School of Statistics and Planning (SSP) Collections
Permanent URI for this collection
Browse
Recent Submissions
1 - 5 of 395
-
ItemWill the parish development model pillar 1 services interventions promote agricultural production? An ex- ante analysis on groundnut production using the Uganda panel data set.(Makerere University, 2025-11)Using the UNPS 2018/19 and UNPS 2019/20 datasets, this study assesses how the proxies of PDM pillar 1 services interventions are likely to affect groundnut production in Uganda. Descriptive statistics were used to analyze the distribution and characteristics of respondents. At the multivariable level of analysis, the Random Effects Linear Regression Model was fitted to investigate the likely effects of proxies of the PDM pillar one interventions on groundnuts production in Uganda at a 5% level of significance. The study found that twelve of the seventeen proxies of the PDM pillar one services interventions indeed had a statistically significant (p <0.05) effects on groundnut production in Uganda, ceteris paribus. The PDM pillar one service interventions proxies with statistically significant positive effects included: 1-agriculture extension services, 2-use of agricultural inputs such as: i) quantity of groundnuts seeds sown, ii) organic fertilizer usage, iv) pesticides usage, and v) mechanization (use of tractors and ox-plough), 3-household farmland ownership documentation, 4-access to credits, 5-type of crop stand (pure stand/mono-cropping), 6-quality standard of groundnuts seeds, 7-household members’ participation in community crop harvesting activity, 8-access to markets, 9-erosion control methods, 10-water sources used for farming. Conversely, the PDM pillar one service interventions proxies with statistically significant negative effects included: 2-agricultural inputs, such as inorganic fertilizer usage, 11-commodity storage methods, and 12-transport costs. All the four geographical regions of farmers (such as the Central, Eastern, Northern, and Western regions) negatively affected groundnut production in Uganda. Therefore, the study recommended that: First, all PDM Pillar One interventions with potentially positive effects on groundnut production should be scaled up and strengthened by the Government of Uganda to enhance production. These interventions have demonstrated a capacity to improve production and, therefore, warrant continued investment and expansion to other farming communities. Second, in contrast, interventions with potentially negative effects should be critically reviewed and restructured by the Government of Uganda to address underlying challenges and improve their effectiveness in promoting production and farmer welfare. Subject keywords; Agricultural production, Groundnut production, Parish development model pillar 1, Services interventions,
-
ItemDimension reduction and regularization approaches in response to multicollinearity problem of the prediction of student performance in the final national examination: case of North-Kivu/Goma-DRC(Makerere University, 2025-11)Multicollinearity among predictors in regression models can inflate variance estimates and undermine the stability and interpretability of parameter estimates. This study conducts a comparative analysis of four widely used approaches: Dimension reduction approaches, Principal Component Regression (PCR), and Partial Least Square Regression (PLSR) on one hand and regularization approaches Ridge and Lasso Regression on the other hand. Through Student’s performances dataset, we assessed these methods in terms of model fit and predictive performance, variable selection capability and interpretability. Model selection criteria were employed, as well as T-paired test to compare residuals (MSE) of competing models, Akaike Information Criterion (AIC), and R-Squared (R2) determined the relative effectiveness and prediction accuracy of each approach. Results report there is no significant difference between residuals of Lasso and Ridge regression (Paired t-test P-value =0.15), this means that Ridge and Lasso regression models have same predictive performance. Lastly the test revealed a significant difference between residuals of Partial Least Square and Principal Component Regression (Paired t-test P-value=0.00), this means that PLS regression model outperformed PC regression model in terms of predictive accuracy. Results indicated that Lasso Regression outperformed the other approaches in terms of model fit with the least AIC= -2229.66, followed by the Ridge Regression with AIC= -2225.38, the Partial Least Square Regression and the Principal Component Regression were also performed respectively with AIC of -1041.05 and -1013.925. The findings also revealed the Lasso regression with the highest R2 value (72.7%) indicating the highest proportion of variance explained in the dependent variable. Through all the approaches, the regression models report that Sex, School of the student and Cohort of study were the most significant covariates predictors of the final national score at the national examination. In Addition, three of the four Principal components (humanities social sciences, science and Mathematics, Creative and Technical skills) are significant Predictors of The final Score. In the Ridge and Lasso Regression approaches, French, Chemistry, Civism, English, Probability, Biology, Philosophy and Algebra as the most important predictors of the Final score. Keywords; Student performance, Final national examination, North-Kivu/Goma-DRC
-
ItemCurrent health expenditure and under-five mortality rates in Uganda (2001 to 2021)(Makerere University, 2025)Numerous studies in Sub-Saharan Africa have shown that increased healthcare spending contributes to lower child mortality rates. This study examined whether this relationship holds true for Uganda by assessing the impact of both economic and health system factors on under-five mortality between 2001 and 2021. The main objective was to determine the extent to which current health expenditure per capita influences child survival outcomes, alongside GDP per capita, immunization coverage, and population size. An observational ecological longitudinal (time-series) was used to analyze national-level data from Uganda (2001–2021) on under-five mortality and its one-year lagged predictors, including health expenditure, GDP per capita, immunization coverage, and population size. Data were obtained from UNICEF and World Bank databases. Ridge-adjusted hierarchical regression models were applied to assess associations while controlling for multicollinearity and ensuring model validity. Descriptive analysis revealed substantial variability in under-five mortality (mean = 81.5 deaths per 1,000 live births, standard deviation of 33.14.) and in economic indicators over the 21-year period. Correlation analysis indicated significant negative relationships between under-five mortality and health expenditure per capita, immunization coverage, population size, and GDP per capita. The hierarchical regression model showed that