Jamshid Parvar

A logistic regression approach to modelling the contractor's decision to bid

Significant factors in the decision to bid process are identified and a pro‐forma to elicit a numerical assessment of these factors is developed and validated using the bid/no‐bid decision‐makers from a UK construction company. Using the pro‐forma, data were collected from the collaborating company for historical bid opportunities. Statistical techniques are used to gain a better understanding of the data characteristics and to model the process. Eight variables have a significant relationship with the decision to bid outcome and for which the decision‐makers are able to discriminate. Factor analysis is used to identify the underlying dimensions of the pro‐forma and to validate functional decomposition of the factors. Finally, two logistic regression models of the decision to bid process are developed. While one model is ultimately rejected, the selected model is capable of classifying the total sample with an overall predictive accuracy rate of 94.8%. The results, therefore, demonstrate that the model functions effectively in predicting the bid/no‐bid decision process.