Ryfujk

Affine transformation of circular arc in 3D

3.5% Interest Student Loan or use all of my savings on Tuition?

What does "rhumatis" mean?

What is the oldest European royal house?

Is every open circuit a capacitor?

An Undercover Army

Calculate total length of edges in select Voronoi diagram

Computing the volume of a simplex-like object with constraints

Named nets not connected in Eagle board design

Can inspiration allow the Rogue to make a Sneak Attack?

What's the best tool for cutting holes into duct work?

Remove object from array based on array of some property of that object

When to use the term transposed instead of modulation?

Sundering Titan and basic normal lands and snow lands

Are there other characters in the Star Wars universe who had damaged bodies and needed to wear an outfit like Darth Vader?

Is there a way to find out the age of climbing ropes?

Is this nominative case or accusative case?

Create chunks from an array

Under what conditions would I NOT add my Proficiency Bonus to a Spell Attack Roll (or Saving Throw DC)?

Convert an array of objects to array of the objects' values

Why aren't there more gauls like Obelix?

Practical reasons to have both a large police force and bounty hunting network?

Professor forcing me to attend a conference

Was it really inappropriate to write a pull request for the company I interviewed with?

Area Under the Curve - Variable and Log Transformed Variable

How to calculate sample size for comparing the area under the curve of two models?pattern of ROC curve and choice of AUCArea Under Curve ROC penalizes somehow models with too many explanatory variables?Area Under the ROC Curve, a simple questionArea Under the ROC Curve: Comparing identification performance between two values of the same variabletwo questions; how to interpret the AUROC (area under the ROC curve)Area Under the Curve physical meaningArea Under The Receiver Operating - incompatible explanationsQ: Possible to optimize for area under the precision-recall curve in glmnet logistic regression?How to distinguish overfitting and underfitting from the ROC AUC curve?

2

$begingroup$

I have a situation where I am fitting two simple logistic regression models - one model with the variable of interest included as the only predictor, and the other model with the log of the variable of interest included as the only predictor. Both models have the same Area Under the Curve, and I would like to know how to explain why this occurs. I am sure this is not due to chance, but rather has something to do with how AUC is calculated, and it's interpretation.

logistic roc auc

share|cite|improve this question

edited 4 hours ago

APK

asked 5 hours ago

APKAPK

1278

$endgroup$

add a comment | 

2

$begingroup$

I have a situation where I am fitting two simple logistic regression models - one model with the variable of interest included as the only predictor, and the other model with the log of the variable of interest included as the only predictor. Both models have the same Area Under the Curve, and I would like to know how to explain why this occurs. I am sure this is not due to chance, but rather has something to do with how AUC is calculated, and it's interpretation.

logistic roc auc

share|cite|improve this question

edited 4 hours ago

APK

asked 5 hours ago

APKAPK

1278

$endgroup$

add a comment | 

$begingroup$

I have a situation where I am fitting two simple logistic regression models - one model with the variable of interest included as the only predictor, and the other model with the log of the variable of interest included as the only predictor. Both models have the same Area Under the Curve, and I would like to know how to explain why this occurs. I am sure this is not due to chance, but rather has something to do with how AUC is calculated, and it's interpretation.

logistic roc auc

share|cite|improve this question

edited 4 hours ago

APK

asked 5 hours ago

APKAPK

1278

$endgroup$

share|cite|improve this question

edited 4 hours ago

APK

asked 5 hours ago

APKAPK

1278

share|cite|improve this question

edited 4 hours ago

APK

asked 5 hours ago

APKAPK

1278

asked 5 hours ago

APKAPK

1278

asked 5 hours ago

APKAPK

1278

1 Answer
1

active

oldest

votes

3

$begingroup$

It is because the AUC is invariant to monotonic changes of variable, of which the log-transform is a special case. The AUC is the probability that a randomly selected case has a higher risk than a control. While the raw difference in risk may not be the same for those two models, the case will still have a higher risk when calculated using either the log-transformed predictor or the untransformed predictor.

