Evaluating the Total Quality of Life: Factor Analysis & More

This report explores the factors influencing the total quality of life through an exploratory factor analysis of a quality of life instrument. It begins with an introduction to the concept of quality of life, highlighting its subjective nature and various influencing factors, then develops three hypotheses related to cultural, social environment, and socioeconomic factors. The method section details the research design, including a mixed-method approach, dependent and independent variables, and techniques for assessing construct, content, and criterion validity, as well as reliability using Cronbach's alpha. The results section presents descriptive statistics of the participants, including age and gender distribution. This document, contributed by a student and available on Desklib, provides a comprehensive analysis of the quality of life instrument and its psychometric properties.

RUNNING HEADER: TOTAL QUALITY OF LIFE INFLUENCERS 1
Total quality of life influencers
Student’s name:
Student’s ID:
Institution:

Total quality of life influencers 2
Introduction
According to Fayers & Machin (2013) there has been a lot of focus on the definition
of quality of life in the contemporary years in terms of social policies which in turn
have directed providing care and service provision which impacts positively on the
quality of life of an individual.
According to Buffel, Philipson & Scharf (2012), quality of life is very subjective to
the individual since it is not scientifically measureable. Thus, it depends on an
individual’s ageing experience. Consequently, the term life satisfaction and well-
being are used in many occasions to mean attaining an understanding into the degree
in which a person views how they get to experience quality of life. Hence, various
authors give diverse spheres as the significance though the significance are subjective
to whet the older individual accesses as the most vital feature to them (Nay & Garratt,
2009). Nay & Garratt (2009) argue that the quality of life typically measures general
health, cognitive, emotional, sexual and physical functioning while also measuring
the happiness of the person. However, it is subjective to the individual since what one
person views as vital may vary from another individual. Thus, Zekovic & Renwick
(2003) add that factors such as activities and social networks, employment, self-
identity, cognitive and physical function, and social security should be considered to
impact on life quality.
Standard of living, social networks, and health are vital factors within an individual’s
life though the prominence of the factors differ as an individual continues along their
course of life (Pekmezovic et al., 2011). There are complexities in defining the main
factors within the quality of life as shown by various research sources. The
preliminary reading by the researchers underlined the numerous elements which are

Total quality of life influencers 3
grouped loosely within three sub-themes in relation to the quality of life. The three
sub-themes include physical factors, economic factors and social structure factors.
Stuart-Hamilton (2012) claimed that focusing on a narrow domain can lead to some
domains appearing more vital within the research than they possibly are. Domains
such as income, environment and health have an impact on the life satisfaction of a
person in general and are all inter-related. However, a person’s personality also
impact on how they measure their life satisfaction.
According to Van der Maesen & Walker (2005), quality of life does not have distinct
significant factors thereby making most researchers to focus on environment, health,
relationships and employment. The environment can either reduce or enhance the
quality of life since it embroils social, physical, cultural, and economic elements.
Health entails the general health, mental, emotional and physical health of an
individual. Employment entails income and is related to an individual’s wealth.
According to Sosnowski et al., (2017), the World Health Organisation considers life
to compromise of three components. They include functionality (physical and mental
wellbeing), environment and affiliations (social functioning) and development
(performance of roles in life and general wellbeing). Basically, the quality of life is
the range in which an individual can make use of the opportunities brought by life.
Thus the most important areas in human life are belonging, being and becoming.
Being is comprised of three main domains; psychological being, physical being, and
spiritual being.
It should be noted that the quality of life does not have any distinct key factors. Most
researchers however choose to focus on health, employment, environment, and
relationships. The environment has physical, cultural, economic and social elements
which can enhance or diminish the quality of life. The following study aims at

Total quality of life influencers 4
looking at how the quality of life is impacted by cultural (age, gender), social
environment (marital status) and social economic factors (education and occupation).
Thus, the following hypotheses were developed.
H1: There is an association between the quality of life and cultural factors
H2: There is an association between the quality of life and social environment factors
H3: There is an association between the quality of life and social economic status
Method
The capacity to respond to a research question is as good as the instrument developed
(Cooper & Schindler, 2006). A survey instrument that is well-developed should
provide a researcher with data of high quality in order to answer or solve a problem.
The study aims to test validity aspects of the instrument and reliability. Validity
entails examining how truthful the instruments are. It involves how the instrument
measure what is claims to measure. Generally, researches evaluate validity through
asking of a number of questions and then searching for answers in other researches.
Validity of the instruments will be done through content validity, construct validity
and criterion validity.
Research Design
Research design is the whole approach selected to integrate diverse factors of the
research in a logical and coherent way thus warranting that it will address efficiently
the research problem (Lewis, 2015). The research adopted a mixed-method design.
The method is best stied since it is used in representing more of an approach to
examine a problem than a methodology. The method I characterised through focusing
on research problems that require an examination of real-life contextual
understanding, intentional perspectives and influence of culture and an objective

