A. N., & Ahmad, S. (2015). Permutation Test, Non-parametric, and
Confidence Set Approaches to Multi Group Analysis for Comparing 2 Groups Using Partial Least
Square Structural Equation Modeling (Pls-Sem). International Journal of Mathematics and Statistics
Studies, 3(4), 18-34.
6. Afthanorhan, A., Awang, Z., & Fazella, S. (2017). Developing the patients' loyalty model for medical
tourism industry: the case of Malaysia. International Journal of Society Systems Science, 9(2), 139-
164.
7. Afthanorhan, A., Awang, Z., & Fazella, S. (2017). Perception of Tourism Impact and Support
Tourism Development in Terengganu, Malaysia. Social Sciences, 6(3), 106.
8. Afthanorhan, A., Awang, Z., & Mamat, M. (2016). A comparative study between GSCA-SEM and
PLS-SEM. MJ Journal on Statistics and Probability, 1(1), 63-72.
9. Afthanorhan, A., Nazim, A., & Ahmad, S. (2014). A parametric approach to partial least square
structural equation modeling of multigroup analysis (PLS-MGA). International Journal of Economic,
Commerce, and Management, 2(10), 15.
10. Afthanorhan, W. M. A. B. W. (2013). A comparison of partial least square structural equation
modeling (PLS-SEM) and covariance based structural equation modeling (CB-SEM) for
confirmatory factor analysis. International Journal of Engineering Science and Innovative
Technology, 2(5), 198-205.
11. Afthanorhan, W. M. A. B. W. (2014). Hierarchical component using reflective-formative
measurement model in partial least square structural equation modeling (Pls-Sem). International
Journal of Mathematics, 2(2), 33-49.
12. Afthanorhan, W. M. A. B. W., & Ahmad, S. (2013). Modelling a high reliability and validity by using
confirmatory factor analysis on five latent construct: Volunteerism program. International Research
Journal Advanced Engineer and Scientific Technology (IRJAEST), 1(1), 7.
13. Afthanorhan, W. M. A. B. W., & Ahmad, S. (2013). Modelling The Multigroup Moderator-Mediator
On Motivation Among Youth In Higher Education Institution Towards Volunteerism
Program. International Journal of Scientific & Engineering Research (IJSER), 4(7), 5.
14. Afthanorhan, W. M. A. B. W., & Ahmad, S. (2013). Modelling the multimediator on motivation
among youth in higher education institution towards volunteerism program. Mathematical Theory
and Modeling, 3(7), 64-70.
15. Afthanorhan, W. M. A. B. W., & Ahmad, S. (2014). Path analysis in covariance-based structural
equation modeling with Amos 18.0. European Journal of Business and Social Sciences, 2(10).
16. Afthanorhan, W. M. A. B. W., Ahmad, S., & Mamat, I. (2014). Pooled Confirmatory Factor Analysis
(PCFA) using structural equation modeling on volunteerism program: A step by step
approach. International Journal of Asian Social Science, 4(5), 642-653.

