School of Statistics and Planning (SSP) Collections
Permanent URI for this collection
Browse
Recent Submissions
1 - 5 of 424
-
ItemMale circumcision uptake in Uganda and it's associated factors: a structural equation modelling approach(Makerere University, 2025)The World Health Organization (WHO) and UNAIDS recommend male circumcision as a preventive measure against HIV, with evidence showing about a 60% reduction in the risk of male-to-female HIV transmission. This study aimed to identify factors influencing the uptake of male circumcision in Uganda. Data from 5,008 men aged 15–54 years were drawn from the Uganda Demographic and Health Survey. A Generalized Structural Equation Model (GSEM) was applied to simultaneously estimate both direct and indirect effects of potential predictors on circumcision uptake. Results from direct effect analysis show that, holding other factors constant, increased likelihood of having undergone male circumcision was associated with men with secondary education (coef = 0.153, p=0.000) compared to men with no education, men who are rich (coef= 0.076, p =0.000) compared to men who are poor, men living with a partner (coef= 0.087, p =0.000) compared to men never in union. However an increase in the age of respondents was associated with less likelihood of having undergone male circumcision. Indeed the likelihood of having undergone male circumcision was lower for age group 35-44(coef= -0.139, p=0.000) and age group 45-54(coef= -0.176, p= 0.000) compared to age group 15-24. ). Also rural residents were less likely to have undergone male circumcision (coef= -0.069, p =0.000) compared to urban residents. Region was also found to significantly affect male circumcision status. Indeed, men from northern (coef = -0.237, p = 0.000) and western (coef=-0.108, p=0.000) were less likely to have undergone male circumcision compared to men from Central. Indirect effect analysis showed no significant mediation through comprehensive HIV knowledge, indicating that observed associations were driven entirely by direct effects. Increasing male circumcision uptake in Uganda requires targeted health education for men with lower education levels, expanded free or subsidized services for poorer men, and couple‑focused communication to encourage partner support. Age‑specific interventions should address older men’s concerns about pain and healing, while rural access must be improved through mobile clinics, community health workers, and local leadership engagement. Finally, region‑specific strategies that respond to cultural beliefs and service gaps are essential to ensure equitable uptake across the country.
-
ItemPredictors of women’s participation in crop farming and livestock rearing in Uganda(Makerere University, 2025)This study examined the predictors of women’s participation in crop farming and livestock rearing in Uganda. Specifically, it assessed the effects of land size and tenure systems, access to extension services, availability of financial and input resources, and selected socio-demographic characteristics on women’s engagement in the two agricultural subsectors. Given that women constitute a substantial share of Uganda’s agricultural workforce, identifying these predictors is critical for informing targeted and inclusive agricultural policies. The study employed descriptive statistics, correlation analysis, and logistic regression techniques using data from the 2019 Annual Agricultural Survey. The results indicate that 57.7 percent of women participated in crop farming, while 62.9 percent were involved in livestock rearing. In crop farming, land tenure emerged as a key determinant, with Mailo and customary tenure reducing participation, while access to public land and larger land sizes increased women’s engagement. Access to extension services and storage facilities positively influenced participation, whereas reliance on radio or farmer-to-farmer information channels and being divorced or separated were associated with lower participation. In livestock rearing, Mailo tenure, access to extension services, farmer training, agricultural credit, transport, and storage facilities significantly enhanced women’s involvement, while leasehold tenure, higher levels of education, and information obtained through radio or informal sources reduced participation. Notable regional disparities were observed, with women in the Northern region being more likely to engage in livestock rearing than their counterparts in the Central region. The study recommends strengthening women’s access to and control over land, expanding agricultural extension and training services, and improving access to credit, transport, and storage infrastructure to enhance women’s participation in both crop farming and livestock rearing. In addition, policy interventions should account for socio-demographic differences by supporting single or divorced women, addressing regional inequalities, and promoting entrepreneurship and market linkages to encourage greater participation among educated women.
-
ItemAn approach to enhance the performance of the Xgboost Classifier(Makerere University, 2025)XGBoost is a dominant machine learning model for prediction and classification tasks. The XGBoost algorithm is an ensemble that often outperforms other machine learning models due to its enhanced predictive performance, efficiency, and regularization technique that prevent overfitting and underfitting. However, its heavy reliance on hyperparameter tuning creates computational weaknesses due to the intensive resource requirements of traditional methods like grid and random search. Furthermore, the raw features used for classification tasks may contain complex, non-linear relationships, not explicitly captured by XGBoost’ s base leaners. This study proposed an improved alternative by combining k-means clustering with Bayesian-optimized XGBoost. To validate this approach, the study utilised the red wine dataset from the UCI data repository. We first derived objective quality clusters from physicochemical attributes (like acidity, sugar, alcohol content) using k-means. Thereafter, two hyperparameter tuning approaches were then compared: (1) traditional hyperparameters, (2) Bayesian optimization. This study demonstrates that combining k-means clustering with Bayesian-optimized XGBoost significantly improves model classification accuracy compared to the use of traditional hyperparameters. When evaluated, the cluster-based model with Bayesian optimization achieved a 97.9% accuracy, F1-score of 97.4% and recall of 98.05%. On the other hand, the baseline model achieved 93.1% accuracy, 96.18% F1-score and 97.2% recall. This study demonstrates that the integration of k-means clustering with Bayesian optimization significantly enhances the performance of the XGBoost classifier. Consequently, we recommend deploying this validated model in real-world applications, such as automated wine quality grading, as well as in other industrial domains that require scalable and accurate classification solutions.
