<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Archiving and Interchange DTD v1.0 20120330//EN" "JATS-archivearticle1.dtd">
<article xmlns:xlink="http://www.w3.org/1999/xlink">
  <front>
    <journal-meta />
    <article-meta>
      <title-group>
        <article-title>An Empirical Study on E-government Adoption in Vietnam: Moderating Role of Uncertainty Avoidance*</article-title>
      </title-group>
      <contrib-group>
        <contrib contrib-type="author">
          <string-name>Thi-Thanh-Thao Vo</string-name>
          <xref ref-type="aff" rid="aff0">0</xref>
        </contrib>
        <contrib contrib-type="author">
          <string-name>Phuoc-Cuu-Long Le</string-name>
          <xref ref-type="aff" rid="aff0">0</xref>
        </contrib>
        <aff id="aff0">
          <label>0</label>
          <institution>Copyright © by the paper's authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0). In: N. D. Vo, O.-J. Lee, K.-H. N. Bui</institution>
          ,
          <addr-line>H. G. Lim, H.-J. Jeon, P.-M. Nguyen, B. Q. Tuyen, J.-T. Kim, J. J. Jung</addr-line>
          ,
          <institution>T. A. Vo (eds.): Proceedings of the 2nd International Conference on Human-centered Artificial Intelligence (Computing4Human 2021)</institution>
          ,
          <addr-line>Da Nang</addr-line>
          ,
          <country country="VN">Viet Nam</country>
          ,
          <addr-line>28-October-2021, published at</addr-line>
        </aff>
        <aff id="aff1">
          <label>1</label>
          <institution>Vietnam - Korea University of Information and Communication Technology, The University of Danang</institution>
          ,
          <addr-line>Danang</addr-line>
          ,
          <country country="VN">Vietnam</country>
        </aff>
      </contrib-group>
      <fpage>49</fpage>
      <lpage>56</lpage>
      <abstract>
        <p>With the aims to improve government productivity and meet the citizens' requirements, E-government has gained incredible popularity in many nations worldwide. Vietnam has established an E-government to enhance the quality of its public services for many years. Exploring factors affecting Egovernment adoption in Vietnam has drawn significant attention from many scholars; however, considering the effect of national culture in general, especially the uncertainty avoidance dimension, is still a shortage of studies. Therefore, based on the UTAUT model, this study explores the determinants of usage behavior and the moderating role of uncertainty avoidance dimension to usage behavior of citizens in E-government services in Vietnam. The results show that performance expectancy, effort expectancy, social influence have significant impacts on behavioral intention toward E-government usage behavior, and facilitating conditions play an essential role in forming E-government usage behavior. Moreover, uncertainty avoidance was found to be a moderator to the relationship between social influence and behavioral intention to use E-government.</p>
      </abstract>
      <kwd-group>
        <kwd>E-government</kwd>
        <kwd>UTAUT</kwd>
        <kwd>Uncertainty Avoidance</kwd>
      </kwd-group>
    </article-meta>
  </front>
  <body>
    <sec id="sec-1">
      <title>-</title>
      <p>
        E-government is defined as "the use by government agencies of information
technologies (such as wide area networks, Internet, and mobile computing) that can transform
relations with citizens, businesses, and other arms of government. These technologies
can serve various ends: better delivery of government services to citizens, improved
interactions with business and industry, citizen empowerment through access to
information, or more efficient government management. The resulting benefits can be less
corruption, increased transparency, greater convenience, revenue growth, and cost
reductions" [
        <xref ref-type="bibr" rid="ref1">1</xref>
        ]. Especially under the domination of the Covid-19 pandemic, the
importance of E-government has been shown off significantly by solving a bunch of issues
for citizens, including disseminating information, performing contact tracing,
conducting online transactions, etc. make citizens' life much more convenient. Vietnam has
developed E-government system with many initiatives since 2009 [
        <xref ref-type="bibr" rid="ref2">2</xref>
        ]. With an overall
score of 0.66 on the E-government Development Index (EGDI), Vietnam was ranked
86th out of 193 countries in 2020, moved up two places from 2018 [
        <xref ref-type="bibr" rid="ref3">3</xref>
        ]. In the Southeast
Asia region, Vietnam’s EGDI in 2020 was ranked 6th behind Singapore, Malaysia,
Thailand, Brunei, and the Philippines. Vietnam E-government is aspired to be among
the top four in the Southeast Asia region by 2025 [
        <xref ref-type="bibr" rid="ref3">3</xref>
        ]. Up to now, the E-government
portal has provided 6,800 administrative procedures at four levels of public services
and received more than 116 million visits and over 468,000 registered accounts [
        <xref ref-type="bibr" rid="ref4">4</xref>
        ].
