Quality Analysis and Evaluation Method for Multisource Aggregation Data based on Structural Equation Model

In the era of big data, how to evaluate the data quality of multi-source aggregation data is very important. The reason is that uneven data quality will directly lead to inaccurate or ambiguous data in the database, and indirectly lead to the deviation of subsequent data mining and decision-making. In this paper, structural equation model(SEM) is introduced to explore the effectiveness of various data quality evaluation indicators in data aggregation and finding out internal relationship between them. A new quality evaluation method of multi-source aggregation data is proposed, based on the regression's significance analysis and factor loads of each observation index in the SEM model. The case analysis shows that the proposed method is feasible and can be used to evaluate the quality of multi-source aggregation data adaptively for a long time.