Individual Difference Research Project
There has been advanced research in the development of parameters in psychology that measure various personality traits such as conscientiousness, extraversion, openness to experience, neuroticism and aggressiveness (Eggen, 1999). However, there have been little research in evaluating and testing more complex traits namely submissiveness, moral absolutism and perfectionism. The study attempts to develop a questionnaire that looks into the three complex personality traits. It develops questions that measure the traits, giving a method that show the relationship between each question and the traits that the individual is most likely to have. It evaluates the effectiveness of the questionnaire and whether it can be applied in personality testing. It uses quantitative methods and factor analysis in evaluating the questionnaire. After evaluating the viability of the questionnaire, the study makes recommendations for future research, describing whether such an evaluation can be used for general personality assessment.
Over the years, psychologists have developed questionnaires that assist people in determining their personality traits. The questions are set to elicit a specific kind of response from a person based on their perceptions on different issues as well as how likely they are to behave in different situations. The most common types of personality tests include the Seven Factor Personality Questionnaire, the Revised NEO Personality Inventory as well as the Woodsworth Personal Data Sheet as well as the Myers Briggs’ personality test (First & Taylor, 2007). Each of the questionnaires enables self-inventory, such that a person is able to answer the questions based on how they feel on a specific issue. According to Poropat (2012), after answering the questions, the tabulated data makes it easier to determine the personality traits, based on the relationship between the questions. The answers in each question are all connected to give a specific trait (Hines, 2003). The responses that the individual give are analyzed to show specific characteristics. Some of the adjectives that psychologists have researched on include conscientiousness, being an extrovert or introvert, behaving based on experience, aggressiveness and neuroticism (Pietense et al, 2010). They are some of the areas where advanced research has been carried out and questionnaires developed to differentiate between various personalities with proper tools to define each characteristic.
With advancement in psychological research, however, there are other personality traits that are yet to have sufficient tools to define the associated behavior and emotion (Roberts & Delvechio, 2000). Such tools present a challenge in identifying the appropriate question whose answer can be linked to the personality trait (McGhee, 2008). They include perfectionism, moral absolutism and submissiveness. The three traits lack a proper methodology of assessment, since there are various factors that the psychologist has to consider (Zuckerman, 2007). When evaluating perfectionism, for example, the psychologist has to consider whether the individual plans ahead for all the daily activities (Gosling, 2001). The questionnaire must also inquire whether the person seeks to perform their tasks to perfection or is keen only on completing a specific activity. Perfectionism also looks into the emotion elicited when an activity is done to one’s level best or the desired outcome is achieved, according to Ones (2009). The person possessing the trait will be happy when he or she is able to complete the task on time and does it based on the required quality (Simpson, 2005). When developing the questionnaire, such questions must be present as they assess the factors necessary to evaluate individual behavior and how perfect the wish to complete a task or plan ahead to schedule all activities.
Moral absolutism is also uncommon factor personality tests. It refers to a trait whereby the individual has a critical view whether an action is either morally right or wrong. Karon (2000) asserts that a person with this personality trait is able to identify the morally right or wrong behavior based on various justifications such as religion, philosophy, social norms or other methodologies (Irbina, 2014). An individual with absolutism has a given characteristic that they identify specific as being either good or bad regardless of the objective (Karon, 2000). For example, stealing can be termed as an immoral action regardless of whether it is for the well-being of others, such as taking food from a wealthy household and giving it to the poor (Boyle et al, 2015). When creating a questionnaire to determine moral absolutism, the researcher should consider questions that may have a differing answer to people (Olivola & Todolov, 2010). For example, one may inquire whether killing is justified for a soldier, given that the individual is facing other enemies in the battlefield or defending innocent civilians. A person with moral absolutism will strongly agree that such an action is not justified in any circumstance. (Mischel & Shoda, 2008) The trait is difficult to identify as various questions may have differing answers based on the circumstances or the consequences of one’s actions (Andrew et al, 2011). Therefore, the questionnaire should come up with questions that elicit a specific emotion and one that does not have a definite moral answer as demonstrated in a study by Ashton (2017). It assists in differentiating the personality trait that different individuals possess based on whether they agree on such controversial matters in the society.
