To assess the accuracy of vertical components obtained by Classical RTK and Network Real Time Kinematic positioning with different correction methods with setting of different number of epoch, height differences obtained from precise geometric leveling was used as reference height differences along with those obtained from static GPS only solutions, and combined solutions of GPS and GLONASS on different GNSS days. One-way variance analysis (ANOVA) were applied to the height differences to test them whether they are significantly different or not. The significant differences, if any, were further tested by using Post Hoc test to reveal the effects of the method used, the epoch number, or the measuring time, which is responsible for the significant differences. The results from ANOVA showed that the number of epoch had not much effect on the vertical components but on the correction methods. MAC method presented the most deviated results compared to the other methods with different GNSS days' solutions. In general, VRS method was found to be the most consistent method among others used. This study is important in both; an accuracy assessment with respect to the most precise method in heights (i. e., precise geometric leveling) was carried. The techniques (ANOVA and Post Hock Test) used in the accuracy assessment. (C) 2016 Elsevier Ltd. All rights reserved.