-
ItemMethodological aspects in the construction of a composite indicator of service delivery in Uganda(Makerere University, 2025)This study elaborates methodological aspects encountered in the building of composite indicators with application to service delivery in Uganda. This study amplified the three main stages, the selection of quality data, the building of the composite indicator itself and statistical approaches that may be utilized to model service delivery composite indicator (CI). This study formulated a data quality assessment framework (DQAF) to enhance the construction of a composite indicator. The DQAF was formulated with a dual orientation that prioritizes two user-oriented data quality components (DQCs) namely; relevance, and interpretability, and three producer-oriented DQCs of methodological soundness, accuracy, and statistical adequacy. The application of the DQAF to service delivery data resulted in the selection of 51 from a pool of 103 potential indicators, reflecting a 48.6% acceptability percentage. The composite indicator for statistical regions, which included five dimensions—education, health, water, agriculture, and roads—was developed utilizing official data from the 2021 National Service Delivery Survey conducted by the Uganda Bureau of Statistics, along with various sector performance reports from the Ministry of Health and the Ministry of Water and Environment. Additionally, the study developed an alternative composite indicator for district local governments, concentrating on the education, health, and water dimensions, which was modeled against potential covariates. The composite indicator for statistical regions indicated that Uganda achieved a score of 0.49 (0 ≤ composite indicator score ≤ 1) utilizing equal weighting, minimax transformation, and additive aggregation, whereas the score was 0.45 with equal weighting, distance-to-reference point transformation, and geometric aggregation. Min-max transformation yields higher scores compared to distance-to-reference point, attributable to the exogenously determined goalposts. Weights that are participatory determined were comparable with data-derived weights. Robustness tests demonstrated that the constructed composite indicator exhibited stability and can therefore be utilized. The absolute differences in ranks by region were observed, with Kampala and Lango exhibiting the lowest differences and Karamoja and Kigezi the highest, attributable to the presence of outliers and inequitable performance in the examined variables. The aggregation stage was the most sensitive accounting for nearly 60% of the total variance, primarily due to interaction with mainly the transformation stage; this underscores the necessity to cautiously select an aggregation method, as it greatly influences the robustness of the results. The absolute rank differences were highest in the education dimension at 2.00 and lowest in the roads and health dimension at 1.33, indicating the varying impact of excluding aspects from the composite index. In assessing the differentials of service delivery at local government level, the composite indicator scores ranged from 0.25 to 0.60, with a substantial portion of the density plot situated below 0.50, indicating inadequate service delivery levels. While beta regression adeptly models bounded data, random forest regression highlights the relative importance of predictors, and generalized additive model captures non-linear covariate effects. The comparable predictive accuracy of these methods, as evaluated using root mean square error, suggests their applicability to this investigation in accordance with the analytical objectives. It is recommended that data quality assessment frameworks should encompass producer and user data quality components that are developed collaboratively with potential users of the composite indicator, in addition to identifying and addressing redundancies among them. Given that the aggregation stage was the most sensitive, it is recommended to explore the use of penalization techniques to address the substitution of variables while maintaining official statistics.
-
ItemMacroeconomic determinants of retail banking loan performance in Uganda: a case of ABSA Bank(Makerere University, 2025)This study examines the macroeconomic determinants of retail banking loan performance in Uganda, focusing on Absa Bank Uganda. Using quarterly secondary data from 2015 to 2023, the research investigates the influence of key macroeconomic variables GDP growth, inflation, unemployment, and exchange rate on loan performance. The data were analyzed using descriptive statistics, correlation analysis, and the Autoregressive Distributed Lag (ARDL) modeling technique. The findings reveal that the exchange rate has a statistically significant positive impact on loan performance, suggesting that depreciation of the Uganda Shilling is associated with improved loan recovery efforts, possibly due to stricter repayment enforcement or inflation induced repayment prioritization. In contrast, GDP growth, inflation, and unemployment were found to have no significant effect on loan performance during the study period. The model explained approximately 77.9% of the variation in loan performance, confirming a strong explanatory power. The study concludes that exchange rate fluctuations are a critical driver of retail loan performance in Uganda. It recommends that banks strengthen foreign exchange risk management and enhance credit risk assessment based on past repayment patterns. Subject keywords: Macroeconomic determinants; Retail banking; loan performance; Uganda; ABSA Bank