Abstract
Manufacturing efficiency is a critical determinant of industrial growth and structural development. In many developing economies, a persistent gap exists between policy ambitions for industrial transformation and the empirical measurement of efficiency gains at the plant level, hindering effective policy evaluation. This policy analysis aims to develop and evaluate a novel time-series forecasting model to quantify manufacturing efficiency gains, providing a robust methodological tool for assessing the impact of industrial policies on plant-level systems. The analysis employs a state-space modelling framework, integrating plant-level operational data. The core forecasting model is specified as $yt = \mut + \beta Xt + \epsilont$, where $\mu_t$ is a local linear trend component. Model parameters were estimated using maximum likelihood, with inference based on robust standard errors to account for heteroskedasticity. The model identifies a positive but decelerating trend in technical efficiency gains across the studied period, with a notable structural break. Forecasts indicate that, under current policy conditions, the rate of annual efficiency improvement is likely to plateau at approximately 1.2% within the forecast horizon, with a 95% confidence interval of [0.8%, 1.6%]. The proposed model provides a statistically rigorous tool for policy analysis, revealing that existing industrial policies are insufficient to sustain earlier rates of efficiency growth. This underscores a need for targeted interventions. Policy should shift towards incentivising advanced process innovation and capability building within plants. Monitoring and evaluation frameworks must adopt such dynamic forecasting models to move beyond static efficiency snapshots. manufacturing efficiency, time-series forecasting, state-space model, industrial policy, plant systems, Ghana This article provides a novel application of state-space forecasting to the policy analysis of manufacturing efficiency, generating a replicable methodology and a critical evidence base for structural engineering and industrial policy.