The third personality trait under submissiveness, which is a complex personality trait as it encompasses various levels of behavior. According to Hunsley et al. (2003) may be that one individual may submit to an authority figure but not among his or her peers (Hunsley et al, 2003). It may also be that another person is submissive to all people regardless of their authority or level of control. In assessing submissiveness, the questionnaire should inquire whether the person is ready to act based on instructions, commands or simple will (Graham, 2006). The questions should be such that they evaluate the ability of the individual to follow instructions or commands without being pushed or forced to carry out the actions (Goldman et al, 2006). The three personality traits have been missing in previous questionnaires and tests since they present a wide range of questions, which should be specifically formulated to suit the emotions and behavior that the individuals may possess (Terracciano et al, 2006). They are unique in that they do not have an absolute method of testing or evaluation and may be difficult to examine (Rule & Albady, 2010). Psychologists have continued to carry out research on whether the methods applied in assessing such complex traits are accurate as well as the effectiveness of the questionnaires in showing the relationship between various forms of behavior in each trait.
Research Rationale and Hypothesis
The objective of the research is to evaluate whether the questionnaire that has been provided is effective in testing the three personality traits, namely moral absolutism, perfectionism and submissiveness. The research seeks to look into each of the questions provided in the questionnaire and how it relates to each of the traits being tested. The behavior associated with each trait is obtained from the literature review, which defines the variables required to ascertain that the individual possesses or lacks the personality. Data analysis shows how each question correlates to the other. It seeks to establish whether the data collected can be used to exclusively state whether the person has the trait based on how they answer the questions. The relationship between each question is evaluated using the DSM-5 criteria, which shows the extent to which a person agrees or disagrees with a specific proposition (Ashton, 2017). The propositions set a baseline for the personality test as they indicate the person’s behavior and how they are likely to react to different scenarios that they face each day. Data analysis shows whether the questionnaire is effective by looking at the relationship between the questions, evaluating whether it can be a successful assessment tool.
Based on the research rationale and objectives, the study is based on the null the hypothesis that “the questionnaire is ideal in testing the complex personality traits.” The alternative hypothesis is that “the questionnaire is not ideal for testing the complex personality traits.” The research uses quantitative methods to test the hypothesis. The methods used are correlation, commonality and factor analysis, evaluating the relationship between each question and how they relate to the personality traits being assessed. Accepting the null hypothesis means that the questionnaire can be used for future personality tests while the alternative hypothesis means that there is need for future research to come up with an effective measuring tool (Solomon, 1991).
In this section, we ought to cover various results majorly concerning Shapiro Wilks, KMO and Bartlett’s Test, Scree Plot and rotated components matrix.
shapiro wilks does the same work as Kolmogorov-smirnov test. they both determine the normality distribution of the data. From shapiro wilks table, all 30 questionnaires have their p-values less than 0.05 and their degrees of freedom (df) are 209.this mean that the sample amount to 210.their p-values will play a critical part in the (discussion section) when will be interpretation and discussing the figure statistically.
KMO and Bartlett’s Test. this test indicates whether data is probably factorable. we use p < .05 to determine this assumption. The following summarizes the output of this test.
Scree Plot. Plot graph plots the eigenvalues (y-axis) by the component number (x-axis). The plot always curves downward (Krueger et al, 2012). This is useful because it enables you to see whether some factors are strong and have high eigenvalues, and where the weaker factors begin to occur. The weaker factors emerge when the curve begins to flatten. This is called the Point of Inflexion. Components or factors above this flattening point area generally chosen for discussion.
Rotated component matrix. The loading values in the matrix reflect correlations between the variables and the factors. It is usual to suppress factor loadings below 0.3 to make this table easier to interpret.
Total Variance Explained. This table shows the principal components that were extracted from the data. The cumulative % indicates how much variance the number of factors you have chosen explains. Once you have decided how many factors best explains your data then you need to report the percentage of variance explained by the factors you have included.
We will discuss in detail in the section below.
shapiro-wilk test. this non-parametric test employs the use of hypothesis test to conclude whether certain variable hold normality assumption or not (Goodman, 1954). The hypotheses are formulated as follows;
Null hypothesis: a variable is normally distributed
Alternative hypothesis: a variable is not normally distributed.
If p-value is found to be less 0.05, the null hypothesis is rejected and vice versa.
From the given output, all the questionnaires (designated as Q1, Q2, Q3…Q30) are not normally distributed because they have their p-values less than 0.05. there are several factors that might have contributes to this conclusion, maybe there is presence of outliers and thus it violates the normality assumption. In regard to our problem, we can conclude that something must be done to the data. Since our data is not normally distributed, I bet it will adversely affect the outcome of the research and thus the result should not be 100% trusted.
