MonalisaThomas/Songea-Girls-High-School-Performance-Analysis

# Songea Girls High School: A Five-Year Data-Driven Analysis of NECTA Performance (2014–2019) This case study analyzes academic trends at Songea Girls High School using NECTA A-Level exam data (ACSEE) from 2014 to 2019. The dataset was compiled by Yusuph and made publicly available on Kaggle: NECTA Test Results Dataset. As a graduate of the Songea Girls class of 2018 and now a data scientist, I revisited the performance data of my former school to understand long-term academic trends and uncover areas of improvement. The project simulates what it would be like to consult for an NGO focused on enhancing educational outcomes for girls in Tanzania. --- ## Objectives - Analyze subject group performance across five academic years - Identify top-performing subjects - Track student enrollment by subject combination - Evaluate performance trends per subject combination - Estimate changes in total student participation over time --- ## Assumptions - Grading standards were consistent across all years (2014–2019) - Subject scores are proxies for both student comprehension and curriculum delivery quality --- ## Guiding Questions - How strong was performance in Science and Arts over time? - How did the class of 2018 compare to other years? - Which subject groups need targeted support from administrators or education partners? --- ## Analytical Approach - Merged and cleaned yearly NECTA ACSEE data using R - Transformed wide-format datasets into long-form for flexible analysis - Grouped subjects into five categories: Science, Math, Languages, Arts, and Business - Created plots to visualize academic performance and enrollment patterns - Focused exclusively on Songea Girls' data using filtering techniques and visual breakdowns --- ## Key Insights ### Subject Group Performance - **Languages** improved steadily, peaking in 2019. - **Science and Math** had moderate results, with a performance dip in 2016. - A consistent decline was observed across all groups in 2016, l …