TY  - JOUR
T1  - A MODEL SELECTION APPROACH IN STATISTICAL MODELING
AU  - Menteş, Turhan
JF  - Hacettepe Journal of Mathematics and Statistics
PB  - Hacettepe University
WT  - DergiPark
SN  - 2651-477X
SP  - 131
EP  - 135
VL  - 39
IS  - 1
LA  - en
AB  - It is argued that quantitative results from statistical surveys and experiments should be communicated as inferences of the model maximisingthe log Bayes factor against a reference model penalised by a subjectively chosen constant times the difference in model complexity. Modelcomplexity is measured by the degrees of freedom. In this study, anefficient algorithm is proposed to select a model from among a large setof models with unit penalties in some interval. The algorithm utilizesthe penalised log Bayes factor with only the likelihood ratio statistic,model dimensions and a constant. This approach seems to be a morerealistic screening device than related criteria similar to the Bayesianinformation criterion.
KW  - Model selection
KW  - Bayes factor
KW  - Penalty function
KW  - Utility function
CR  - ...
UR  - https://dergipark.org.tr/en/pub/hujms/issue//531117
L1  - https://dergipark.org.tr/en/download/article-file/655732
ER  -