In the field of Earth sciences, understanding and modeling the complex dependencies among various variables, including their statistical distributions and relationships, is crucial for many applications. Assessing the combined effect of multiple independent variables on several dependent variables is often the focus of many studies. Canonical correlation analysis (CCA) is a valuable tool that enables the simultaneous measurement of the impact of multiple independent variables on multiple dependent variables, providing more precise and reliable analysis. Precipitable Water Vapor (PWV) is a fundamental parameter in the field of climate change and weather forecasting. This parameter exhibits significant spatial and temporal variations and can be estimated using Global Positioning System (GPS) observations. In this study, canonical correlation analysis was used to examine the relationship between PWV obtained from GPS observations and five meteorological parameters (temperature, relative, dew point temperature, soil surface temperature, and wind speed) from the ERA-5 model. The study area, located in North America, includes 25 GPS stations. PWV values were estimated using GPS data for a week in the summer. The findings show an 88% canonical correlation coefficient between PWV and the meteorological parameters from the ERA-5 model, indicating a strong positive correlation where changes in one group of variables lead to changes in the other.