Thus, attracting citizens using E-government services has become a priority task to sync
the public administration and E-government services with the participation of entire
citizens to enhance the productivity and efficiency of government services. Therefore,
research investigating determinants of E-government usage behavior is necessary not
only for a theoretical aspect but also for a practical one. Exploring factors affecting
Egovernment adoption has drawn significant attention from many scholars; however,
considering the effect of national culture in general, especially the uncertainty
avoidance dimension, is still a shortage of studies. This study attempts to fill the gap by
discovering which factors affect E-government usage behavior in Vietnam and the
impact of uncertainty avoidance dimension to the E-government adoption. To do that, this
study aims to address two main research questions (1) Which factors have influences
on citizens’ usage behaviors in E-government services in Vietnam?, and (2) How does
the uncertainty avoidance dimension have an influence on citizens’ usage behavior in
E-government services in Vietnam? An examination into these two research questions
would help to discover the most affecting factors as well as their effects on Vietnamese
usage behavior in E-government, from that, suggesting solutions for the Vietnam
government to attract citizens joining E-government services.
2
2.1
      </p>
    </sec>
    <sec id="sec-2">
      <title>Literature Review</title>
      <sec id="sec-2-1">
        <title>The Unified Theory of Acceptance and Use of Technology</title>
        <p>
          The Unified Theory of Acceptance and Use of Technology (UTAUT), which
Venkatesh and others developed, is one of the most recent developments in general
technology acceptance models [
          <xref ref-type="bibr" rid="ref2">2</xref>
          ]. UTAUT was first synthesized and developed in 2003
aiming to explain user’s intention to use an information system and subsequent usage
behavior based on four fundamental constructs: performance expectancy, effort
expectancy, social influence, and facilitating conditions. Performance expectancy, effort
expectancy, and social influence are direct determinants of behavioral intention toward
usage behavior; meanwhile, facilitating conditions is a direct determinant of usage
behavior. Moreover, the impact of four primary constructs on behavioral intention and
        </p>
        <p>
          An Empirical Study on E-government Adoption in Vietnam 51
usage behavior is moderated by gender, age, experience, and voluntariness of use [
          <xref ref-type="bibr" rid="ref5">5</xref>
          ].
And because of its synthetic, UTAUT was chosen as a base model in this research.
2.2
        </p>
      </sec>
      <sec id="sec-2-2">
        <title>National Culture</title>
        <p>
          Culture is defined as “the collective programming of the mind that distinguishes the
members of one group or category of people from another” [
          <xref ref-type="bibr" rid="ref6">6</xref>
          ]. Citizens' shapes values,
beliefs, perceptions, expectations, assumptions, and behaviors that distinguish people
of one country from others are all parts of national culture [
          <xref ref-type="bibr" rid="ref2">2</xref>
          ]. The cultural dimensions
theory which Geert Hofstede developed illustrates the impacts of a society's cultures on
its members' values and the relations between these values and behavior by using a
structure drawn from the factor analysis [
          <xref ref-type="bibr" rid="ref7">7</xref>
          ]. Hofstede's cultural dimensions theory has
been used extensively in IT/IS research to discover the relationship between national
culture and E-government adoption. According to Hofstede's theory, dimensions of
national cultures include Power distance, Individualism vs. collectivism, Uncertainty
avoidance, Masculinity vs. femininity, Long-term orientation vs. short-term
orientation, Indulgence vs. restraint. This research used Uncertainty Avoidance dimensions
from Hofstede's theory to examine its moderating role on determinants of
E-government usage behavior in Vietnam.