including immunization and population variables increased the explained variance in under-five mortality from 88% to 98%. In the ridge- adjusted model, current health expenditure per capita (β = –0.70, 95% CI -1.40 to -0.01, p = 0.047), immunization coverage (β = –0.97,95% CI -1.52 to -0.41, p = 0.002), and population (β = –2.85, 95% CI -3.86 -1.85, p < 0.001) remained significant predictors, while GDP per capita was not. The study concludes that higher current health expenditure per capita significantly reduces under- five mortality in Uganda, underscoring the importance of targeted health investments in improving child survival. Immunization coverage and population dynamics also play vital roles, whereas general economic growth alone does not ensure better health outcomes. Policy efforts should therefore focus on increasing and efficiently utilizing health spending and sustaining universal immunization programs to accelerate progress toward reducing under-five mortality. Subject Keywords: Health expenditure; Children under-five; mortality rates; Child mortality; Uganda
-
ItemEducation financing and economic growth: an analysis of Uganda's public expenditure in education (1986-2023)(Makerere University, 2025)Uganda’s economy has grown steadily at about 5 to 6% annually, but this progress has not translated into broad-based development. A key challenge lies in low public spending on education averaging only 2.5% of GDP, well below UNESCO’s 6% benchmark which has resulted in reduced learning outcomes and a weak human capital base. This study therefore examines how education expenditure influences economic growth in Uganda, alongside factors such as labor participation, gross capital formation, inflation, and government consumption, to provide evidence-based insights for more effective education financing and sustainable economic transformation. Using 38 cases of annual time series data from the World Bank development indicators from 1986 to 2023, the study models economic growth as a function of education expenditure, labor participation rate, inflation, gross capital formation and government final consumption expenditure. The Autoregressive Distributed Lag (ARDL) approach was employed, using the EViews statistical package, given the mixed stationarity of the variables, to capture both short- and long-run dynamics The results showed that GDP was stable while inflation was highly volatile. Education spending and investment were positively linked to growth, whereas government consumption and inflation had negative effects. Causality analysis indicated that education expenditure, inflation, and investment significantly influenced GDP. Mixed stationarity levels justified using the ARDL model, and the bounds test confirmed a long-run relationship among the variables. The long-run results reveal that education expenditure has a strong and statistically significant positive effect on Uganda’s economic growth (coefficient = 0.7091, p < 0.01), confirming that investment in human capital enhances productivity, innovation, and long-term development. Conversely, labor force participation shows a marginally significant negative effect (-0.086, p = 0.0512), reflecting structural inefficiencies such as underemployment and low productivity that limit its growth contribution. Inflation has a negative but insignificant impact (-0.0059, p = 0.1132), implying that inflation levels during the study period were moderate and did not substantially affect output. Similarly, gross capital formation, though positive (0.039), is insignificant (p = 0.2569), suggesting inefficiencies in investment allocation and weak linkages between capital spending and productive growth. Government consumption expenditure, however, exerts a significant negative effect (-0.108, p = 0.0004), indicating that a large share of public spending in Uganda is unproductive. In the short run, changes in education expenditure, inflation, and investment significantly affect GDP, often with lagged effects, highlighting the importance of policy consistency and efficiency to sustain growth momentum. The study shows that education spending is vital for Uganda’s long-term growth, while inefficiencies in labor, investment, and public spending hinder progress. To sustain growth, this study recommends that Uganda should invest strategically in quality education, strengthen labor skills through vocational and entrepreneurship programs, and improve investment efficiency by prioritizing high-impact projects. Maintaining macroeconomic stability and redirecting public expenditure toward productive sectors are as well essential, alongside continuous research to ensure policies remain effective and responsive to the country’s evolving economic needs. Subject Keywords: Education financing; Economic growth; Uganda; Public expenditure; Education
-
ItemFactors associated with dietary divesity among children 6 to 23 months in Northern Uganda(Makerere University, 2025)Different foods and food groups are important sources of various macro- and micronutrients, which are essential for the physical and mental growth and development of children. Providing children with a diversified diet is therefore crucial. However, little is known about the factors influencing dietary diversity among children in the Northern region of Uganda. This study aimed to examine the factors associated with dietary diversity among children aged 6 to 23 months in this region. Data was analyzed from 387 children aged 6–23 months, collected through the 2022 Uganda Demographic and Health Survey (UDHS). A Negative Binomial regression model was applied to investigate the factors associated with dietary diversity, with model accuracy confirmed through the Likelihood Ratio chi-square test and the link specification test. Findings are presented as adjusted Risk Ratios (aRR) with 95% Confidence Interval (CI). On average, children in the Northern region consumed only 3 out of the 8 recommended food groups. The Negative Binomial regression model identified significant associations between child dietary diversity and several factors. Children from the Lango sub-region (aIRR = 2.106; 95% CI: 1.075–4.124) and those with higher birth-order (aIRR = 1.235; 95% CI: 1.197–1.529) had higher rates of dietary diversity. In contrast, breastfed children (aIRR = 0.420; 95% CI: 0.218–0.807) and those living in larger households (aIRR = 0.931; 95% CI: 0.837–0.994) were found to have significantly lower rates of dietary diversity compared to their respective counterparts. These findings indicated low child dietary diversity in the region, underscoring the need to implement interventions and support programs that focus on improving access to nutritious foods, promoting food security, and providing targeted resources to households with lower dietary diversity. Additionally, enhancing breastfeeding support programs and implementing regional sensitive nutrition education programs may contribute to improved dietary diversity and raise awareness about its importance for children's health and well-being.