MENU
An analyst fits a logistic regression model to predict whether or not a client will default on a loan. One of the predictors in the model is agent, and each agent serves 15-20 clients each. The model fails to converge. The analyst prints the summarized data, showing the number of defaulted loans per agent. See the partial output below:
What is the most likely reason that the model fails to converge?
Suggested Answer: A
Get Premium A00-240 Questions
as Interactive Web-Based Practice Test or PDF
Real Exam Format
Detailed Explanations
Instant Access
Get Your Practice Test
11 comments · newest first
DE
Deeanna
12 months ago
Missing values could also mess things up, but not as likely.
KI
Kimberely
12 months ago
Wait, how can there be too many observations? That seems odd.
JA
Jarvis
1 year ago
I thought collinearity could be a problem too, though.
TE
Teresita
1 year ago
Totally agree, that’s a classic reason for non-convergence.
SA
Sabra
1 year ago
Looks like quasi-complete separation is the issue here.
CA
Carmelina
1 year ago
I doubt having too many observations is the issue; more data usually helps, right? It seems like A is the most likely answer.
HO
Hollis
1 year ago
Missing values could be a factor, but I feel like they usually just lead to warnings rather than convergence failures.
BE
Bettina
1 year ago
I think collinearity could also be a problem, but I’m not sure if it would prevent convergence like separation would.
LO
Loreen
1 year ago
I remember something about quasi-complete separation causing convergence issues in logistic regression. That might be it.
DE
Denna
1 year ago
This looks like a classic cross-site scripting (XSS) attack. The attacker is injecting malicious JavaScript code into the URL, which could be executed by the victim's browser.
KA
Karma
1 year ago
Okay, I've got a strategy for this. I'll start by eliminating the options that I know are false, then focus on the remaining ones to determine which three are true. Single-row functions can be tricky, but I think I can work through this.