Total quality of life influencers 5
drawing on the strengths of qualitative and quantitative techniques of techniques of
data gathering in formulating a holistic interpretive framework for creating
conceivable solutions or new problems’ understanding (Tashakkori & Cresswell,
2017).
DV and IV
The dependent variables to be used will be the aggregate scores of the various
components which are used to describe the quality of life. Thus, variables LS1 to
LS32 will be aggregated.
The independent variables include gender, occupation, age, education and marital
status. The age variable is continuous while gender, occupation, educational and
marital status are categorical variables. Gender entails male and female as the two
categories in which male is coded as 0 and female as 1. Occupation entails four
categories which are student, blue collar, grey collar and white collar. The four
categories are coded from 1 to 4 respectively as they represent the various ranks of
the occupation (Burton & Turrel, 2000). Education also entailed four categories
which include primary, secondary, senior secondary and tertiary coded from 1 to 4
respectively. The order of these categories are in line with the order in which
individuals acquire education in Australia. The final independent variable was
marital status. The variable was categories into 4 categories of single, in a
relationship, married/de facto, and separated/divorced/widowed/others from 1 to 4
respectively. The coding is justified as it can be seen to be the levels of
companionship in the society.
Construct validity

Total quality of life influencers 6
Construct is the preliminary notion, concept, hypothesis or question which evaluates
which data is to be collected and how it is to be collected (Hagströmer, Oja, &
Sjöström). Construct validity is the degree in which an instrument evaluates the
theoretical construct or trait which is intended to be measured. In this study, construct
validity will be demonstrated by a 3 factor structure which shows items grouped into
these categories in accordance with the arguments by Sosnowski et al., (2017). The
three factor structure are satisfaction with functionality, environment and affiliations,
and development.
Construct validity was conducted through a factor analysis. Precisely, a Principal
Component Analysis (PCA) was the method of used for the variable reduction
(Jolliffe, 2011). The assumptions made during the test was that there are multiple
variables, there is a linear relationship between all variables, there is sampling
adequacy, the data is suitable for reduction and that there are no significant outliers.
Subsets that loaded strongly on the various components will considered while those
that did not would have to be dropped.
Content validity
Content validity entails the measure in which the instrument measures or assesses the
interested construct fully (Heale & Twycross, 2015). According to Wynd, Schmidt &
Schaefer (2003), the development of a content valid instrument entails achieving it
through an instrument rational analysis by rates (ideally 3 to 5) conversant with the
interested construct. To determine content validity, the following research used
content validity index (CVI). Content validity index is the most widely used when
conducting a quantitative evaluation. CVI entails two types, I-CVI and S-CVI.
Computing a modified kappa statistics can be used in adjusting I–CV for chance

Total quality of life influencers 7
agreement. S-CVI/Ave and S-CVI-UA are both levels of scales for CVI with different
formulas. It is recommended by researchers that a scale with excellent content
validity needs to be composed of I-CVIs of 0.78 or higher and S-CVI/Ave and S-
CVI/UA of 0.9 and 0.8 or higher respectively.
Criterion validity
Criterion validity is evaluated when there is an interest in establishing the association
of scores on a test to a precise criterion. The method of the most powerful tool that is
used in establishing pre-employments validity of tests. A test can be considered to
have criterion validity if it is useful in predicting the behaviour or performance in
another situation. The first measure in a criterion validity test is usually considered as
the predictor variable while the second measure is usually considered as the criterion
variable.
A regression model is used in predicting the value of a variable based on two or more
other variables values (Craig et al., 2003). The variable to be forecasted is usually
referred to as the dependent variable while the variable used in forecasting the value
of the dependent variables are called the independent variables. In this study the tool
used in criterion validity was a Hierarchical multiple regression. A Hierarchical
multiple regression was the most suitable since we are predicting a dependent variable
that entails of count data while there are one or more independent variables. In this
regression, the total quality of life was regressed against age, gender, occupation,
marital status and education.
Reliability
Reliability is the measure in which the results are consistent over a period of time
(Joppe, 2000). Thus, a representation that is accurate of the population under study is

