Urban Development Sociology of Metropolitan Streetlight Cost-Sharing Levy Arrears and Night Market Vendor Withdrawal in Lagos's Low-Income Districts: A Bunching Estimation of Arrears Thresholds

The central problem is that conventional regression approaches treat vendor exit as a smooth function of arrears, obscuring the possibility that withdrawal concentrates at specific arrears levels where enforcement, social sanction or administrative classification changes discretely. Because no observational data are available for the present analysis, the contribution is methodological: the paper specifies the identifying assumptions, the estimation equation, the data requirements and the inferential limits of a bunching approach applied to this setting. A design-based power analysis, parameterised by a between-cluster standard deviation of 6.0, a residual standard deviation of 4.5 and an intraclass correlation of 0.64, indicates that 56 clusters would be required to detect a 5 percentage point effect at 80 per cent power. The framework clarifies how threshold identification can distinguish administrative from economic mechanisms in vendor withdrawal, and it specifies the conditions under which bunching estimates would and would not support causal interpretation.