Scenario 1
The first scenario focused on establishing whether there is a relationship between trust in the
police and the presence of democracy. The Afrobarometer data set was used to analyze the
relationship between independent and dependent variables. The research question was, “Is there
a relationship between the respondents trust in police and the presence of democracy?” the null
Hypothesis is “ there is no relationship between the respondents trust in police and the presence
of democracy.
Results
Case Processing Summary
Cases
Valid Missing Total
N Percent N Percent N Percent
Q59h. Trust police *
Democracy (dichotomous)
9492 92.0% 821 8.0% 10313 100.0%
The case processing summary table shows the both the valid and missing cases of the analysis.
Chi-Square Tests
Value df
Asymptotic
Significance (2-
sided)
Pearson Chi-Square 257.634a3 .000
Likelihood Ratio 243.189 3 .000
Linear-by-Linear Association 232.422 1 .000
N of Valid Cases 9492
a. 0 cells (0.0%) have expected count less than 5. The minimum
expected count is 235.23.
The chi-square results shows that the zero cells are less than 5. On the other hand, the minimum
expected count is 235.23. The Pearson Chi-Square is 257.634 and the degree of freedom is 3.
Significance value is .00, thus we reject the null hypothesis.
Verdict
Reject the null hypothesis
According to Wagner, (2020), when analyzing cross tabulations of survey response results, the
Chi-Square test comes in handy. The Chi-Square test tells researchers whether there is a
statistically significant difference in how various segments or categories answered a given
question because cross tabulations show the frequency and percentage of responses to questions
by various segments or categories of respondents (gender, occupation, education level, etc.). The
scenario implication of social change shows that there is little trust between police and the
community.
Q59h. Trust police * Democracy (dichotomous) Cross tabulation
Democracy (dichotomous)
Total
Not a
Democracy Democracy
Q59h. Trust police Not at all Count 424 1655 2079
% within Q59h. Trust police 20.4% 79.6% 100.0%
% within Democracy
(dichotomous)
39.5% 19.7% 21.9%
% of Total 4.5% 17.4% 21.9%
Just a little Count 285 2177 2462
% within Q59h. Trust police 11.6% 88.4% 100.0%
% within Democracy
(dichotomous)
26.5% 25.9% 25.9%
% of Total 3.0% 22.9% 25.9%
Somewhat Count 215 2224 2439
% within Q59h. Trust police 8.8% 91.2% 100.0%
% within Democracy
(dichotomous)
20.0% 26.4% 25.7%
% of Total 2.3% 23.4% 25.7%
A lot Count 150 2362 2512
% within Q59h. Trust police 6.0% 94.0% 100.0%
% within Democracy
(dichotomous)
14.0% 28.1% 26.5%
% of Total 1.6% 24.9% 26.5%
Total Count 1074 8418 9492
% within Q59h. Trust police 11.3% 88.7% 100.0%
% within Democracy
(dichotomous)
100.0% 100.0% 100.0%
% of Total 11.3% 88.7% 100.0%
The results from the cross tabulation table indicates that 39.9% respondents of no democracy
said that they don’t trust the police at all. According to Acemoglu, Daron, Suresh Naidu, Pascual
Restrepo, and James A. Robinson. (2019) most citizens in countries that are not democratic do
not trust the police. The state uses police to enforce its will on people hence the bad blood
between citizens and police.
Scenario 2
The second scenario sought to establish whether trust in police had a relationship depending on
whether the respondents reside in rural, urban or semi-urban. The categorical variables were trust
in police as the dependent variable and urban or rural primary sampling unit as the independent
variable. The research question was” Is there a relationship between citizen trust in police and
respondent residing in rural, urban or semi-urban area”. The null hypothesis for this study was
“There is no significant relationship between citizen trust in police and respondent residing in
rural, urban or semi-urban area.
Results
Case Processing Summary
Cases
Valid Missing Total
N Percent N Percent N Percent
Urban or Rural Primary
Sampling Unit * Q59h. Trust
police
10110 98.0% 203 2.0% 10313 100.0%
The case summary table shows the valid cases and missing cases.