This test has got assumptions that must be fulfilled by the data for validation. These assumptions are;
• The sample must be from a random sample,
• Sample distribution is assumed to have no ties. If it happens to have ties, then the results will be too liberal as this we be as a result of larger d.
• The data must be ordinal.
KMO and Bartlett’s Test. This is a test of the “factorability” of your data. The KMO measure of sampling adequacy is a test of the amount of variance within the data which could be explained by factors. A KMO value of .5 is poor; .6 is acceptable and a value closer to 1 is better.
Bartlett’s test indicates that the data is probably factorable if p .05 do not continue, but if p <.05 check other indicators of factorability before proceeding (Ferguson, 1959). from our results-value=0.00 meaning that our data is probably factorable. Our KMO is 0.758.
Scree plot. Scree plot is used to determine which factors to retain with regards to explanatory factor analysis (FA). It shows Eigen values on the y-axis and number of factors in x-axis. The plot always curves downward. The point where the graph levels off indicates the number of factors that should be retained (Henson & Mellenbergh, 2008). From our scree plot, the number of variables that should be retained for explanatory factor analysis is 3. The results show that the questionnaire is not an ideal method in testing the complex personality traits. The three traits being evaluated are not sufficiently assessed. Therefore, the researchers should attempt to come up with another assessment method, which will be ideal for the three traits being evaluated. It is important to conduct more research on complex traits to come up with a proven testing method.
Rotated component matrix. In the Rotated Component Matrix, you see the components (factors) orthogonally rotated and displaying the loading of each variable (above 0.3 as we defined above) upon it. The loading values in the matrix reflect correlations between the variables and the factors. It is usual to suppress factor loadings below 0.3 to make this table easier to interpret (however, it’s important to understand that every variable loads on every factor). Because each factor is an abstract underlying structure it is up to the researcher to find meaning in the factors. This is the subjective and qualitative component of factor analysis. The variables are ordered according to their loadings on the first factor, from those with the highest loadings to those with the lowest loadings. This helps interpretation of the factor, since the high loading items are the ones that primarily help you decide what the factor means. We would interpret the meaning of these factors in terms of the content of the variables that loaded most highly on them. Each column shows the loading of each variable on that component (although for your output only the ones above 0.3 are shown in the matrix). The loading is essentially the correlation between the factor and the variable: the larger the number, the more likely it is that the component underlies that variable. Loadings can be both positive and negative. To interpret the positive and negative signs, how the statement has been scored also needs to be taken into consideration
Total Variance Explained. The components listed down the left hand side number the same amount as the variables included in the analysis but you will note that only some of the components have entries across the width of the table (in the extraction and rotation sections) and this is the first indication of the number of factors we have extracted from the exploratory factor analysis. The cumulative % indicates how much variance the number of factors you have chosen explains. In our case, the table below 9 factors explains 60.43% of the variance ((9 factors accounted for 60.43% of the total variance explained).
However, if you decided that a 6 factor solution was a better fit to the model 46.19% of the variance will be explained (six factors accounted for 46.19% of the total variance explained).
By observing keenly on both scree plot and rotated components matrix, I chose to work with factor 8.our KMO is 0.78 implying that our degree of common variance is middling and we proceed with the factor analysis.
questionnaire statement factor
Q9 I hold myself to extremely high standards. 0.312
Q2 I adhere to a strict moral code no matter the situation. -0.327
Q17 Certain scenarios are above the law 0.622
Q30 I usually don’t tidy up if I can avoid it -0.431
Q29 Doing something illegal can sometimes be justified 0.342
Q17 Certain scenarios are above the law 0.841
Arendasy, M.; Sommer, H. & Schutzhofer, I. (2011). "Modeling effects of faking on an objective personality test". Journal of Individual Differences. 32 (4): 210–218.
Ashton, M. (2017). Individual Differences and Personality (3rd ed.).Cengage Learning
Boyle, G.J., Saklofske, D.H., & Matthews, G. (2015). (Eds.), Measures of Personality and Social Psychological Constructs. Amsterdam: Elsevier/Academic Press.
Eggen, P. D., & Kauchak, D. (1999). Educational psychology (Vol. 403). Prentice hall.
Ferguson, G. A. (1959). Statistical analysis in psychology and education.
Fiske, S. T., & Taylor, S. E. (2007). Social cognition, from brains to culture. New York, NY: McGraw-Hill.
Goodman, L. A. (1954). Kolmogorov-Smirnov tests for psychological research. Psychological bulletin, 51(2), 160.
