Συγκρίσεις εναλλακτικών μεθόδων παλινδρόμησης σε οικονομετρική ανάλυση μικροδεδομένων : γραμμική και παλινδρόμηση πεμπτημορίων
View/ Open
Keywords
Γραμμική παλινδρόμηση ; Παλινδρόμηση πεμπτημορίων ; SHARE ; ΣυντάξειςAbstract
Multiple Linear Regression is the most common method of detecting the
conditional mean behavior of a variable, when is affected by a set of different
variables. On the contrary, Quantile Regression studies the behavior of the response
variable over the entire range of its distribution. The current study compares the
models, their particularities and their differences. Furthermore, data from the 8 th
wave of SHARE survey were used to detecting which factors affect the annual
pension amount. The statistical analysis of the data was realized using SPSS 26,
using regression models. The purpose of the study was to compare the two regression
models to determine which had better interpretive capacity at the height of pensions.
From the analysis, Linear Regression assumptions were not met for the conclusions
to be reliable, while Quantile Regression could possibly separate the low from the
high levels of the pension amount.