3
        </p>
      </sec>
    </sec>
    <sec id="sec-3">
      <title>Research model and Hypotheses</title>
      <p>
        Based on the prior studies, the research model was proposed (see Fig. 1). In the
Egovernment context, performance expectancy is measured by citizens’ benefits
perceptions when using E-government services, including convenience, time-saving, effort
reduction, service quality improvement, etc. [
        <xref ref-type="bibr" rid="ref8">8</xref>
        ]. The positive influence of performance
expectancy on behavioral intention in E-government has been confirmed in many
studies [2; 8]. Effort expectancy in the E-government context is measured by citizens’
awareness about the ease of use of E-government services [
        <xref ref-type="bibr" rid="ref8">8</xref>
        ]. Users will have
behavioral intention to use the system, which requires less effort when using it. Social
influence is defined as how people believe that their essential people think they should use
the system [
        <xref ref-type="bibr" rid="ref5">5</xref>
        ]. It means that an individual’s behavioral intention is affected by the
important people or close to them. The positive impact of social influence on behavioral
intention was found in several studies [2; 9]. Citizens would be more likely to use
Egovernment services if they know that their family, colleagues, friends already used
them. Facilitating conditions can be known as informing, training, encouraging citizens,
and supporting them when they have difficulties using E-government services. The
positive influence of facilitating conditions on E-government services usage behavior has
been found out [
        <xref ref-type="bibr" rid="ref2">2</xref>
        ]. Behavioral intention refers to the subjective probability of an
individual that he/she would form an actual behavior in the future [
        <xref ref-type="bibr" rid="ref5">5</xref>
        ]. It has been
discovered that an individual’s behavioral intention to use E-government directly affects their
usage behavior [2; 8]. Uncertainty avoidance is defined as the extent to which citizens
of a country/culture/organization are threatened by unknown or uncertain situations [
        <xref ref-type="bibr" rid="ref6">6</xref>
        ].
Citizens in low uncertainty avoidance cultures are willing to take risks and make their
own decisions [
        <xref ref-type="bibr" rid="ref10">10</xref>
        ]. Meanwhile, people in high uncertainty avoidance cultures are not
comfortable in unknown or uncertain situations, and they do not want to approach new
things due to their perceptions [
        <xref ref-type="bibr" rid="ref11">11</xref>
        ]. People in countries with low uncertainty avoidance
are willing to approach new technological innovation than cultures with high
uncertainty avoidance [
        <xref ref-type="bibr" rid="ref7">7</xref>
        ]. As E-government is applying ICTs into the government’s
operations, this research aims to explore the impact of uncertainty avoidance on
E-government adoption in Vietnam. Therefore, this study proposes the following hypotheses:
H1: Performance expectancy (PE) has a positive impact on behavioral intention to use
(BI) E-government services.
      </p>
      <p>H2: Effort expectancy (EE) has a positive impact on behavioral intention to use (BI)
Egovernment services.</p>
      <p>H3: Social influence (SI) has a positive impact on behavioral intention to use (BI)
Egovernment services.</p>
      <p>H4: Facilitating condition (FC) has a positive impact on E-government services usage
behavior (UB).</p>
      <p>H5: Behavioral intention (BI) has a positive impact on E-government services usage
behavior (UB).</p>
      <p>
        H6: Uncertainty avoidance affects the impacts among factors in the research model.
The survey by questionnaires methodology was used to collect data. Based on variables
adapted from prior studies, a self-administered questionnaire was developed. This
study’s subjects are users who have been using E-government services in Vietnam. Out
of 248 self-administered questionnaires distributed, 232 questionnaires were valid for
data analysis. The data analysis was conducted by SPSS 22 and AMOS 20.
Reliability Analysis. All the Cronbach's alpha values are greater than 0.8, indicating
the high reliability of the scale [
        <xref ref-type="bibr" rid="ref12">12</xref>
        ] (see Table 1).
      </p>
      <p>An Empirical Study on E-government Adoption in Vietnam 53</p>
      <p>PE</p>
      <p>EE</p>
      <p>SI</p>
      <p>FC</p>
      <p>BI</p>
      <p>
        UB
Model fit. Table 2 presents the model fit of the research, including the standard-fit
indices (the suggested values) and the measurement model’s fitness test outcomes. The
results show that all the model-fit indices satisfy their respective acceptance criteria
indicated in the previous literature [
        <xref ref-type="bibr" rid="ref13">13</xref>
        ].
Hypotheses Test. As shown in Table 3, all the hypotheses (H1, H2, H3, H4, and H5)
are supported with p-values are less than 0.05 [
        <xref ref-type="bibr" rid="ref13">13</xref>
        ]. It means that performance
expectancy, effort expectancy, and social influence all have significant impacts on
behavioral intention; facilitating conditions and behavioral intention were found to have
substantial effects on usage behavior.
