Open Access Open Access  Restricted Access Subscription Access

An Alternative Approach to AIC and Mallow's Cp Statistic-Based Relative Influence Measures (RIMS) in Regression Variable Selection


Affiliations
1 Department of Statistics, Nnamdi Azikiwe University, Awka, Nigeria
2 Department of Statistics, Abia State Polytechnic, Aba, Nigeria
 

Outlier detection is an important data screening type. RIM is a mechanism of outlier detection that identifies the contribution of data points in a regression model. A BIC-based RIM is essentially a technique developed in this work to simultaneously detect influential data points and select optimal predictor variables. It is an addition to the body of existing literature in this area of study to both having an alternative to the AIC and Mallow's Cp Statistic-based RIM as well as conditions of no influence, some sort of influence and perfectly single outlier data point in an entire data set which are proposed in this work. The method is implemented in R by an algorithm that iterates over all data points; deleting data points one at a time while computing BICs and selecting optimal predictors alongside RIMs. From the analyses done using evaporation data to compare the proposed method and the existing methods, the results show that the same data cases selected as having high influences by the two existing methods are also selected by the proposed method. The three methods show same performance; hence the relevance of the BIC-based RIM cannot be undermined. to the AIC and Mallo

Keywords

Relative Influence Measure (RIM), BIC, AIC, Mallow’s Cp Statistic, Cook’s Distance.
User
Notifications
Font Size

Abstract Views: 89

PDF Views: 1




  • An Alternative Approach to AIC and Mallow's Cp Statistic-Based Relative Influence Measures (RIMS) in Regression Variable Selection

Abstract Views: 89  |  PDF Views: 1

Authors

Umeh Edith Uzoma
Department of Statistics, Nnamdi Azikiwe University, Awka, Nigeria
Obulezi Okechukwu Jeremiah
Department of Statistics, Abia State Polytechnic, Aba, Nigeria

Abstract


Outlier detection is an important data screening type. RIM is a mechanism of outlier detection that identifies the contribution of data points in a regression model. A BIC-based RIM is essentially a technique developed in this work to simultaneously detect influential data points and select optimal predictor variables. It is an addition to the body of existing literature in this area of study to both having an alternative to the AIC and Mallow's Cp Statistic-based RIM as well as conditions of no influence, some sort of influence and perfectly single outlier data point in an entire data set which are proposed in this work. The method is implemented in R by an algorithm that iterates over all data points; deleting data points one at a time while computing BICs and selecting optimal predictors alongside RIMs. From the analyses done using evaporation data to compare the proposed method and the existing methods, the results show that the same data cases selected as having high influences by the two existing methods are also selected by the proposed method. The three methods show same performance; hence the relevance of the BIC-based RIM cannot be undermined. to the AIC and Mallo

Keywords


Relative Influence Measure (RIM), BIC, AIC, Mallow’s Cp Statistic, Cook’s Distance.