We estimated sample size of 100 people, with a power
of 80%, and α error of 0.05 to detect 15% diffrence in VAP
incidence between two groups. Qualitative variables
were reported as percentage and quantitative variables
as mean± standard deviation. We used Student t test
and chi-square test for detection of diffrences between
two groups. Fisher exact test was used for qualitative
analysis when it is necessary. The Logistic regression
analysis with "Enter" method was applied in order to
evaluate the effcts of selected independent variables
on VAP incidence. In this analysis, odds ratios and their
95% confience interval (CI) were reported. SPSS 16 program was used for statistical analysis. P value equal or
less than 0.05 was considered statistically signifiant.