This paper considers a homogeneous multiple regression (HMR) model and a non-homogeneous multiple regression model, that is, ensemble model output statistics (EMOS), which are easy to implement postprocessing techniques to calibrate probabilistic forecasts that take the form of Gaussian probability density functions for continuous weather variables. The HMR and EMOS predictive means are biascorrected weighted averages of the ensemble member forecasts and the EMOS predictive variance is a linear function of the ensemble variance. We also consider the alternative implementations of HMR and EMOS which constrains the coefficients to be non-negative and we call these techniques as HMR+ and EMOS+, respectively. These techniques are applied to the forecasts of surface temperature over Pyeongchang area using 24-member Ensemble Prediction System for Global (EPSG). The performances are evaluated by rank histogram, residual quantile-quantile plot, means absolute error, root mean square error and continuous ranked probability score (CRPS). The results showed that HMR+ and EMOS+ models perform better than the raw ensemble mean, HMR and EMOS models. In the comparison of HMR+ and EMOS+ models, HMR+ performs slightly better than EMOS+ model in terms of CRPS, however they had a very similar CRPS and if there exists a ensemble spread-skill relationship, it is seen that EMOS is slightly better calibrated than the homogeneous multiple regression model.