Many different Small Area Estimation (SAE) methods have been proposed to overcome the challenge of finding
reliable estimates for small domains. Often, the required data for various research purposes are available at different
levels of aggregation. Based on the available data, individual-level or aggregated-level models are used in SAE.
However, parameter estimates obtained from individual and aggregated level analysis may be different, in practice.
This may happen due to some substantial contextual or area-level effects in the covariates which may be misspecified
in individual-level analysis. If small area models are going to be interpretable in practice, possible contextual
effects should be included. Ignoring these effects leads to misleading results. In this paper, synthetic estimators and
Empirical Best Linear Unbiased Predictors (EBLUPs) are evaluated in SAE based on different levels of linear mixed
models. Using a numerical simulation study, the key role of contextual effects is examined for model selection in
Key words: Contextual Effect; EBLUP; Small Area Estimation; Synthetic Estimator.