BI
BI
BI
UB
UB
      </p>
      <p>Hypotheses




</p>
      <p>PE
EE
SI
FC
BI</p>
      <p>Estimate
.172
.565
.154
.431
.227
Moderator Test. To determine whether Uncertainty Avoidance can be the moderator
of the impacts among factors in the research model, the authors conducted the MSEM
test. The results show that Uncertainty Avoidance can affect the impacts among factors
in the research model, hypothesis 6 is supported. To test the impact of the moderator,
the authors divided the moderator into two groups (high and low) to examine the
difference. As shown in Table 4, under the moderator of Uncertainty Avoidance, there
is a difference in Social Influence on Behavioral intention between the two groups.</p>
      <p>BI
BI
BI
UB
UB




</p>
      <p>PE
EE
SI
FC
BI</p>
      <p>Estimate
0.151
This study presented a research framework of E-government usage behavior based on
the UTAUT model to test the moderating role of the uncertainty avoidance dimension.
Based on the outcomes, effort expectancy has the highest impact on behavioral
intention with β = 0.565, p &lt; 0.001, follow by performance expectancy and social influence
with β = 0.172, p = 0.04 and β = 0.154, p = 0.018, respectively. The results are
consistent with other studies [5; 8]. It can be said that the first factor that affects citizens
forming their behavioral intention to use E-government services is the ease of use of
these services, the second factor is the usefulness or benefits which are brought by using
E-government services, and the last one is the influence of society. When citizens know
that the E-government services require less effort to use, they can access these services
anywhere, anytime if they have Internet and smart devices along, they will have the
intention to use it. In addition, citizens have perceptions about E-government services
and their benefits such as time-saving, cost-saving, convenience, transparency,
up-todate information, which can reinforce their intention to use. Finally, the influence of
society, the opinions of others can affect citizens' behavioral intention to use
E-government services. Therefore, to increase the participation of citizens in E-government
services, the administrators should design the E-government system simply for citizens to
be able to use it easily and ensure the adequacy and flagrant of information. Facilitating
conditions was found to strongly impact usage behavior with β = 0.431, p &lt; 0.001.
Obviously, when citizens get supports, guidance from organizations and the
government in using E-government services, they are willing to take a chance toward using it.
Hence, organizing conferences and workshops about E-government services in
institutions, companies, etc., to raise citizens' awareness is necessary. Moreover, actively
propagating about E-government services and their benefits in living areas by
distributing printed documents introducing E-government services and guiding how to use
Egovernment services can be considered an efficient method for encouraging citizens'
participation. E-government usage behaviors of citizens are affected by the uncertainty
avoidance dimension. From the results, there is no difference in perceiving the
usefulness, ease of use, and getting support in using E-government services between two
groups: high and low uncertainty avoidance. Meanwhile, there is a difference between
high and low uncertainty avoidance groups regarding social influence. People in the
low uncertainty avoidance group with β = 0.032 have not been affected much by society
than people in the high one (β = 0.409). People with high uncertainty avoidance tend to
avoid changes, afraid of trying something new; hence, they need to be convinced and</p>
      <p>
        An Empirical Study on E-government Adoption in Vietnam 55
affected much more by their associated people to use the E-government services.
Meanwhile, people in the low uncertainty avoidance group are kind of willing to take risks
to try innovation technology, so they do not need many opinions of others to use
Egovernment services; they can decide it by themselves. The more associate people using
E-government services, the more people in high uncertainty avoidance will follow.
Egovernment in Vietnam is now in level 4, allowing citizens to fill and submit forms and
pay fees online, even though it is still shortcoming and limited. Still, Vietnam
E-government has become a bright spot in governmental operation, especially in 2020 [
        <xref ref-type="bibr" rid="ref4">4</xref>
        ].
