Factor affecting the severity of the dengue fever using multivariate adaptive regression spline (Mars) method

Dengue fever is a disease that still has a global problem in more than 100 countries in the world. If the DBD system is infected, the virus can be used to treat the virus. Dengue fever with four degrees of severity, such as class I (mild), class II (moderate), class III (severe) and class IV (very severe). In this study, patients were divided into two categories, severe and non-severe. One statistical method that can be used for keeping the factors that vary as you love to be sued is Multivariate Adaptive Regression Spline (MARS). MARS is a nonparametric regression model that can be used for the data problem that knows bestas crank dimension and more than the prediction that corresponds to the respondent. MARS is a very complex complex with spline and Recursive Partitioning Regression (RPR). In this study we cautioned the use of MARS to determine the factors that caused berdarah fever in Rumah Sakit Islam Jemursari Surabaya. Minimum data rate General Cross Verification GCV 0.04181718 for Basic aggregation (BF) = 51, Maximum Interaction (MI) = Minimum Observation (MO) 3 days = 2. APER and Press'Q.