This paper proposes a novel approach to infer missing electricity meter data of a building using a seasonal autoregressive integrated moving average model with exogenous variables (SARIMAX). A cross-correlation function is utilized to identify buildings that have electricity usage patterns similar to the building with missing meter data. We train a SARIMAX model using the historic electricity usage of the building with missing data,the weather temperature as an exogenous variable,and electricity usage of buildings identified to be similar to the building of interest,to facilitate collaborative inference of missing meter data. The proposed approach is verified using actual 15-minute interval electricity meter data of four office buildings in Northern California.