Chi-Square Tests
Value df
Asymptotic
Significance (2-
sided)
Pearson Chi-Square 130.275a6 .000
Likelihood Ratio 131.556 6 .000
Linear-by-Linear Association 122.728 1 .000
N of Valid Cases 10110
a. 0 cells (0.0%) have expected count less than 5. The minimum
expected count is 27.60.
Results from the table above shows that the Pearson Chi-square is 130.275, the degree of
freedom is 6 while the significance value is represented by .000. The P value is less than .005.
Verdict
We therefore reject the null hypothesis that there is no significant relationship between citizen
trust in police and respondent residing in rural, urban or semi-urban.
Urban or Rural Primary Sampling Unit * Q59h. Trust police Cross tabulation
Q59h. Trust police
Total
Not at
all
Just a
little Somewhat A lot
Urban or Rural Urban Count 1009 1069 993 827 3898
Primary Sampling Unit % within Urban or
Rural Primary
Sampling Unit
25.9% 27.4% 25.5% 21.2% 100.0%
% within Q59h. Trust
police
45.9% 41.0% 38.1% 30.6% 38.6%
% of Total 10.0% 10.6% 9.8% 8.2% 38.6%
Rural Count 1166 1507 1576 1836 6085
% within Urban or
Rural Primary
Sampling Unit
19.2% 24.8% 25.9% 30.2% 100.0%
% within Q59h. Trust
police
53.1% 57.8% 60.5% 67.9% 60.2%
% of Total 11.5% 14.9% 15.6% 18.2% 60.2%
Semi-
Urban
Count 22 30 34 41 127
% within Urban or
Rural Primary
Sampling Unit
17.3% 23.6% 26.8% 32.3% 100.0%
% within Q59h. Trust
police
1.0% 1.2% 1.3% 1.5% 1.3%
% of Total 0.2% 0.3% 0.3% 0.4% 1.3%
Total Count 2197 2606 2603 2704 10110
% within Urban or
Rural Primary
Sampling Unit
21.7% 25.8% 25.7% 26.7% 100.0%
% within Q59h. Trust
police
100.0% 100.0% 100.0% 100.0% 100.0%
% of Total 21.7% 25.8% 25.7% 26.7% 100.0%
The results from the cross tabulation indicates that 45.9% of the urban residents feel most
people can be trusted, as compared to 53.1% of people in the rural area. The results shows that
people in the rural areas have trust in the police as compared to urban residents.
Symmetric Measures
Value
Asymptotic
Standard ErroraApproximate Tb
Approximate
Significance
Nominal by Nominal Phi .114 .000
Cramer's V .080 .000
Interval by Interval Pearson's R .110 .010 11.146 .000c
Ordinal by Ordinal Spearman Correlation .111 .010 11.272 .000c
N of Valid Cases 10110
a. Not assuming the null hypothesis.
b. Using the asymptotic standard error assuming the null hypothesis.
c. Based on normal approximation.
The Cramers test gives a value of .080. This shows a statistical relationship between the
independent and dependent variables. The social change implication indicates that the
government should educate its people on the role of policy. On the other, police reforms should
be carried out on community police and service to the people to restore faith and trust in the
police service.
Scenario 3
The third scenario sought to find out whether there is a relationship between current economic
conditions and extent of democracy. The research question was “is there a relationship between
current economic conditions and extent of democracy?” The null hypothesis was “there is no
relationship between the perception of current economic conditions and extent of democracy.
Extent of democracy and employment status were the categorical variables of the study.
Results
Case Processing Summary
Cases
Valid Missing Total
N Percent N Percent N Percent
Q5a. Country's economic
condition compared to 12
months ago * Q42. Extent of
democracy
9477 91.9% 836 8.1% 10313 100.0%
The case processing summary indicates the valid and missing cases.
Q5a. Country's economic condition compared to 12 months ago * Q42. Extent of
democracy Crosstabulation
Q42. Extent of democracy
Total
Not a
democracy
A
democracy,
with major
problems
A
democracy,
but with
minor
problems
A full
democracy
Q5a. Country's
economic condition
compared to 12
months ago
Much
Worse
Count 217 390 328 144 1079
% within Q5a.
