We explored the methods of computational statistics in the application of ability assessment for university students. This paper used both exploratory factor analysis and confirmatory factor analysis carried out by statistical analysis software SPSS18.0 and lisrel 8.7, aimed to study a questionnaire which could be used to assess the comprehensive ability of university students. The retest reliability and the Cronbach reliability of the questionnaire were 0.88 and 0.90 respectively. And the structural equation model of university students ability suggested there were five factors: learning ability, innovation, career planning ability, communicative skills and psychological qualities. The indexes of RMSEA, GFI, AGFI, NNFI, NFI and CFI of the model were 0.075, 0.91, 0.91, 0.90, 0.93, and 0.92 respectively. The indexes of reliability and validity met the statistical criteria. The results can provide a guide for the ability assessment of university students.