Gosling, S. D. (2001). From mice to men: What can we learn about personality from animal research? Psychological Bulletin, 127(1), 45–86.
Goldberg, L. R., Johnson, J. A., Eber, H. W., Hogan, R., Ashton, M. C., Cloninger, C. R., & Gough, H. C. (2006). The International Personality Item Pool and the future of public-domain personality measures. Journal of Research in Personality, 40, 84-96.
Graham, J. R. (2006). MMPI-2: Assessing personality and psychopathology (4th ed.). New York, NY: Oxford University Press.
Herman J. A. &. Mellenbergh, G. (2008) Advising on Research Methods: a consultant's companion. Johannes van Kessel Publ. p. 244.
Hines, T. (2003). Pseudoscience and the paranormal (2nd ed.). Amherst, NY: Prometheus Books.
Hunsley, J., Lee, C. M., & Wood, J. M. (2003). Controversial and questionable assessment techniques. In S. O. Lilienfeld, S. J. Lynn, & J. M. Lohr (Eds.), Science and pseudoscience in clinical psychology (pp. 39–76). New York, NY: Guilford Press.
Karon, B. P. (2000). The clinical interpretation of the Thematic Apperception Test, Rorschach, and other clinical data: A reexamination of statistical versus clinical prediction. Professional Psychology: Research and Practice, 31(2), 230–233.
Krueger, R. F.; Derringer, J.; Markon, K. E.; Watson, D.; Skodol, A. E. (2012). "Initial construction of a maladaptive personality trait model and inventory for DSM-5". Psychological Medicine. 42 (9): 1879–1890
Lynam, D. R &; Widiger, T. A. (2001). "Using the five-factor model to represent the DSM-IV personality disorders: An expert consensus approach". Journal of Abnormal Psychology. 110 (3): 401–412
McGhee, R.L., Ehrler, D. & Buckhalt, J. (2008). Manual for the Five Factor Personality Inventory — Children Austin, TX
Mischel, W., & Shoda, Y. (2008). Toward a unified theory of personality: Integrating dispositions and processing dynamics within the cognitive-affective processing system. In O. P. John, R. W. Robins, & L. A. Pervin (Eds.), Handbook of personality psychology: Theory and research (3rd ed., pp. 208–241). New York, NY: Guilford Press.
Olivola, C. Y., & Todorov, A. (2010). Fooled by first impressions? Reexamining the diagnostic value of appearance-based inferences. Journal of Experimental Social Psychology, 46(2), 315–324.
Ones, D.S. (2009). Personality at work: Raising awareness and correcting misconceptions. Human Performance, 18, 389-404.
Pieterse, A. N., Van Knippenberg, D., Schippers, M., & Stam, D. (2010). Transformational and transactional leadership and innovative behavior: The moderating role of psychological empowerment. Journal of Organizational Behavior, 31(4), 609–623.
Poropat, A. E. (2014-08-01). "Other-rated personality and academic performance: Evidence and implications". Learning and Individual Differences. 34: 24–32.
Rammstedt , B. (2007). The 10-Item Big Five Inventory: Norm Values and Investigation of Sociodemographic Effects Based on a German Population Representative Sample. European Journal of Psychological Assessment 23 (3), pg. 193-201
Roberts, B. W., & DelVecchio, W. F. (2000). The rank-order consistency of personality traits from childhood to old age: A quantitative review of longitudinal studies. Psychological Bulletin, 126(1), 3–25.
Rule, N. O., & Ambady, N. (2010). Democrats and Republicans can be differentiated from their faces. PLoS ONE, 5(1), e8733.
Simpson, D. (2005). Phrenology and the neurosciences: Contributions of F. J. Gall and J. G. Spurzheim. ANZ Journal of Surgery, 75(6), 475–482.
Solomon, H. M. (1991). Archetypal psychology and object relations theory: history and communalities. Journal of Analytical Psychology, 36(3), 307-329
Terracciano, A., McCrae, Rr R. & Costa, P. T. (2006). "Longitudinal trajectories in Guilford-Zimmerman temperament survey data: results from the Baltimore longitudinal study of aging". The Journals of Gerontology. Series B, Psychological Sciences and Social Sciences. 61 (2): P108–116
Urbina, S. (2014. Essentials of Psychological Testing (Second ed.). Hoboken. New Jersey: John Wiley & Sons, Incorporated. pp. 127–128, 165–167.
Zuckerman, M. (2007). Sensation seeking and risky behavior. Washington, DC: American Psychological Association.