Total quality of life influencers 8
stated to be having the component of reliability. A research instrument is measured as
reliable when the study results can be produced with a similar methodology. A
questionnaire, observation, test or any measurement procedure is considered reliable
if it produces the same results when the trials are repeated (Golafshani, 2003).
Consequently, the degree to which the responses of individual in a survey stay the
same over time is a measure of reliability.
To measure reliability, the Cronbach’s alpha will be used. The Cronbach’s alpha is
commonly used for surveys or questionnaires which have multiple Likert questions
which form a scale. The Cronbach’s alpha reliability coefficient usually ranges from
0 to 1. When the coefficient is closer to 1, it can be deduced that internal consistency
of the items or variables is great. The Cronbach’s alpha usually increases as the
number of items increases. Consequently, it also increases as the average inter-item
correlations increase, that is, when holding the number of items is constant.
According to (Tavakol & Dennick, 2011), a Cronbach’s alpha that is greater than 0.7
is considered acceptable in most social science research situations. In the study, the
various variables were loaded into their respective factors. Then the average scores of
the four factors were obtained. From the results, the average score were subjected to a
reliability test by obtaining the Cronbach’s alpha.
Results
Descriptive statistics
The number of participants in this survey was 361. The descriptive statistics of the
participants’ age is as shown below:
Table 1: Age descriptive statistics
Minimum Maximum Mean Std. Deviation
16 83 32.9 15.047

Total quality of life influencers 9
The mean age of the participants was 32.9 with a standard deviation of 15. The figure
below shows the distribution of the participants by gender.
Figure 1: Gender
It is evident that most of the participants were female with a representation of 67%.
On the other hand, the male participants had a representation of 33%.
Figure 3: Education
Majority of the participants whether undertaking or had completed education at the
tertiary level (68%). Those who had reached senior secondary were second with 27%

Total quality of life influencers 10
while those with secondary education had a representation of 5%. The primary level
of education was represented by 0%.
Figure 4: Occupation
From figure 4 above, it can be seen that most of the participants were undertaking
grey collar jobs (31%) closely by those with white collar jobs (36%). Students had a
representation of 24% while the blue collar jobs were the least presented with 9%.
Figure 5: Marital Status

Total quality of life influencers 11
As seen above, majority of the participants were single (47%) while those married or
in de facto relationships were represented by 37% of the participants. The least
presented people were those in a relationship (9%) and those who were separated,
divorced, widowed or others (7%).
Factor Analysis
The results of the construct validity are as shown below.
Table 2: Total Variance Explained

Total quality of life influencers 12
Table 2 above showed the actual factors that were extracted. The rotation sums of
squared loadings shows only those factors that met the cut-off criterion (extraction
method). It is seen that there were three factors with eigenvalues that were greater
than 1. The percentage of variance shows how much of the total variability can be
accounted for by each of these factors. That is factor 1 accounts for 21.7% of the

Total quality of life influencers 13
variability, factor 2 accounts for 12.59% of the variability while factor 3 accounts for
9.48% of the variability.
Figure 6: Scree plot
Figure 6 above shows the scree plot of the component analysis. Consequently, it was
seen that the slope of the curve started to flat out after factor 3.
Table 3: Rotated Component Matrix

Total quality of life influencers 14
From table 3 above, the factor loading can be observed. The coding in bold are the
components that loaded strongly into the factors.
Content Validity Index

Total quality of life influencers 15
Table 5: I-CVI
S-CVI/Ave 0.82
Total Agreement 0
S-CVI/UA #DIV/0!
From table 5 above, it is evident that the variables do not meet the recommendation
of most researchers of having an S-CVI/Ave of 0.82. However, the S-CVI/AU was
not applicable since there were no total agreement among the raters. However,
decision should not be based on S-CVI/AU intuitively since the value of S–CVI/Ave
can be considered to be high at 0.82.
Cronbach’s alpha
The results of the reliability test is as shown below:
Table 6: Reliability test
Table 6 shows that the Cronbach’s alpha is 0.91. Thus, there is a high level of internal
consistency for this scale. Thus, the construct is indeed reliable.
Hierarchical multiple regression
The results of the hierarchical multiple regression carried out are as shown below.
Table 7: Model summary

Total quality of life influencers 16
From the model summary in table 7 above, it is seen that the Durbin-Watson test was
2.225. The test result is between the values of 1.5<d<2.5. Thus, it is safe to say that
there was no linear auto-correlation of the first order in our hierarchical multiple
regression data.
Consequently, the results shows that the accounted variance (R2) with the first two
indicators (age and gender) was equal to 0.0007 (adjusted R2 = 0.0001). However, it
was observed that this was not significantly different from 0 (F(2,293) = 1.025, p>0.05.
Socio-economic factors (education and occupation) was factored into the regression
equation. The change in accounted variance (DR2) was equal to 0.012. Likewise, this
was not a statistically significant increase in the accounted variance from the step one
model (DF(2,291) = 1.77, p > 0.05. In step three, social environment factors (marital
status) were factored into the regression model. The change in accounted variance
(DR2) was equal to 0.55. However, this was not a statistically significant increase in
accounted variance by the previous predictor variables entered in the second step (DF
(1,290) = 0.55, p>0.05.
Table 7: Coeicients
From table 7 above, it can be seen that at the 5% confidence interval no variable was
statistically significant. All the other factors of social economic factors (age, gender),

