Fear for small animals and insects
People fear for different types of animals and insects. The fear for spiders, rats and snakes are more common than fear from rabbits or giraffes. According to a study conducted by Davey (1994), the fear for small animals such as spiders come from disgust. Thus, he hypothesized that people with higher disgust propensity are more likely to be feared than the ones with lower disgust propensity. This study has been conducted to investigate the proposal stated by Davey. The study was conducted on 150 participants. All the participants filled in a questionnaire to measure their level of fear from spider.
In order to determine the outliers to the data, the upper and the lower bound of the outliers have to be evaluated. The upper and the lower outlier ranges are given by the formula:
Upper Outlier Range: Third Quartile + 1.5 * Interquartile Range = 28.09 + 1.5 * 20.84 = 59.35
Lower Outlier Range: First Quartile – 1.5 * Interquartile Range = 7.25 – 1.5 * 20.84 = – 24.01
The Extreme values as given in the following table 1 shows that there are no values in the dataset lower than – 24.01 but there are 5 values higher than 59.35. Thus, there are 5 outliers to the dataset. The outliers are also shown diagrammatically in figure 1.
It can be seen from table 2 that the normality statistic has been obtained as 0.115, which is higher than the critical value of the normality statistic obtained from the table for 150 degrees of freedom at 95% level of significance. Thus, it can be said the data is not normal. Figure 2 also shows that the residuals of the data are not linear. Thus, it can be said that the data is not normal.
Table 1: Extreme Values |
||||
Case Number |
Value |
|||
Fear of spiders |
Highest |
1 |
109 |
65.58 |
2 |
127 |
64.48 |
||
3 |
149 |
63.44 |
||
4 |
148 |
62.19 |
||
5 |
104 |
59.37 |
||
Lowest |
1 |
7 |
.03 |
|
2 |
21 |
.09 |
||
3 |
81 |
.64 |
||
4 |
59 |
1.04 |
||
5 |
26 |
1.44 |
Table 2: Tests of Normality |
||||||
Kolmogorov-Smirnova |
Shapiro-Wilk |
|||||
Statistic |
df |
Sig. |
Statistic |
df |
Sig. |
|
Fear of spiders |
.115 |
150 |
.000 |
.893 |
150 |
.000 |
a. Lilliefors Significance Correction |
From the values of the descriptive statistics, it can be seen that the average fear score for spiders is 20.38 with a standard deviation of 16.35 which is quite high. This indicates that the fear scores are quite scattered and not much close to the mean. The median score is 16.58, which is less than the mean. This indicates that the scores are positively skewed. Thus, most people are less scared of spider as most of the scores of fear from spiders are less than the average score. This does not support normality. Thus, from here also it can be said that the data is not normally distributed.
Determining outliers to the data
The hypothesis stated by the researcher is that the fear of spider is higher in people with higher disgust and lower in people with lower disgust. To test this hypothesis, the following Null and alternate hypothesis have been designed:
Null Hypothesis (H0): The fear of spider does not differ between people with different levels of disgust.
Alternate Hypothesis (HA): The fear of spider differs between people with different levels of disgust.
To test this hypothesis, one-way ANOVA test has been conducted in SPSS. From the results of the test, it can be seen that the significance value is 0.000 which is less than the level of significance (0.05). Thus, the null hypothesis is rejected. There are differences in the fear of spiders between at least two different levels of disgust.
Table 3: ANOVA |
|||||
Fear of spiders |
|||||
Sum of Squares |
df |
Mean Square |
F |
Sig. |
|
Between Groups |
12317.183 |
2 |
6158.591 |
32.872 |
.000 |
Within Groups |
27540.208 |
147 |
187.348 |
||
Total |
39857.391 |
149 |
Analysis of Variance (ANOVA) shows that there are significant differences between any two of the three groups – high, medium and low levels of disgust. It cannot be understood whether there are differences between high and low level of disgust specifically. To understand that, post hoc test has to be conducted. From the results of the post hoc test, it can be seen that the significance value for all the levels of disgust are less than 0.05. Thus, there are significant differences between the scores of fear for spiders for all the levels of disgust.
