Question

We can potentially evaluate the performance of Logit/Probit models based on measures calculated from the confusion matrix, such as precision and recall. However, in many cases, these two measures may send conflicting messages. Let's say we have two models (M1 and M2), where the precision of M1 = 0.8 and the recall of M1 = 0.4, whereas the precision of M2 = 0.4 and the recall of M2 = 0.8. How would you choose between the two models? Explain.

Name: we can potentially evaluate performance of logitprobit models based on measures calculated from the confusion matrix such as precision and recall however in many cases these two measures may 11476
Uploaded: 2023-07-10T17:19:26-08:00
Duration: 2 min 29 s
Channel: Madhur L
Description: we can potentially evaluate performance of logitprobit models based on measures calculated from the confusion matrix such as precision and recall however in many cases these two measures may 11476

          We can potentially evaluate the performance of Logit/Probit models based on measures calculated from the confusion matrix, such as precision and recall. However, in many cases, these two measures may send conflicting messages. Let's say we have two models (M1 and M2), where the precision of M1 = 0.8 and the recall of M1 = 0.4, whereas the precision of M2 = 0.4 and the recall of M2 = 0.8. How would you choose between the two models? Explain.

Added by Joaquin H.

Elementary Statistics a Step by Step Approach

Allan G. Bluman 9th Edition

Instant Answer

Solved by Expert Madhur L

07/10/2023

Step 1

Precision (P) is the ratio of true positive predictions to the total number of positive predictions, i.e., the proportion of correct positive predictions among all positive predictions. It is given by: $$P = \frac{TP}{TP + FP}$$ Recall (R), also known as Show more…

Show all steps

Thanks for your feedback!

We can potentially evaluate the performance of Logit/Probit models based on measures calculated from the confusion matrix, such as precision and recall. However, in many cases, these two measures may send conflicting messages. Let's say we have two models (M1 and M2), where the precision of M1 = 0.8 and the recall of M1 = 0.4, whereas the precision of M2 = 0.4 and the recall of M2 = 0.8. How would you choose between the two models? Explain.