Chi-Square Test and Symmetric Measures

Case Processing Summary
  Cases
Valid Missing Total
N Percent N Percent N Percent
Q59h. Trust police * Urban or Rural Primary Sampling Unit 50485 97.9% 1102 2.1% 51587 100.0%
Q59h. Trust police * Urban or Rural Primary Sampling Unit Crosstabulation
  Urban or Rural Primary Sampling Unit Total
Urban Rural Semi-Urban
Q59h. Trust police Not at all Count 5216 5937 104 11257
% within Urban or Rural Primary Sampling Unit 26.6% 19.6% 15.5% 22.3%
Just a little Count 5360 7082 178 12620
% within Urban or Rural Primary Sampling Unit 27.4% 23.4% 26.5% 25.0%
Somewhat Count 5130 7973 177 13280
% within Urban or Rural Primary Sampling Unit 26.2% 26.4% 26.3% 26.3%
A lot Count 3878 9237 213 13328
% within Urban or Rural Primary Sampling Unit 19.8% 30.6% 31.7% 26.4%
Total Count 19584 30229 672 50485
% within Urban or Rural Primary Sampling Unit 100.0% 100.0% 100.0% 100.0%
Chi-Square Tests
  Value df Asymp. Sig. (2-sided)
Pearson Chi-Square 877.477a 6 .000
Likelihood Ratio 893.555 6 .000
Linear-by-Linear Association 794.593 1 .000
N of Valid Cases 50485    
a. 0 cells (0.0%) have expected count less than 5. The minimum expected count is 149.84.
Symmetric Measures
  Value Approx. Sig.
Nominal by Nominal Phi .132 .000
Cramer’s V .093 .000
N of Valid Cases 50485  

                In this scenario, we are comparing the relationship between Citizens’ trust in police and the question of whether respondents reside in rural, urban, or semi-urban settings. Using SPSS, Afrobarometer 2015, I have tabulated two variables, as categorized. Secondly, I have identified dependent variable as Trust in Police with an independent variable of respondents Urban or Rural Primary Sampling Unit. There is a total N of 51587 with 2.1% missing or not applicable to the data in question. Our cross-tabulation shows percent difference between the two variables. This allows us to further view the present of relationship between the variables. For example, there are 27.4%, 23.4% and 26.4% of Urban, Rural, and Semi-Urban respectively trust police just a little. Chi-Square Tests showed Pearson Chi-Square of 877.477 with associated P-value of 0.000. Cramer’s V of 0.093 with an associated P-value of 0.000 showed the strength of the relationship between the two variables (Laureate Education, 2016a). In this case, we can reject null hypothesis that there is no relationship between citizens’ trust in police and the question of whether respondents reside in rural, urban or semi-urban settings. The positive implications lies on the facts that different localities of citizens can have great impact on the nature and perception of police. It is certainly true that the duties of police is important, but what is even truer is the citizens’ trust in the duties of police officers.