ANALISIS DATA KATEGORI DENGAN LOG LINIER MENGGUNAKAN PRINSIP HIRARKI (STUDI KASUS JUMLAH KECELAKAAN LALU LINTAS DI KOTA MAKASSAR TAHUN 2011)
Abstract
Presentation of data commonly used frequency tables, but for categorical data, the table used is the contingency table, it is a table in the form of rows and columns and can be used for two or more variables. As with the variable type of vehicle, age, and education level in the case of traffic accidents of Makassar in 2011. If the case stated in the table is included in the category of three-dimensional contingency table, then the appropriate analysis use is an analysis of the log linear analysis, it is techniques to determine the cause dependency category. The parameters of the log linear models estimated using Maximum Likelihood. Test used is the Goodness of Fit test aims to determine independence between variables with the statistical Chi-Square test or Likelihood Ratio. Furthermore, the selection of the best model using backward Elimination matode which basically uses the principle of hierarchy. In the estimation of log linear models for three-dimensional model has several estimators corresponding to such possible models: estimator for model (X, Y, Z) is 𝑚 𝑖𝑗𝑘= 𝑛𝑖.. 𝑛.𝑗. 𝑛..𝑘 𝑛…
2, then the other estimators in accordance with their respective models. The produced analysis of log linear analysis of traffic accidents in the city of Makassar in 2011 is a model of interaction between the types of vehicles with Last Education and age of the rider with driver education last driver.
This license allows authors to copy, redistribute, remix, transform, and build upon the Work, in any format or medium, for any purpose including commercial purpose, on a perpetual basis provided they credit the Work and the authors. Authors
must explain any changes that were made from the original and may not suggest the authors endorse the use. The resultant work must be made available under the same terms, and must include a link to the CC BY 4.0 International License.