Testing for One-Way ANOVA
Research Question
Is the poverty index level the same across the four different regions of Africa?
Introduction
Eradication of poverty is one of the main goals of the Sustainable Development Goal. The target aims by 2030, extreme poverty in Africa would be completely eradicated (Anyanwu & Anyanwu, 2017). Measures to support the achievement have been put across by different entities of the world to ensure that the goal is met. African nations have been urged to promote ideas that can assist in fully eradicating poverty. One of the major factors of eliminating poverty is enhancing economic drivers. Attainment of economic freedom reduces the poverty levels in any county. Hence countries are urged to ensure the promotion of good leadership and democracy to provide a safe avenue for investors. Additionally, the countries are urged to fully focus on education as education creates skilled human capital that is essential to any developing country (Anyanwu & Anyanwu, 2017).
Data analysis
This exercise seeks to measures the variation in poverty index across different regions in Africa. The regions examined entails, South Africa, North Africa, West Africa and East Africa. The establishment of such variation is essential in providing insights on where resources should be allocated for poverty eradication programs.
The method of Analysis adopted is a One-Way Analysis of Variance. The technique compares the mean of more than two groups. The dependent variable in this technique is continuous while the independent variable is a group variable with more than two levels. The dependent variable in the exercise is the poverty index while the independent variable is regions. The research question would, therefore, be answered by the following hypothesis.
H0: μ1 = μ2 = μ3
H1: Means are not all equal
The results of the One-Way Analysis of Variance are as per the tables below;
Table 1: The table shows the results of the One-Way Analysis
ANOVA | |||||
Lived Poverty Index (average index of 5 poverty items) | |||||
Sum of Squares | df | Mean Square | F | Sig. | |
Between Groups | 434.373 | 3 | 144.791 | 170.996 | .000 |
Within Groups | 8611.465 | 10170 | .847 | ||
Total | 9045.838 | 10173 |
Table 2: The table shows the results of the post-hoc test of One-way Analysis of Variance
Multiple Comparisons | ||||||
Dependent Variable: Lived Poverty Index (average index of 5 poverty items) | ||||||
Tukey HSD | ||||||
(I) Country by region | (J) Country by region | Mean Difference (I-J) | Std. Error | Sig. | 95% Confidence Interval | |
Lower Bound | Upper Bound | |||||
West Africa | East Africa | .0344 | .0270 | .579 | -.035 | .104 |
Southern Africa | .2705* | .0215 | .000 | .215 | .326 | |
North Africa | .6461* | .0311 | .000 | .566 | .726 | |
East Africa | West Africa | -.0344 | .0270 | .579 | -.104 | .035 |
Southern Africa | .2361* | .0272 | .000 | .166 | .306 | |
North Africa | .6117* | .0353 | .000 | .521 | .702 | |
Southern Africa | West Africa | -.2705* | .0215 | .000 | -.326 | -.215 |
East Africa | -.2361* | .0272 | .000 | -.306 | -.166 | |
North Africa | .3756* | .0313 | .000 | .295 | .456 | |
North Africa | West Africa | -.6461* | .0311 | .000 | -.726 | -.566 |
East Africa | -.6117* | .0353 | .000 | -.702 | -.521 | |
Southern Africa | -.3756* | .0313 | .000 | -.456 | -.295 | |
*. The mean difference is significant at the 0.05 level. |
Table 3: The table shows the homogeneity of the group variable
Lived Poverty Index (average index of 5 poverty items) | ||||
Tukey HSD,b | ||||
Country by region | N | Subset for alpha = 0.05 | ||
1 | 2 | 3 | ||
North Africa | 1142 | .784 | ||
Southern Africa | 3601 | 1.160 | ||
East Africa | 1685 | 1.396 | ||
West Africa | 3746 | 1.430 | ||
Sig. | 1.000 | 1.000 | .640 | |
Means for groups in homogeneous subsets are displayed. | ||||
a. Uses Harmonic Mean Sample Size = 1986.314. | ||||
b. The group sizes are unequal. The harmonic mean of the group sizes is used. Type I error levels are not guaranteed. |
Conclusion
The results from the ANOVA results show that there is a significant difference across the different regions in Africa (F (3, 10173) = 170.996, P<0.5) hence the null hypothesis is rejected. The result of the post-hoc test shows that the poverty index is higher is west Africa compared to the other regions. North Africa has the lowest poverty index compared to other regions. In terms of homogeneity of groups, North African and South Africa fall under the same category as their poverty index is lower. West and East Africa fall under the same groups as their poverty index level is higher. The results of the analysis show that more measures and resources should be directed towards West Africa and East Africa to eradicate poverty in the regions.
References
Anyanwu, J., & Anyanwu, J. (2017). The Key Drivers of Poverty in Sub-Saharan Africa and
What Can Be Done About it to Achieve the Poverty Sustainable Development Goal?
Asian Journal Of Economic Modelling, 5(3), 297-317.
https://doi.org/10.18488/journal.8.2017.53.297.317
Berkman, E., & Reise, S. (2011). A conceptual guide to statistics using SPSS (p. 73).