Total quality of life influencers 17
social environment factors (marital status) and cultural factors (age and gender) were
not statistically significant.
Table 8: Hierarchical Regression Analysis Evaluating Quality of Life Predictors
Discussion
The survey instrument used in gathering data proved to be indeed valid and reliable.
Indeed, the survey instrument passed the construct validity test, criterion validity test,
content validity test and the reliability test. The World Health Organisation classifies
quality of life into three components. Through construct validity, the variables were
all found to load heavily on their various components as seen in table 3. From the
hierarchical multiple regression it was observed that none of the predictors was
statistically significant. Thus, there are no coefficients which are interpretable. If
there were statistical significance in any of the betas, then it would be possible to use
the weights of the betas and multiply them with every individual person’s score on
the independent variable in order to get what individuals predicted score are on the
dependent variable.
Future researchers should consider more underlying factors in carrying out a similar
study. As a result, they will be able to determine the exact association between the

Total quality of life influencers 18
variables. The number of participants should also be increased in order to avoid bias
in future.
References
Buffel, T., Phillipson, C., & Scharf, T. (2012). Ageing in urban environments:
Developing ‘age-friendly’cities. Critical Social Policy, 32(4), 597-617.
Burton, N. W., & Turrell, G. (2000). Occupation, hours worked, and leisure-time
physical activity. Preventive medicine, 31(6), 673-681.
Cooper, D. R., Schindler, P. S., & Sun, J. (2006). Business research methods (Vol.
9). New York: McGraw-Hill Irwin.
Craig, C. L., Marshall, A. L., Sjorstrom, M., Bauman, A. E., Booth, M. L.,
Ainsworth, B. E., ... & Oja, P. (2003). International physical activity
questionnaire: 12-country reliability and validity. Medicine and science in
sports and exercise, 35(8), 1381-1395.

Total quality of life influencers 19
Fayers, P. M., & Machin, D. (2013). Quality of life: the assessment, analysis and
interpretation of patient-reported outcomes. John Wiley & Sons.
Golafshani, N. (2003). Understanding reliability and validity in qualitative
research. The qualitative report, 8(4), 597-606.
Hagströmer, M., Oja, P., & Sjöström, M. (2006). The International Physical Activity
Questionnaire (IPAQ): a study of concurrent and construct validity. Public
health nutrition, 9(6), 755-762.
Heale, R., & Twycross, A. (2015). Validity and reliability in quantitative
studies. Evidence-based nursing, ebnurs-2015.
Jolliffe, I. (2011). Principal component analysis. In International encyclopedia of
statistical science (pp. 1094-1096). Springer, Berlin, Heidelberg.
Joppe, G. (2000). Testing reliability and validity of research instruments. Journal of
American Academy of Business Cambridge, 4(1/2), 49-54.
Lewis, S. (2015). Qualitative inquiry and research design: Choosing among five
approaches. Health promotion practice, 16(4), 473-475.
Nay, R., & Garratt, S. (2009). Older people: Issues and innovations in care. Elsevier
Australia.
Pekmezovic, T., Popovic, A., Tepavcevic, D. K., Gazibara, T., & Paunic, M. (2011).
Factors associated with health-related quality of life among Belgrade
University students. Quality of life research, 20(3), 391-397.
Sosnowski, R., Kulpa, M., Ziętalewicz, U., Wolski, J. K., Nowakowski, R., Bakuła,
R., & Demkow, T. (2017). Basic issues concerning health-related quality of
life. Central European journal of urology, 70(2), 206.
Stuart-Hamilton, I. (2012). The psychology of ageing: An introduction. Jessica
Kingsley Publishers.

Total quality of life influencers 20
Tashakkori, A., & Creswell, J. W. (2007). The new era of mixed methods
[Editorial]. Journal of mixed methods research, 1(1), 3-7.
Tavakol, M., & Dennick, R. (2011). Making sense of Cronbach's alpha. International
journal of medical education, 2, 53.
Van der Maesen, L. J., & Walker, A. C. (2005). Indicators of Social Quality. The
European Journal of Social Quality, 5(1-2), 8-24.
Wynd, C. A., Schmidt, B., & Schaefer, M. A. (2003). Two quantitative approaches
for estimating content validity. Western Journal of Nursing Research, 25(5),
508-518.
Zekovic, B., & Renwick, R. (2003). Quality of life for children and adolescents with
developmental disabilities: Review of conceptual and methodological issues
relevant to public policy. Disability & Society, 18(1), 19-34.