The Best Quadratic Unbiased Estimation (BQUE) of variance components in the Gauss-Helmert model is used to combine adjustment of GPS/levelling and geoid to determinethe individual variance components for each of the three height types. Through theresearch, different reasons for achievement of the negative variance components werediscussed and a new modified version of the Best Quadratic Unbiased Non-negativeEstimator (MBQUNE) was successfully developed and applied. This estimation could beuseful for estimating the absolute accuracy level which can be achieved using theGPS/levelling method. A general MATLAB function is presented for numericalestimation of variance components by using the different parametric models. Themodified BQUNE and developed software was successfully applied for estimating thevariance components through the sample GPS/levelling network in Iran. In the followingresearch, we used the 75 outlier free and well distributed GPS/levelling data. Threecorrective surface models based on the 4, 5 and 7 parameter models were used throughthe combined adjustment of the GPS/levelling and geoidal heights. Using the 7-parametermodel, the standard deviation indexes of the geoidal, geodetic and orthometric heights inIran were estimated to be about 27, 39 and 35 cm, respectively.