Abstract:
Climate variability is analyzed by applying linear and nonlinear statistical methods. Their use aims to compare and demonstrate the advantages and disadvantages of each technique in the analysis of climate series. The use of correlation analysis with a time lag confirmed the generally accepted view that carbon dioxide (CO2) is the main initiator of global warming. The multiple linear regression showed that the selection of factor variables must be done very carefully, taking into account the potential dependences between them. Using nonlinear regression, it was found that the variations of the Earth’s magnetic field is an alternative to CO2 as an engine of modern global warming.

Keywords:
statistical methods, climate variability, geomagnetic field, surface temperature