1.bartlett spherical test method is based on correlation coefficient matrix. Its zero assumes that the correlation coefficient matrix is a identity matrix, that is, all elements on the diagonal of the correlation coefficient matrix are 1, and all elements on the off-diagonal are zero. According to the determinant of correlation coefficient matrix, the statistics of bartlett spherical test method are obtained.

If the value is large and the corresponding correlation probability value is less than the specified significance level, the null hypothesis is rejected, indicating that the correlation coefficient matrix is not identity matrix, and there is correlation between the original variables, which is suitable for principal component analysis; On the contrary, the null hypothesis holds, there is no correlation between the original variables, and the data is not suitable for principal component analysis.

Second, the spherical test is mainly used to test the distribution of data and the independence of each variable. Ideally, if we have a variable, all the data will be on one line. If there are two completely independent variables, all the data are on two vertical lines. If there are three completely independent variables, all the data are on three mutually perpendicular lines.

If there are n variables, then all the data will be on n mutually perpendicular lines. When the range of each variable is roughly equal (common in all kinds of questionnaire questions), all the data will be distributed like a sphere, which is roughly the same. If the data distribution has not passed the spherical test, then it will violate the assumption of factor analysis when doing factor analysis-each variable is independent of each other to some extent.

Thirdly, there is an option about bartlet spherical test in factor analysis of spss. If the sig value is less than 0.05, the data is spherical.