Table 4: Multiple Comparisons |
||||||
Dependent Variable: Fear of spiders Tukey HSD |
||||||
(I) Disgust propensity group |
(J) Disgust propensity group |
Mean Difference (I-J) |
Std. Error |
Sig. |
95% Confidence Interval |
|
Lower Bound |
Upper Bound |
|||||
LowDP |
ModerateDP |
-6.78135* |
2.73751 |
.038 |
-13.2629 |
-.2998 |
HighDP |
-21.69438* |
2.73751 |
.000 |
-28.1759 |
-15.2128 |
|
ModerateDP |
LowDP |
6.78135* |
2.73751 |
.038 |
.2998 |
13.2629 |
HighDP |
-14.91302* |
2.73751 |
.000 |
-21.3946 |
-8.4315 |
|
HighDP |
LowDP |
21.69438* |
2.73751 |
.000 |
15.2128 |
28.1759 |
ModerateDP |
14.91302* |
2.73751 |
.000 |
8.4315 |
21.3946 |
|
*. The mean difference is significant at the 0.05 level. |
It can be seen from the results obtained in tables 3 and 4 that the scores differ between the disgust levels. It can also be understood from table 4 that the average fear score for high disgust level is higher than that of low disgust level. Thus, the hypothesis stated by the researchers can be supported from this analysis.
A study conducted previously on the first year college students. They were shown a speech on tuition fees. It was noted that there were three types of students. Some swear at the beginning of the speech, some swear at the end of the speech and some other do not swear. In this study a similar experiment has been conducted to test whether there are any significant interaction effects of swearing groups and measurement times on the positive attitude towards a topic. Participants of the study were assigned to one of the three swearing groups and their positive attitude towards the topic was scored by the speaker before and after the speech.
To test the differences in the positive attitude between the students before and after the speech, a paired t-test has to be conducted. The null and the alternate hypothesis can be stated as follows:
Null Hypothesis (H01): There are no significant differences in the positive attitude before and after the speech.
Alternate Hypothesis (HA1): There are significant differences in the positive attitude before and after the speech.
From the results of the test given in table 5, it can be seen that the significance value is 0.000, which is less than 0.05 (5% level of significance). Thus, the null hypothesis is rejected. There are significant differences in the positive attitude before and after the speech between the students.
Table 5: Paired Samples Test |
|||||||||
Paired Differences |
t |
df |
Sig. (2-tailed) |
||||||
Mean |
Std. Deviation |
Std. Error Mean |
95% Confidence Interval of the Difference |
||||||
Lower |
Upper |
||||||||
Pair 1 |
Positive attitude before speech – Positive attitude after speech |
-73.54 |
68.376 |
7.895 |
-89.270 |
-57.806 |
-9.314 |
74 |
.000 |
It can be seen from table 6 that the significance value for the interaction effect of time of measurement and swearing group is less than the level of significance. Thus, it can be said that there are significant interaction effects of time and swearing groups towards the positive attitude on a topic for the students.
Table 6: Tests of Between-Subjects Effects |
|||||
Dependent Variable: Positive_Attitude |
|||||
Source |
Type III Sum of Squares |
df |
Mean Square |
F |
Sig. |
Corrected Model |
423998.182a |
5 |
84799.636 |
71.011 |
.000 |
Intercept |
1861494.000 |
1 |
1861494.000 |
1558.802 |
.000 |
Swearing_Group |
129441.554 |
2 |
64720.777 |
54.197 |
.000 |
Time_of_Measurement |
202790.227 |
1 |
202790.227 |
169.815 |
.000 |
Swearing_Group * Time_of_Measurement |
91766.401 |
2 |
45883.200 |
38.422 |
.000 |
Error |
171962.298 |
144 |
1194.183 |
||
Total |
2457454.480 |
150 |
|||
Corrected Total |
595960.480 |
149 |
|||
a. R Squared = .711 (Adjusted R Squared = .701) |