Based on the crude fat, protein, amino acids and mineral element content of different areas big particle Coix seed (BCS) and small particle Coix seed (SCS), this paper analyzed whether there was a difference on the major nutrient content between BCS and SCS by using analysis of variance, and discriminated the BCS and SCS by using principal component analysis (PCA) and support vector machine (SVM). The results indicated that the nutrient contents measured in this text of SCS were higher than or not significant difference from those of BCS except the crude fat, Mg, and Al content. The characteristic variables extracted by PCA could be used to discriminate BCS from SCS, and the prediction accuracy of the SVM model was 100%. These display that it is feasible to determine the type of Coix seed by using the major nutrient contents of Coix seed combined with chemometrics.