You are on page 1of 13

Findings

Research Question 1:
To identify the most dominant trait of personality among respondents.

For Research Question 1, the mean score for three personality traits have been
calculated. The mean score for Machiavellianism is the highest, which is 3.2778, followed by
Narcissism, which is 3.1889, and the lowest mean score is Psychopathy, which is 3.1567
(Table 1). This showed that the most dominant trait of personality among the respondents is
Machiavellianism because it has the highest mean score.

Next, we will be looking into standard deviation. The lower the value of standard
deviation, the smaller the dispersion of the scores. Among these three personality traits,
Narcissism has the lowest value of standard deviation, which is .30624 whereas Psychopathy
has the highest value of standard deviation, which is .48685 (Table 1). The standard deviation
of Machiavellianism is .47478, which is in between Narcissism and Psychopathy. The scores
for Psychopathy is more scattered than the scores of Narcissism and Machiavellianism.

Table 1. Mean and standard deviation for the score of Machiavellianism, Narcissism and
Psychopathy.
Machiavellianism Narcissism Psychopathy
Mean 3.2778 3.1889 3.1567
SD .47478 .30624 .48685
Research Question 2:
To identify if there is any significant difference in dominant trait personality between male
and female.

For this research question, we have used t-test to compare the mean score of male and
female on their Machiavellianism trait, as this is the most dominant trait because it has the
highest mean score. There were 15 males and 15 females who have responded to the
instrument. Male scored higher than female, where the mean score of male is 3.4370 while
the mean score of female is 3.1185 (Table 2). The standard deviation for male is also higher
(.57193) than female (.29237), which explained that the scores for male are more scattered.

Table 2. Mean score of male and female in Machiavellianism trait.


Gender N Mean SD
Machiavellianism Male 15 3.4370 .57193
Female 15 3.1185 .29237

Next, Table 3 gives the values of Independent Samples Test for mean score of male
and female in Machiavellianism trait. Levene’s test is used to assess the equality of variances.
The significance value from Levene’s Test of Equality of Variances, .020, is lower than the
alpha value, 0.05, thus the data of “equal variances not assumed” will be read. Referring to
the t-test of Equality of Means, the significance value, .069, is more than the value of alpha,
thus failing to reject the null hypothesis. This means that there is no significant difference
between male and female in the Machiavellianism.

Table 3. Independent Samples Test for mean score of gender in Machiavellianism trait.
Levene’s test t-test for Equality of Means
F Sig. t df Sig. (2- Mean Std. Error
tailed) Difference Difference
Equal 6.045 .020 1.921 28 .065 .31852 .16585
variance
assumed
Equal 1.921 20.849 .069 .31852 .16585
variance
not
assumed
Research Question 3:
To identify if there is any significant difference in dominant trait personality between marital
status.

For this research question, we have also used t-test to compare the mean score of
marital status (single and married) on their Machiavellianism trait. There were 23
respondents who were single and 17 respondents who were married. Referring to Table 4,
the mean score for single respondents (3.3188) is higher than the mean score of married
respondents (3.1429). On the other hand, the standard deviation for married respondents is
higher (.53562) than single respondents (.45972), which explained that the scores for married
marital status are more scattered.

Table 4. Mean score of male and female in Machiavellianism trait.


Marital Status N Mean SD
Machiavellianism Single 23 3.3188 .45972
Married 17 3.1429 .53562

Next, Table 3 gives the values of Independent Samples Test for mean score of male
and female in Machiavellianism trait. The significance value from Levene’s Test of Equality
of Variances, .613, is higher than the alpha value, 0.05, thus the data of “equal variances
assumed” will be read. Referring to the t-test of Equality of Means, the significance
value, .400, is more than the value of alpha, thus failing to reject the null hypothesis. This
means that there is no significant difference between marital status in the Machiavellianism
trait.

Table 5. Independent Samples Test for mean score of marital status in Machiavellianism trait.
Levene’s test t-test for Equality of Means
F Sig. t df Sig. (2- Mean Std. Error
tailed) Difference Difference
Equal .261 .613 .855 28 .400 .17598 .20590
variance
assumed
Equal .786 8.870 .453 .17598 .22399
variance
not
assumed
Reliability

The reliability index of this instrument is calculated using SPSS software. Table 6
below showed the reliability statistics of Dark Triad Personality Test. Cronbach’s alpha is the
measure of internal consistency of the items. The value of Cronbach’s alpha obtained is .850.
According to Carrillo Flores (2016), .70 is the minimum acceptable value for Cronbach’s
alpha. The alpha values between .80 and .90 are more preferred at most times. Therefore the
Cronbach’s alpha for this instrument is considered preferable.

Table 6. Reliability Statistics of Dark Triad Personality Test.


