The impact of pre-selected variance inflation factor thresholds on the stability and predictive power of logistic regression models in credit scoring

Abstract

Standard Bank, South Africa, currently employs a methodology when developing application or behavioural scorecards that involves logistic regression. A key aspect of building logistic regression models entails variable selection which involves dealing with multicollinearity. The objective of this study was to investigate the impact of using different variance inflation factor 1 (VIF) thresholds on the performance of these models in a predictive and discriminatory context and to study the stability of the estimated coefficients in order to advise the bank. The impact of the choice of VIF thresholds was researched by means of an empirical and simulation study. The empirical study involved analysing two large data sets that represent the typical size encountered in a retail credit scoring context. The first analysis concentrated on fitting the various VIF models and comparing the fitted models in terms of the stability of coefficient estimates and goodness-of-fit statistics while the second analysis focused on evaluating the fitted models' predictive ability over time. The simulation study was used to study the effect of multicollinearity in a controlled setting. All the above-mentioned studies indicate that the presence of multicollinearity in large data sets is of much less concern than in small data sets and that the VIF criterion could be relaxed considerably when models are fitted to large data sets. The recommendations in this regard have been accepted and implemented by Standard Bank.

Family Relations and Remarriage Postdivorce and Postwidowhood in China

“…Given the dynamic and time-sensitive nature of care exchange, we are also careful to report and discuss the results in terms of association rather than causality. In both sets of models, the variance inflation factor test was conducted and the variance inflation factor values were well below the conservative threshold of 2.5 for all our key variables (de Jongh et al, 2015).…”

Cardiovascular risk prediction model and stratification in patients with type 2 diabetes enrolled in a Medicare Advantage plan

“…Applying both the VIF and correlation thresholds was felt to sufficiently address any multicollinearity and the thresholds acceptable for large sample sizes. 25 The final best model was created using only the training data sample.…”

Dual-stage and dual-deficit? Word recognition processes during text reading across the reading fluency continuum

“…For FFD and SRD, log-transformed values were analyzed to fulfill regression model assumptions, including random distribution of residuals and good fit over the entire scale of the dependent variable. The multicollinearity was inspected with the vif-function (variance inflation factor) of the car-package and was not found to be problematic for any of the analyses (< 3.1;De Jongh et al, 2015). The observed statistical power (simr -package; Green & MacLeod, 2016) in the lmer-analyses was optimal (90-95%) for testing two-way interactions, but low for testing the three-way interaction (30-40%).…”