Statistical Analysis of Unemployment Trends Among Youth in Lagos State Using Time Series Methods

Youth unemployment remains a critical socioeconomic challenge in Lagos State, Nigeria's commercial hub in the South West geopolitical zone, where rapid population growth has outpaced formal job creation. This study applies time series statistical methods to analyse unemployment trends among youth aged 15 to 35 years in Lagos State from 2015 to 2023. Monthly unemployment data were sourced from the National Bureau of Statistics and Lagos State Ministry of Economic Planning and Budget. Exploratory data analysis, trend decomposition using the classical additive model, and autoregressive integrated moving average (ARIMA) modelling were employed to identify trend patterns, seasonal fluctuations, and generate short-term forecasts. The augmented Dickey-Fuller test confirmed non-stationarity in the original series, requiring first-order differencing. The best-fitting model, ARIMA(1,1,1), yielded a mean absolute percentage error of 4.3 percent on the holdout validation set. Trend decomposition revealed a persistent upward unemployment trend punctuated by seasonal peaks in the first quarter of each year, corresponding to post-graduation entry cohorts. Structural breaks were identified in 2020, coinciding with COVID-19 economic disruptions. Forecast projections indicate continued youth unemployment elevation through 2025 without targeted intervention. The study provides a data-driven baseline for labour policy evaluation and recommends integration of real-time administrative employment records into the Lagos State statistical monitoring framework. Keywords: youth unemployment, time series, ARIMA, Lagos State, trend analysis