182
A Handbook on SEM
Zainudin Awang - Universiti Sultan Zainal Abidin
17. Afthanorhan, W. M. A. W. (2014). Modeling The Multiple Indirect Effect Among Latent Constructs
By Using Structural Equation Modeling: Volunteerism Program. International Journal of Advances in
Applied Sciences, 3(1), 25-32.
18. Ahmad, S., & Afthanorhan, W. M. A. B. W. (2014). The importance-performance matrix analysis in
partial least square structural equation modeling (PLS-SEM) with smartpls 2.0 M3. International
Journal of Mathematics Research, 3(1), 1.
19. Ahmad, S., Safee, S., & Afthanorhan, W. M. A. W. (2014). Learning styles towards mathematics
achievements among higher education students. Global Journal of Mathematical Analysis, 2(2), 50-
57.
20. Aimran, A. N., Afthanorhan, W. M. A. W., & Razali, N. H. M. (2015). Moderated Mediation Using
Partial Least Square Structural Equation Modeling (PLS-SEM).
21. Aimran, A. N., Ahmad, S., & Afthanorhan, A. (2016). Confirming the Mediation Effect of A Structural
Model By Using Bootstrap Approach: A Case Study of Malaysian 8th Grade Students’ Mathematics
Achievement. International Journal of Business, Economics and Management, 3(4), 44-51.
22. Aimran, A. N., Ahmad, S., Afthanorhan, A., & Awang, Z. (2017, August). The development of
comparative bias index. In AIP Conference Proceedings (Vol. 1870, No. 1, p. 060008). AIP
Publishing.
23. Aimran, A. N., Ahmad, S., Afthanorhan, A., & Awang, Z. (2017, May). The assessment of the
performance of covariance-based structural equation modeling and partial least square path
modeling. In AIP Conference Proceedings (Vol. 1842, No. 1, p. 030001). AIP Publishing.
24. Asri, M. A. M., Ahmad, S., & Afthanorhan, A. (2015). Algorithmic Modelling of Boosted Regression
Trees’ on Environment’s Big Data. Statistics.
25. Asyraf, W. M. (2014). Improving Energy Conservation using six sigma methodology at faculty of
computer and mathematical sciences (FSKM), universiti teknologi mara (UiTM), SHAH
ALAM. Asian Journal of Economic Modelling, 2(1), 52-68.
26. Awang, Z. (2007). The influence of service quality and corporate image on students' loyalty in
higher education (Doctoral dissertation, Fakulti Pengurusan Ekonomi).
27. Awang, Z. (2010). Analyzing the Effects of Corporate Reputation on the Competitiveness of
Telecommunication Industry using the Structural Equation Modelling: The Case of Kelantan.
In Proceedings of the Regional Conference on Statistical Sciences, Malaysia Institute of Statistics,
Faculty of Computer and Mathematical Sciences, University Technology, MARA (UTM),
Malaysia (pp. 283-396).
28. Awang, Z. (2010). The Importance of corporate image in the marketing of university postgraduate
programs. Asian Journal of University Education, 6(1), 13-28.
29. Awang, Z. (2012). Research methodology and data analysis. Penerbit Universiti Teknologi MARA
Press.
30. Awang, Z. (2015). SEM made simple: A gentle approach to learning Structural Equation Modeling.
MPWS Rich Publication.
31. Awang, Z. H. (2010). Research Methodology for Business and Social Science. Pusat Penerbitan
Universiti, Universiti Teknologi MARA.
32. Awang, Z. H., & Jusoff, K. (2009). The effects of corporate reputation on the competitiveness of
Malaysian telecommunication service providers. International Journal of Business and
Management, 4(5), 173.
33. Awang, Z., Afthanorhan, A., & Mamat, M. (2016). The Likert scale analysis using parametric based
Structural Equation Modeling (SEM). Computational Methods in Social Sciences, 4(1), 13.
34. Awang, Z., Afthanorhan, A., Mohamad, M., & Asri, M. A. M. (2015). An evaluation of measurement
model for medical tourism research: the confirmatory factor analysis approach. International Journal
of Tourism Policy, 6(1), 29-45.

