The paper analyzes the causal relationship between energy demand and economic growth in Bangladesh using annual time series data from 1980 to 2011 from World Development Indicator (WDI), Database of the World Bank. Since the results of causal direction are sensitive to the models being employed, the paper uses Maximum Entropy Bootstrap (meboot) due to its superiority to overcome small sample bias and limitation of asymptotic distribution theory. To avoid the omitted variables bias, the paper uses multivariate framework in production function specification. The paper finds that a unidirectional causality runs from economic growth to energy demand which indicates that conservative policy might not harm the Bangladesh economy but since economic progress leads higher energy consumption, demand side management of energy and exploring renewable energy sources are must. The implications are discussed.