Likelihood Ratio Test (LRT) and Best Linear Unbiased Estimator (BLUE) have been researched as estimation methods of observation event in sensor network. LRT and BLUE can estimate the observation event with high accuracy at the Fusion Center (FC) when the FC has a perfect knowledge of observation statistics of each sensor node. However, all the sensor nodes ' observation statistics are not always available at the FC. In this paper, we propose a method to estimate false alarm probability and observation noise variance of each sensor node at the FC, and present the performance of LRT and BLUE using the proposed estimation method. We show that the LRT and BLUE using the proposed method achieve almost the same bit error rate (BER) as the conventional LRT and BLUE with perfect knowledge of them.