Cronbach’s Alpha Cronbach’s Alpha N of Items
Based on
Standardized Items
.850 .853 29

Validity

The content validity is processed through factor analysis using SPSS software. The
factor analysis was done separately on Machiavellianism, Narcissism, and Psychopathy.

(i) Machiavellianism

The first output from the analysis is the correlation coefficient. A correlation matrix is
simply a rectangular array of numbers which gives the correlation coefficients between a
single variable and every other variables in the investigation. The correlation coefficient
between a variable and itself is always 1, hence the principal diagonal of the correlation
matrix contains 1s (See Red Line in the Table 7 below). The correlation coefficients above
and below the principal diagonal are the same.

Referring to the Correlation Matrix, if any pair of variables has a value less than 0.5,
it is advisable to drop one of them from the analysis (by repeating the factor analysis test in
SPSS by removing variables whose value is less than 0.5). The off-diagonal elements (The
values on the left and right side of diagonal in the table below) should all be very small (close
to zero) in a good model.
According to Table 7, the following pairs of variables have values higher than 0.5:

 Part1Q1 and Part1Q4


 Part1Q1 and Part1Q6
 Part1Q3 and Part1Q5
 Part1Q3 and Part1Q8
 Part1Q5 and Part1Q8
 Part1Q6 and Part1Q10
 Part1Q7 and Part1Q10

Thus, it is advisable to keep items Part1Q1, Part1Q3, Part1Q4, Part1Q5, Part1Q6,


Part1Q7, Part1Q8 and Part1Q10. The value of the pair Part1Q1 and Part1Q10 is 0.492, which
is very close to 0.5. Despite having an arguable value, Part1Q1 and Part1Q10 are still
advisable to be kept as they have greater values when paired with other items.

Table 7. Correlation Matrix


Part1Q1 Part1Q2 Part1Q3 Part1Q4 Part1Q5 Part1Q6 Part1Q7 Part1Q8 Part1Q9 Part1Q10

Part1Q1 1.000 .411 -.140 .613 -.131 .649 .349 -.209 .243 .492

Part1Q2 .411 1.000 .276 .082 .180 .193 -.020 .279 .130 .238

Part1Q3 -.140 .276 1.000 -.336 .644 -.040 .091 .526 .000 .334

Part1Q4 .613 .082 -.336 1.000 -.249 .371 -.011 -.106 .326 .192

Part1Q5 -.131 .180 .644 -.249 1.000 -.117 -.132 .654 -.058 .197
Correlation
Part1Q6 .649 .193 -.040 .371 -.117 1.000 .469 -.118 -.297 .507

Part1Q7 .349 -.020 .091 -.011 -.132 .469 1.000 -.449 -.235 .536

Part1Q8 -.209 .279 .526 -.106 .654 -.118 -.449 1.000 .143 .209

Part1Q9 .243 .130 .000 .326 -.058 -.297 -.235 .143 1.000 -.122

Part1Q10 .492 .238 .334 .192 .197 .507 .536 .209 -.122 1.000

The KMO test measures the sampling adequacy. It determines if the sample responses
provided are sufficient or not. The sampling adequacy should be close to 0.5 for a satisfactory
factor analysis to proceed. A KMO value of 0.5 is recommended as the minimum value to be
accepted, with 0.7-0.8 being acceptable, and with values above 0.9 being the best. Looking at
Table 8 below, the KMO measure is 0.386, which is far from 0.5 and therefore is not
acceptable.

Bartlett’s test is another test that can be used to indicate the strength of the
relationship among the variables. It tests the null hypothesis that the correlation matrix is an
identity matrix. The purpose is to reject this null hypothesis. From the same table, the
Bartlett’s Test Of Sphericity is significant (0.000), having its significance less than 0.05. This
means that correlation matrix is not an identity matrix.
Table 8. KMO and Bartlett's Test
Kaiser-Meyer-Olkin Measure of Sampling Adequacy. .386
Approx. Chi-Square 147.543

Bartlett's Test of Sphericity df 45

Sig. .000

Communalities showed the degree to which the factor describe the variance of the
variables. Two sets of communalities are provided namely initial sets and the extracted sets
within the proper solution. The value of one or more communalities can appeared to exceed
1.00 when the maximum likelihood procedure goes skewed due to inappropriate data
condition, which is considered to be theoretically impossible as it is unattainable in
explaining more that 100% of a variable’s variance, which rendered further explanation
impossible. In reference to this study, the communalities were fine which further support that
the results are suitable for interpretation.

Table 9. Communalities
Initial Extraction

Part1Q1 1.000 .887


Part1Q2 1.000 .454
Part1Q3 1.000 .750
Part1Q4 1.000 .723
Part1Q5 1.000 .731
Part1Q6 1.000 .722
Part1Q7 1.000 .737
Part1Q8 1.000 .788
Part1Q9 1.000 .632
Part1Q10 1.000 .744

Extraction Method: Principal Component


Analysis.

