Statistical Analysis of Micro-credit Repayment Performance in Agricultural Cooperatives in Niger State

This study conducts a statistical analysis of micro-credit repayment performance in agricultural cooperatives in Niger State, North Central Nigeria, examining the demographic, financial, and institutional determinants of loan repayment compliance among smallholder farmer borrowers. Niger State's agricultural sector is supported by several state-level and federal micro-credit programmes, yet repayment rates remain below sustainability thresholds for many lending windows, threatening the continuation of credit access for rural farmers. The study analyses administrative records from 28 agricultural cooperatives registered with the Niger State Cooperative Development Agency, covering a combined loan portfolio of 1,840 individual borrower accounts accessed between 2020 and 2024. Binary logistic regression is employed with loan repayment status as the dependent variable, and borrower characteristics including age, gender, educational level, farm size, crop type, prior credit history, group membership solidarity score, and loan size as independent variables. Model performance is assessed using the area under the receiver operating characteristic curve and classification accuracy at optimal probability threshold. Results indicate that prior credit history, group solidarity score, and loan size relative to farm income are the three most statistically significant predictors of repayment performance. Female borrowers in groups with structured mutual guarantee arrangements exhibit significantly higher repayment rates than male counterparts. The study recommends solidarity-based loan monitoring and progressive lending protocols. Keywords: micro-credit, repayment performance, logistic regression, agricultural cooperatives, Niger State