Till 2020, there have been over 940,000 administrative documents were processed
online using the E-government system; a total amount of 26.7 billion VND was made
with 67,000 e-payment transactions. Especially each year, the E-government portal has
saved more than VND 8.1 trillion, along with over VND 1.2 trillion each year in paper
and delivery costs [
        <xref ref-type="bibr" rid="ref4">4</xref>
        ]. With the current advantages, the popularity of E-government to
entire Vietnam citizens is not in the far future; therefore, administrators should have
appropriate strategies and policies to encourage citizens to take part in E-government
services. While the outcomes of this research contribute to a deeper understanding of
the E-government usage behavior in Vietnam, this research still has some limitations
that should be noted to leave open future research directions. First is the limit in the
size of sample data. Hence, future research can expand the sample of data in different
regions, in other countries, or other cultural backgrounds. Second, this research used
the UTAUT model as the core model to investigate the E-government usage behavior,
which led to the insufficiency of other factors affecting usage behaviors; hence future
research should consider more determinants to broaden and complete the study.
      </p>
    </sec>
  </body>
  <back>
    <ref-list>
      <ref id="ref1">
        <mixed-citation>
          1.
          <string-name>
            <given-names>World</given-names>
            <surname>Bank.: E- Governments</surname>
          </string-name>
          (
          <year>2012</year>
          ). http://web.worldbank.org/
        </mixed-citation>
      </ref>
      <ref id="ref2">
        <mixed-citation>
          2.
          <string-name>
            <surname>Vo</surname>
          </string-name>
          , T. T. T.,
          <string-name>
            <surname>Lee</surname>
            ,
            <given-names>J. K.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Lee</surname>
            ,
            <given-names>S.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Gim</surname>
            ,
            <given-names>G.</given-names>
          </string-name>
          , &amp;
          <string-name>
            <surname>Kim</surname>
            ,
            <given-names>J. B.</given-names>
          </string-name>
          :
          <article-title>A Study on the Effect of the National Culture on the E-government Usage Behavior in Vietnam</article-title>
          . International Information Institute (Tokyo).
          <source>Information</source>
          <volume>19</volume>
          (
          <issue>7A</issue>
          ),
          <volume>2613</volume>
          (
          <year>2016</year>
          ).
        </mixed-citation>
      </ref>
      <ref id="ref3">
        <mixed-citation>
          3.
          <string-name>
            <given-names>United</given-names>
            <surname>Nations.: UN E-Government</surname>
          </string-name>
          <string-name>
            <surname>Survey</surname>
          </string-name>
          2020
          <source>Report</source>
          (
          <year>2020</year>
          ).
        </mixed-citation>
      </ref>
      <ref id="ref4">
        <mixed-citation>
          4.
          <string-name>
            <given-names>Khanh</given-names>
            <surname>Phuong</surname>
          </string-name>
          .:
          <string-name>
            <surname>Five-year Implementation Of E-Government Development Reviewed</surname>
          </string-name>
          (
          <year>2021</year>
          ). http://news.chinhphu.vn/Home/Fiveyear-Implementation-
          <article-title>Of-</article-title>
          <string-name>
            <surname>EGovernment-</surname>
          </string-name>
          Development-Reviewed/20213/43183.vgp
        </mixed-citation>
      </ref>
      <ref id="ref5">
        <mixed-citation>
          5.
          <string-name>
            <surname>Venkatesh</surname>
            ,
            <given-names>V.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Morris</surname>
            ,
            <given-names>M. G.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Davis</surname>
            ,
            <given-names>G. B.</given-names>
          </string-name>
          , &amp;
          <string-name>
            <surname>Davis</surname>
            ,
            <given-names>F. D.:</given-names>
          </string-name>
          <article-title>User acceptance of information technology: Toward a unified view</article-title>
          .
          <source>MIS Quarterly</source>
          <volume>27</volume>
          (
          <issue>3</issue>
          ),
          <fpage>425</fpage>
          -
          <lpage>478</lpage>
          (
          <year>2003</year>
          ).
        </mixed-citation>
      </ref>
      <ref id="ref6">
        <mixed-citation>
          6.
          <string-name>
            <surname>Hofstede</surname>
            ,
            <given-names>G.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Hofstede</surname>
            ,
            <given-names>G. J.</given-names>
          </string-name>
          , &amp;
          <string-name>
            <surname>Minkov</surname>
            ,
            <given-names>M.</given-names>
          </string-name>
          :
          <article-title>Cultures and organizations: Software of the mind</article-title>
          . New York: Mcgraw-hill (
          <year>2005</year>
          ).
        </mixed-citation>
      </ref>
      <ref id="ref7">
        <mixed-citation>
          7.