The maximum likelihood estimation procedure was used to extract the factors from
the variable data. Kaiser’s rule was applied in order to find out that which factors were most
eligible for interpretation as the rule demands that a given factor must be able to describe at
least the equivalent of one variable’s variance. This is not unreasonable since the factor
analysis has as its objective reducing several variables into fewer factors. With the reference
to this rule, three factors were extracted (see Table total variance explained). The
combination of this factors are used in the explanation that covered roughly 71.661% of all
the variable variances. A plot of the eigenvalues is conducted where it is suggested that a
proper solution was achievable through maximum likelihood since it was capable of
converging in 4 iterations based on the review of the initial factor loadings.
Table 10. Total Variance Explained
Component Initial Eigenvalues Extraction Sums of Squared Rotation Sums of Squared
Loadings Loadings

Total % of Cumulative Total % of Cumulative Total % of Cumulative


Variance % Variance % Variance %

1 2.915 29.150 29.150 2.915 29.150 29.150 2.614 26.140 26.140


2 2.527 25.273 54.423 2.527 25.273 54.423 2.575 25.751 51.891
3 1.724 17.238 71.661 1.724 17.238 71.661 1.977 19.770 71.661
4 .821 8.208 79.868
5 .773 7.731 87.599
6 .408 4.082 91.682
7 .322 3.221 94.903
8 .278 2.780 97.683
9 .183 1.830 99.512
10 .049 .488 100.000

Extraction Method: Principal Component Analysis.


(ii) Narcissism

Based on the same standards of values in the previous discussion on


Machiavellianism, according to Table 11, the following pairs of variables have values higher
than 0.5:
 Part2Q3 and Part2Q5
 Part2Q3 and Part2Q8

Thus, it is advisable to keep items Part2Q5, Part2Q5 and Part2Q8. The number of
items that are advised to be kept are too few when compared to those of Machiavellianism.
Hence, it is advised to modify the items will low correlation values.

Table 11. Correlation Matrix


Part2Q1 Part2Q2 Part2Q3 Part2Q4 Part2Q5 Part2Q6 Part2Q7 Part2Q8 Part2Q9

Part2Q1 1.000 .217 -.278 .397 -.505 .304 .438 -.197 .074

Part2Q2 .217 1.000 .197 .360 .149 .397 .230 .147 -.083

Part2Q3 -.278 .197 1.000 -.248 .668 -.204 .215 .582 -.155

Part2Q4 .397 .360 -.248 1.000 -.399 .195 -.056 -.150 .283

Correlation Part2Q5 -.505 .149 .668 -.399 1.000 -.240 -.147 .456 -.088

Part2Q6 .304 .397 -.204 .195 -.240 1.000 .349 -.237 -.254

Part2Q7 .438 .230 .215 -.056 -.147 .349 1.000 -.176 -.382

Part2Q8 -.197 .147 .582 -.150 .456 -.237 -.176 1.000 -.175

Part2Q9 .074 -.083 -.155 .283 -.088 -.254 -.382 -.175 1.000

Based on the same standards of values in the previous discussion on


Machiavellianism, looking at Table 12 below, the KMO measure is 0.516, which is close to
0.5 and therefore is barely acceptable. From the same table, the Bartlett’s Test Of Sphericity
is significant (0.000), having its significance less than 0.05. This means that correlation
matrix is not an identity matrix. Also, inn reference to this study, the communalities were fine
which further support that the results are suitable for interpretation (Table 13).

Table 12. KMO and Bartlett's Test


Kaiser-Meyer-Olkin Measure of Sampling Adequacy. .516
Approx. Chi-Square 90.586

Bartlett's Test of Sphericity df 36

Sig. .000
Table 13. Communalities
Initial Extraction

Part2Q1 1.000 .594


Part2Q2 1.000 .769
Part2Q3 1.000 .774
Part2Q4 1.000 .772
Part2Q5 1.000 .755
Part2Q6 1.000 .559
Part2Q7 1.000 .718
Part2Q8 1.000 .607
Part2Q9 1.000 .659

Extraction Method: Principal


Component Analysis.

With the reference to the same rule used when discussing the part on
Machiavellianism, three factors were extracted (see Table total variance explained). The
combination of this factors are used in the explanation that covered roughly 68.973% of all
the variable variances. A plot of the eigenvalues is conducted where it is suggested that a
proper solution was achievable through maximum likelihood since it was capable of
converging in 4 iterations based on the review of the initial factor loadings.

