Abstract

A very common problem when building software project effort models is dealing with missing data. To address this there exist a range of imputation techniques. However, selecting the appropriate imputation technique can also be a difficult problem. One reason for this is that these techniques make assumptions about the underlying missingness mechanism, that is how the missing values are distributed within the data set. It is also compounded by the fact that for small data sets it may be very difficult to determine what is the missingness mechanism. This means there is a danger of using an inappropriate imputation technique. Therefore, it is necessary to determine what is the safest default assumption about the missingness mechanism for imputation techniques when dealing with small data sets. In this short paper, we try to help assess what imputation method can be used under what circumstances by assessing the impact of different missingness mechanisms. We consider two simple and commonly used techniques: Class Mean Imputation (CMI) and k Nearest Neighbors (k-NN) coupled with two missingness mechanisms: missing completely at random (MCAR) and missing at random (MAR). We conclude that the impact of missingness mechanism on the MMREs is not statistically significant. Therefore MAR is a reasonable missingness mechanism assumption for both CMI and k-NN methods to impute missing software project data.

Citations