A study examined the relationship of native language and level of English proficiency to the structure of the Test of English as a Foreign Language (TOEFL). Using all of the information provided by various responses to the test's items (the four alternatives, omitted, and not reached), the items' interrelations were analyzed by three-way multidimensional scaling for samples of examinees systematically varying in native language and level of English proficiency. Four dimensions were identified: three corresponded to the sections of the test, and the fourth was an end-of-test phenomenon. The dimensions were predominantly defined by easy items and were most salient for low-scoring examinees. Native language had little influence on results. The major conclusions were that the TOEFL's construct validity is supported, the test's interpretation varies with the examinees' English proficiency, easy and difficult items differ in their potential for diagnosis and global screening, and the dimensionality of the TOEFL and of competence in English depends on the examinees' English proficiency. (Author/MSE)