Table 14. Total Variance Explained


Component Initial Eigenvalues Extraction Sums of Squared Rotation Sums of Squared Loadings
Loadings

Total % of Cumulative Total % of Cumulative Total % of Cumulative


Variance % Variance % Variance %

1 2.835 31.495 31.495 2.835 31.495 31.495 2.515 27.942 27.942


2 1.996 22.174 53.668 1.996 22.174 53.668 1.878 20.867 48.809
3 1.377 15.304 68.973 1.377 15.304 68.973 1.815 20.164 68.973
4 .873 9.700 78.672
5 .704 7.821 86.494
6 .457 5.077 91.571
7 .366 4.066 95.637
8 .263 2.918 98.556
9 .130 1.444 100.000

Extraction Method: Principal Component Analysis.


(iii) Psychopathy

Based on the same standards of values in the previous discussion on


Machiavellianism and Narcissism, according to Table 15, the following pairs of variables
have values higher than 0.5:
 Part3Q1 and Part3Q8
 Part3Q2 and Part3Q7
 Part3Q2 and Part3Q8
 Part3Q4 and Part3Q6
 Part3Q5 and Part3Q10
 Part3Q6 and Part 3Q9
 Part3Q7 and Part3Q8

Thus, it is advisable to keep items Part3Q1, Part3Q2, Part3Q4, Part3Q5, Part3Q6,


Part3Q7, Part3Q8, Part3Q9 and Part3Q10.
Table 15. Correlation Matrix
Part3Q1 Part3Q2 Part3Q3 Part3Q4 Part3Q5 Part3Q6 Part3Q7 Part3Q8 Part3Q9 Part3Q10

Part3Q1 1.000 .428 .401 .425 .041 .116 .475 .605 .275 -.077

Part3Q2 .428 1.000 .259 -.129 .360 -.432 .563 .633 -.148 .310

Part3Q3 .401 .259 1.000 .435 .233 .282 .181 .363 .341 .414

Part3Q4 .425 -.129 .435 1.000 -.192 .681 .016 .276 .475 -.061

Part3Q5 .041 .360 .233 -.192 1.000 -.250 .353 .019 .077 .506
Correlation
Part3Q6 .116 -.432 .282 .681 -.250 1.000 -.054 -.137 .613 .010

Part3Q7 .475 .563 .181 .016 .353 -.054 1.000 .525 .136 -.054

Part3Q8 .605 .633 .363 .276 .019 -.137 .525 1.000 -.094 -.141

Part3Q9 .275 -.148 .341 .475 .077 .613 .136 -.094 1.000 .166

Part3Q10 -.077 .310 .414 -.061 .506 .010 -.054 -.141 .166 1.000

Based on the same standards of values in the previous discussion on


Machiavellianism, looking at Table 16 below, the KMO measure is 0.610, which is greater
than 0.5 and therefore is acceptable. From the same table, the Bartlett’s Test Of Sphericity is
significant (0.000), having its significance less than 0.05. This means that correlation matrix
is not an identity matrix. Also, inn reference to this study, the communalities were fine which
further support that the results are suitable for interpretation (Table 17).

Table 16. KMO and Bartlett's Test


Kaiser-Meyer-Olkin Measure of Sampling Adequacy. .610
Approx. Chi-Square 139.838

Bartlett's Test of Sphericity df 45

Sig. .000

Table 17. Communalities


Initial Extraction

Part3Q1 1.000 .731


Part3Q2 1.000 .828
Part3Q3 1.000 .641
Part3Q4 1.000 .784
Part3Q5 1.000 .700
Part3Q6 1.000 .832
Part3Q7 1.000 .578
Part3Q8 1.000 .827
Part3Q9 1.000 .653
Part3Q10 1.000 .808

Extraction Method: Principal Component


Analysis.
With the reference to the same rule used when discussing the part on
Machiavellianism and Narcissism, three factors were extracted (see Table total variance
explained). The combination of this factors are used in the explanation that covered roughly
73.820% of all the variable variances. A plot of the eigenvalues is conducted where it is
suggested that a proper solution was achievable through maximum likelihood since it was
capable of converging in 4 iterations based on the review of the initial factor loadings.

Table 18. Total Variance Explained


Component Initial Eigenvalues Extraction Sums of Squared Rotation Sums of Squared Loadings
Loadings

Total % of Cumulative Total % of Cumulative Total % of Cumulative


Variance % Variance % Variance %

1 3.083 30.825 30.825 3.083 30.825 30.825 2.821 28.209 28.209


2 2.573 25.727 56.552 2.573 25.727 56.552 2.638 26.381 54.590
3 1.727 17.268 73.820 1.727 17.268 73.820 1.923 19.229 73.820
4 .869 8.687 82.506
5 .450 4.497 87.004
6 .411 4.113 91.117
7 .355 3.554 94.671
8 .269 2.693 97.364
9 .151 1.505 98.869
10 .113 1.131 100.000

Extraction Method: Principal Component Analysis.


Carrillo Flores, J. W. (2016). Retrieved from ResearchGate:
https://www.researchgate.net/post/How_do_i_interpret_my_Alpha_cronbach_value

You might also like