Time-series insolation, environmental, thermal and power data were analyzed in a statistical analytical approach to identify the thermal performance of microinverters on dual-axis trackers under real-world operating conditions. This study analyzed 24 microinverters connected to 8 different brands of photovoltaic (PV) modules from July through October 2013 at the Solar Durability and Lifetime Extension (SDLE) SunFarm at Case Western Reserve University. Exploratory data analysis shows that the microinverter's temperature is strongly correlated with ambient temperature and PV module temperature, and moderately correlated with irradiance and AC power. Noontime data analysis reveals the variations of thermal behavior across different brands of PV module. Hierarchical clustering using the Euclidean distance measure principle was applied to noontime microinverter temperature data to group the similarly behaved microinverters. A multiple regression predictive model has been developed based on ambient temperature, PV module temperature, irradiance and AC power data to predict the microinverters temperature connected with different brands PV modules on dual-axis trackers.