It should give us some pause and doubt about AUC that it makes no use whatsoever of the actual risk predicted by the model, but rather the ordering of groups according to a predicted risk (be it arbitrary or otherwise). The axes on a ROC are just sensitivity and 1-specificity.

share|cite|improve this answer

answered 4 hours ago

AdamOAdamO

33.8k263140

$endgroup$

• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  Thanks AdamO. Great explanation.
  $endgroup$
  – APK
  4 hours ago
  

  
  
  
  

add a comment | 

Your Answer

StackExchange.ifUsing("editor", function () {
return StackExchange.using("mathjaxEditing", function () {
StackExchange.MarkdownEditor.creationCallbacks.add(function (editor, postfix) {
StackExchange.mathjaxEditing.prepareWmdForMathJax(editor, postfix, [["$", "$"], ["\\(","\\)"]]);
});
});
}, "mathjax-editing");

StackExchange.ready(function() {
var channelOptions = {
tags: "".split(" "),
id: "65"
};
initTagRenderer("".split(" "), "".split(" "), channelOptions);

StackExchange.using("externalEditor", function() {
// Have to fire editor after snippets, if snippets enabled
if (StackExchange.settings.snippets.snippetsEnabled) {
StackExchange.using("snippets", function() {
createEditor();
});
}
else {
createEditor();
}
});

function createEditor() {
StackExchange.prepareEditor({
heartbeatType: 'answer',
autoActivateHeartbeat: false,
convertImagesToLinks: false,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: null,
bindNavPrevention: true,
postfix: "",
imageUploader: {
brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
allowUrls: true
},
onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
});


}
});

draft saved

draft discarded

Sign up or log in

StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});

Sign up using Google

Sign up using Facebook

Sign up using Email and Password

Post as a guest

Name

Email

Required, but never shown

StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstats.stackexchange.com%2fquestions%2f396245%2farea-under-the-curve-variable-and-log-transformed-variable%23new-answer', 'question_page');
}
);

Post as a guest

Name

Email

Required, but never shown

3

$begingroup$

It is because the AUC is invariant to monotonic changes of variable, of which the log-transform is a special case. The AUC is the probability that a randomly selected case has a higher risk than a control. While the raw difference in risk may not be the same for those two models, the case will still have a higher risk when calculated using either the log-transformed predictor or the untransformed predictor.

It should give us some pause and doubt about AUC that it makes no use whatsoever of the actual risk predicted by the model, but rather the ordering of groups according to a predicted risk (be it arbitrary or otherwise). The axes on a ROC are just sensitivity and 1-specificity.

share|cite|improve this answer

answered 4 hours ago

AdamOAdamO

33.8k263140

$endgroup$

• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  Thanks AdamO. Great explanation.
  $endgroup$
  – APK
  4 hours ago
  

  
  
  
  

add a comment | 

3

$begingroup$

It is because the AUC is invariant to monotonic changes of variable, of which the log-transform is a special case. The AUC is the probability that a randomly selected case has a higher risk than a control. While the raw difference in risk may not be the same for those two models, the case will still have a higher risk when calculated using either the log-transformed predictor or the untransformed predictor.

It should give us some pause and doubt about AUC that it makes no use whatsoever of the actual risk predicted by the model, but rather the ordering of groups according to a predicted risk (be it arbitrary or otherwise). The axes on a ROC are just sensitivity and 1-specificity.

share|cite|improve this answer

answered 4 hours ago

AdamOAdamO

33.8k263140

$endgroup$

• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  Thanks AdamO. Great explanation.
  $endgroup$
  – APK
  4 hours ago
  

  
  
  
  

add a comment | 

$begingroup$

It is because the AUC is invariant to monotonic changes of variable, of which the log-transform is a special case. The AUC is the probability that a randomly selected case has a higher risk than a control. While the raw difference in risk may not be the same for those two models, the case will still have a higher risk when calculated using either the log-transformed predictor or the untransformed predictor.

It should give us some pause and doubt about AUC that it makes no use whatsoever of the actual risk predicted by the model, but rather the ordering of groups according to a predicted risk (be it arbitrary or otherwise). The axes on a ROC are just sensitivity and 1-specificity.

share|cite|improve this answer

answered 4 hours ago

AdamOAdamO

33.8k263140

$endgroup$

share|cite|improve this answer

answered 4 hours ago

AdamOAdamO

33.8k263140

answered 4 hours ago

AdamOAdamO

33.8k263140

answered 4 hours ago

AdamOAdamO

33.8k263140