          <string-name>
            <surname>Hofstede</surname>
          </string-name>
          , G.:
          <article-title>Culture's consequences: Comparing values, behaviors, institutions and organizations across nations</article-title>
          .
          <source>Sage Publications</source>
          (
          <year>2001</year>
          ).
        </mixed-citation>
      </ref>
      <ref id="ref8">
        <mixed-citation>
          8.
          <string-name>
            <surname>AlAwadhi</surname>
            ,
            <given-names>S.</given-names>
          </string-name>
          , &amp;
          <string-name>
            <surname>Morris</surname>
            ,
            <given-names>A.</given-names>
          </string-name>
          :
          <article-title>The Use of the UTAUT Model in the Adoption of E-government Services in Kuwait</article-title>
          .
          <source>Proceedings of the 41st annual Hawaii International Conference on System Sciences (HICSS</source>
          <year>2008</year>
          ). pp.
          <fpage>219</fpage>
          -
          <lpage>219</lpage>
          . Waikoloa,
          <string-name>
            <surname>HI</surname>
          </string-name>
          , USA (Jan
          <year>2008</year>
          ).
        </mixed-citation>
      </ref>
      <ref id="ref9">
        <mixed-citation>
          9.
          <string-name>
            <surname>Lu</surname>
            ,
            <given-names>J.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Yu</surname>
            ,
            <given-names>C. S.</given-names>
          </string-name>
          , Liu,
          <string-name>
            <given-names>C.</given-names>
            , &amp;
            <surname>Yao</surname>
          </string-name>
          ,
          <string-name>
            <surname>J. E.</surname>
          </string-name>
          :
          <article-title>Technology acceptance model for wireless Internet</article-title>
          .
          <source>Internet research 13(3)</source>
          ,
          <fpage>206</fpage>
          -
          <lpage>222</lpage>
          (
          <year>2003</year>
          ).
        </mixed-citation>
      </ref>
      <ref id="ref10">
        <mixed-citation>
          10.
          <string-name>
            <surname>McCoy</surname>
            ,
            <given-names>S.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Galletta</surname>
            ,
            <given-names>D. F.</given-names>
          </string-name>
          , &amp;
          <string-name>
            <surname>King</surname>
            ,
            <given-names>W. R.</given-names>
          </string-name>
          :
          <article-title>Applying TAM across cultures: the need for caution</article-title>
          .
          <source>European Journal of Information Systems</source>
          <volume>16</volume>
          (
          <issue>1</issue>
          ),
          <fpage>81</fpage>
          -
          <lpage>90</lpage>
          (
          <year>2007</year>
          ).
        </mixed-citation>
      </ref>
      <ref id="ref11">
        <mixed-citation>
          11.
          <string-name>
            <surname>Arslan</surname>
            ,
            <given-names>A.</given-names>
          </string-name>
          :
          <article-title>Cross-cultural analysis of European e-government adoption</article-title>
          .
          <source>World Applied Sciences Journal</source>
          <volume>7</volume>
          (
          <issue>9</issue>
          ) (
          <year>2009</year>
          ).
        </mixed-citation>
      </ref>
      <ref id="ref12">
        <mixed-citation>
          12.
          <string-name>
            <surname>Straub</surname>
            ,
            <given-names>D. W.</given-names>
          </string-name>
          :
          <article-title>Validating instruments in MIS research</article-title>
          .
          <source>MIS Quarterly</source>
          <volume>13</volume>
          (
          <issue>2</issue>
          ),
          <fpage>147</fpage>
          -
          <lpage>169</lpage>
          (
          <year>1989</year>
          ).
        </mixed-citation>
      </ref>
      <ref id="ref13">
        <mixed-citation>
          13.
          <string-name>
            <surname>Hair</surname>
            ,
            <given-names>J. F.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Black</surname>
            ,
            <given-names>W. C.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Babin</surname>
            ,
            <given-names>B. J.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Anderson</surname>
            ,
            <given-names>R. E.</given-names>
          </string-name>
          , &amp;
          <string-name>
            <surname>Tatham</surname>
            ,
            <given-names>R. L.</given-names>
          </string-name>
          :
          <article-title>Multivariate data analysis</article-title>
          .
          <source>Upper Saddle River</source>
          , NJ: Prentice hall (
          <year>1998</year>
          ).
        </mixed-citation>
      </ref>
    </ref-list>
  </back>
</article>