https://communities.sas.com/t5/Statistical-Procedures/Zero-One-Inflated-Regression-Bias/m-p/721575#M34958 <DIV>We have recently been trying to use the zero-one inflated beta regression macros that you was published in conjunction with SAS Global Forum 2012; they have been very helpful in more accurately modelling the Loss Given Default (LGD) data that we encounter!</DIV><DIV>&nbsp;</DIV><DIV>I am puzzled by something we have observed, and was hoping someone might have some suggestions as to how to proceed.</DIV><DIV>&nbsp;</DIV><DIV>In our dataset, the probability of the zero and one outcomes are ~55% and ~22% respectively.&nbsp; After modelling, the average predicted probabilities are ~71% and ~48% respectively.&nbsp; I am surprised that: (i) the predicted probabilities appear to be biased (i.e., they are not replicating the observed probabilities in the dataset); and (ii) that they sum to &gt;100%, which is obviously impossible.</DIV><DIV>&nbsp;</DIV><DIV>We want to use the model to make forecasts, but given the 'raw' predictions this would obviously&nbsp;result in overestimation.&nbsp; I am thinking of making some simple adjustments (i.e., applying ratios of 55%/71% and 22%/48% to model predictions), but I am wondering whether someone might have some other suggestions that we should consider.</DIV> Wed, 24 Feb 2021 14:20:29 GMT Jesse_C 2021-02-24T14:20:29Z https://communities.sas.com/t5/Statistical-Procedures/Zero-One-Inflated-Regression-Bias/m-p/721575#M34958 <DIV>We have recently been trying to use the zero-one inflated beta regression macros that you was published in conjunction with SAS Global Forum 2012; they have been very helpful in more accurately modelling the Loss Given Default (LGD) data that we encounter!</DIV><DIV>&nbsp;</DIV><DIV>I am puzzled by something we have observed, and was hoping someone might have some suggestions as to how to proceed.</DIV><DIV>&nbsp;</DIV><DIV>In our dataset, the probability of the zero and one outcomes are ~55% and ~22% respectively.&nbsp; After modelling, the average predicted probabilities are ~71% and ~48% respectively.&nbsp; I am surprised that: (i) the predicted probabilities appear to be biased (i.e., they are not replicating the observed probabilities in the dataset); and (ii) that they sum to &gt;100%, which is obviously impossible.</DIV><DIV>&nbsp;</DIV><DIV>We want to use the model to make forecasts, but given the 'raw' predictions this would obviously&nbsp;result in overestimation.&nbsp; I am thinking of making some simple adjustments (i.e., applying ratios of 55%/71% and 22%/48% to model predictions), but I am wondering whether someone might have some other suggestions that we should consider.</DIV> Wed, 24 Feb 2021 14:20:29 GMT https://communities.sas.com/t5/Statistical-Procedures/Zero-One-Inflated-Regression-Bias/m-p/721575#M34958 Jesse_C 2021-02-24T14:20:29Z