Country's economic
condition compared
to 12 months ago
20.1% 36.1% 30.4% 13.3% 100.0%
% within Q42.
Extent of
democracy
20.2% 13.1% 9.2% 7.6% 11.4%
% of Total 2.3% 4.1% 3.5% 1.5% 11.4%
Worse Count 362 949 931 450 2692
% within Q5a.
Country's economic
condition compared
to 12 months ago
13.4% 35.3% 34.6% 16.7% 100.0%
% within Q42.
Extent of
democracy
33.7% 32.0% 26.2% 23.8% 28.4%
% of Total 3.8% 10.0% 9.8% 4.7% 28.4%
Same Count 268 793 1050 558 2669
% within Q5a.
Country's economic
condition compared
to 12 months ago
10.0% 29.7% 39.3% 20.9% 100.0%
% within Q42.
Extent of
democracy
25.0% 26.7% 29.6% 29.6% 28.2%
% of Total 2.8% 8.4% 11.1% 5.9% 28.2%
Better Count 207 753 1115 639 2714
% within Q5a.
Country's economic
condition compared
to 12 months ago
7.6% 27.7% 41.1% 23.5% 100.0%
% within Q42.
Extent of
democracy
19.3% 25.4% 31.4% 33.8% 28.6%
% of Total 2.2% 7.9% 11.8% 6.7% 28.6%
Much
Better
Count 20 83 123 97 323
% within Q5a.
Country's economic
condition compared
to 12 months ago
6.2% 25.7% 38.1% 30.0% 100.0%
% within Q42.
Extent of
democracy
1.9% 2.8% 3.5% 5.1% 3.4%
% of Total 0.2% 0.9% 1.3% 1.0% 3.4%
Total Count 1074 2968 3547 1888 9477
% within Q5a.
Country's economic
condition compared
to 12 months ago
11.3% 31.3% 37.4% 19.9% 100.0%
% within Q42.
Extent of
democracy
100.0% 100.0% 100.0% 100.0% 100.0%
% of Total 11.3% 31.3% 37.4% 19.9% 100.0%
The cross tabulation table shows that when the country is doing better economically, 6.2% of its
citizens don’t believe in a democracy. On the other hand, when the economy is much worse,
20.2% of its citizens do not perceive democracy as important.
Chi-Square Tests
Value df
Asymptotic
Significance (2-
sided)
Pearson Chi-Square 271.646a12 .000
Likelihood Ratio 264.380 12 .000
Linear-by-Linear Association 244.146 1 .000
N of Valid Cases 9477
a. 0 cells (0.0%) have expected count less than 5. The minimum
expected count is 36.60.
The Pearson chi-square is 271.646, the degree of freedom is 12, and the significance value is .00,
which is less than the acceptable yardstick of .05. We therefore reject the null hypothesis that
there is no relationship between the perception of current economic conditions and extent of
democracy.
Symmetric Measures
Value
Asymptotic
Standard ErroraApproximate Tb
Approximate
Significance
Nominal by Nominal Phi .169 .000
Cramer's V .098 .000
Interval by Interval Pearson's R .161 .010 15.830 .000c
Ordinal by Ordinal Spearman Correlation .158 .010 15.563 .000c
N of Valid Cases 9477
a. Not assuming the null hypothesis.
b. Using the asymptotic standard error assuming the null hypothesis.
c. Based on normal approximation.
The Cramers test shows a value of .169. This is evidence of a statistical association between the
two variables. In reference to Cumbers, (2020) countries learn from one another, and a country's
economic success influences not just its own chances of moving to or from democracy, but also
the possibilities for democracy beyond its borders through its influence on neighboring beliefs.
References
Acemoglu, Daron, Suresh Naidu, Pascual Restrepo, and James A. Robinson. (2019).
“Democracy Does Cause Growth.” Journal of Political Economy 127 (1): 47–100.
Cumbers, A. (2020). The Case for Economic Democracy, Polity Press
Wagner, III, W. E. (2020). Using IBM® SPSS® statistics for research methods and social
science statistics (7th ed.). Thousand Oaks, CA: Sage Publications