183
A Handbook on SEM
Zainudin Awang - Universiti Sultan Zainal Abidin
35. Awang, Z., Afthanorhan, W. M. A. W., & Asri, M. A. M. (2015). Parametric and non parametric
approach in structural equation modeling (SEM): The application of bootstrapping. Modern Applied
Science, 9(9), 58.
36. Awang, Z., Ahmad, J. H., & Zin, N. M. (2010). Modelling job satisfaction and work commitment
among lecturers: A case of UiTM Kelantan. Journal of Statistical Modeling and Analytics, 1(2), 45-
59.
37. Awang, Z., Che Mat, M. A., & Asat, S. H. (2005). The Myth and Reality of Service Quality: The
Gaps Analysis.
38. Awang, Z., Mamat, W., Fauzi, W., & Yusof, Z. (2006). Service quality performance students'
satisfaction and students' loyalty in university education/Prof Madya Zainudin Hj Awang, Wan Fauzi
Wan Mamat, Zulkharnain Yusof.
39. Aziz, M. I., Afthanorhan, A., & Awang, Z. (2016). Talent development model for a career in Islamic
banking institutions: A SEM approach. Cogent Business & Management, 3(1), 1186259.
40. Bakar, A. A., & Afthanorhan, A. (2016). Confirmatory Factor Analysis on Family Communication
Patterns Measurement. Procedia-Social and Behavioral Sciences, 219, 33-40.
41. Bakar, A. A., Samsudin, Z., & Afthanorhan, A. (2016). Re-examining Family Communication
Pattern: The Confirmatory Factor Analysis. Journal of Business and Social Review in Emerging
Economies, 2(2), 101-108.
42. Ibrahim, M. D., Salleh, F., & Awang, Z. (2011). The Effects of Financial Factors on Takaful Demand
in Malaysia Journal of.
43. Ibrahim, Y., Awang, Z., & Yusof, Y. (2016). Environmental management practices in the tourism
industry in Malaysia. Man In India, 96(12), 5241-5252.
44. Kashif, M., Awang, Z., Walsh, J., & Altaf, U. (2015). I’m loving it but hating US: understanding
consumer emotions and perceived service quality of US fast food brands. British Food
Journal, 117(9), 2344-2360.
45. Kashif, M., Kashif, M., Braganca, E., Braganca, E., Awang, Z., Awang, Z., ... & Cyril De Run, E.
(2017). You abuse but I will stay: The combined effects of job stress, customer abuse, and
emotional intelligence on employee turnover. Journal of Management Development, 36(7), 899-
914.
46. Kashif, M., Samsi, S. Z. M., Awang, Z., & Mohamad, M. (2016). EXQ: measurement of healthcare
experience quality in Malaysian settings: A contextualist perspective. International Journal of
Pharmaceutical and Healthcare Marketing, 10(1), 27-47.
47. Latif, S. A., Bidin, Y. H., & Awang, Z. (2013). Towards the Realization of Green Cities: The
moderating role of the residents’ education level. Procedia-Social and Behavioral Sciences, 85,
646-652.
48. Latif, S. A., Omar, M. S., Bidin, Y. H., & Awang, Z. (2012). Environmental problems and quality of
life: situational factor as a predictor of recycling behaviour. Procedia-Social and Behavioral
Sciences, 35, 682-688.
49. Latif, S. A., Omar, M. S., Bidin, Y. H., & Awang, Z. (2012). Environmental values as a predictor of
recycling behaviour in urban areas: A comparative study. Procedia-Social and Behavioral
Sciences, 50, 989-996.
50. Latif, S. A., Omar, M. S., Bidin, Y. H., & Awang, Z. (2013). Analyzing the effect of situational factor
on recycling behaviour in determining the quality of life. Journal of Asian Behavioural Studies, 3(8).
51. Latif, S. A., Omar, M. S., Bidin, Y. H., & Awang, Z. (2013). Role of environmental knowledge in
creating pro-environmental residents. Procedia-Social and Behavioral Sciences, 105, 866-874.
52. Lau, T. K., Phang, Y. N., & Awang, Z. (2009). Statistics for UiTM. Oxford Fajar.
53. Mohamad, M., & Awang, Z. (2009). Building corporate image and securing student loyalty in the
Malaysian higher learning industry. The Journal of International Management Studies, 4(1), 30-40.

184
A Handbook on SEM
Zainudin Awang - Universiti Sultan Zainal Abidin
54. Mohamad, M., Mohammad, M., Mat Ali, N. A., & Awang, Z. (2016). The impact of life satisfaction on
substance abuse: delinquency as a mediator. International Journal of Adolescence and Youth, 1-
11.
55. Nazim, A., & Afthanorhan, A. (2014). A comparison between single exponential smoothing (SES),
double exponential smoothing (DES), holt’s (brown) and adaptive response rate exponential
smoothing (ARRES) techniques in forecasting Malaysia population. Global Journal of Mathematical
Analysis, 2(4), 276-280.
56. Noor, N. M., Aziz, A. A., Mostapa, M. R., & Awang, Z. (2015). Validation of the Malay version of the
Inventory of Functional Status after Childbirth questionnaire. BioMed research international, 2015.
57. Raston, N. A., Awang, Z., & Hamzah, N. H. (2010). The effects of Information Communication
Technology (ICT) policy on security compliance among department of Irrigation and Drainage (DID)
staff in Kelantan. Journal of Statistical Modeling and Analytics Vol, 1(28-44).
58. Seman, Z., Awang, Z., Jaafar, Z., Nor, N. M., & Ramli, W. K. H. W. (2010). Modelling Production
Capacity of Cheap Efficient Nursery Tank System (CENTS) using Farm Management and
Technical Efficiency: A case of Terengganu.
59. Yusof, Y., Awang, Z., Jusoff, K., & Ibrahim, Y. (2017). The influence of green practices by non-
green hotels on customer satisfaction and loyalty in hotel and tourism industry. International Journal
of Green Economics, 11(1), 1-14.
60. Zainudin, A. (2012). A handbook on SEM: Structural equation modelling using amos graphics.
61. Zainudin, A. (2012). Research Methodology and Data Analysis 5th Edition. Shah Alam: Universiti
Teknologi MARA Publication Centre.
62. Zainudin, A. (2012). Structural equation modeling using AMOS graphic. Shah Alam: Universiti
Teknologi MARA Publication Centre (UPENA).

185

You might also like