Crthuky

Why Shazam when there is already Superman?

What is going on with gets(stdin) on the site coderbyte?

Review your own paper in Mathematics

How could a planet have erratic days?

How to get directions in deep space?

A variation to the phrase "hanging over my shoulders"

How can ping know if my host is down

Will number of steps recorded on FitBit/any fitness tracker add up distance in PokemonGo?

Why is the Sun approximated as a black body at ~ 5800 K?

Has the laser at Magurele, Romania reached a tenth of the Sun's power?

What is the English pronunciation of "pain au chocolat"?

How to make money from a browser who sees 5 seconds into the future of any web page?

I found an audio circuit and I built it just fine, but I find it a bit too quiet. How do I amplify the output so that it is a bit louder?

Are Captain Marvel's powers affected by Thanos breaking the Tesseract and claiming the stone?

Is there any evidence that Cleopatra and Caesarion considered fleeing to India to escape the Romans?

Why do ¬, ∀ and ∃ have the same precedence?

How to explain what's wrong with this application of the chain rule?

Delete multiple columns using awk or sed

Is my low blitz game drawing rate at www.chess.com an indicator that I am weak in chess?

Why can't the Brexit deadlock in the UK parliament be solved with a plurality vote?

Is this toilet slogan correct usage of the English language?

Why does Carol not get rid of the Kree symbol on her suit when she changes its colours?

Giving feedback to someone without sounding prejudiced

Is it necessary to use pronouns with the verb "essere"?

Why does this expression simplify as such?

General linear hypothesis test statistic: equivalence of two expressionsSlope Derivation for the variance of a least square problem via Matrix notationCovariance of OLS estimator and residual = 0. Where is the mistake?A doubt on SUR modelWhy trace of $I−X(X′X)^-1X′$ is $n-p$ in least square regression when the parameter vector $beta$ is of p dimensions?Getting the posterior for Bayesian linear regression with a flat priorDistribution of coefficients in linear regressionFitted values and residuals: are they random vectors?Proving that Covariance of residuals and errors is zeroWhat is the relationship of long and short regression when we have an intercept?

3

$begingroup$

I'm reading through my professor's lecture notes on the multiple linear regression model and at one point he writes the following:

$$E[(b-beta)e']=E[(X'X)^-1epsilonepsilon'M_[X]]. $$

In the above equation, $b$, $beta$, $e$, and $epsilon$ are all vectors, $X$ is a regressor matrix and $M$ is the residual maker matrix. In general, I have no idea why these expressions are equivalent, and I'm particularly confused at how the $e$ vector disappears and the $epsilon$ vector appears.

regression multiple-regression linear-model residuals

share|cite|improve this question

edited 3 hours ago

Benjamin Christoffersen

1,264519

asked 4 hours ago

DavidDavid

24311

$endgroup$

add a comment | 

3

$begingroup$

I'm reading through my professor's lecture notes on the multiple linear regression model and at one point he writes the following:

$$E[(b-beta)e']=E[(X'X)^-1epsilonepsilon'M_[X]]. $$

In the above equation, $b$, $beta$, $e$, and $epsilon$ are all vectors, $X$ is a regressor matrix and $M$ is the residual maker matrix. In general, I have no idea why these expressions are equivalent, and I'm particularly confused at how the $e$ vector disappears and the $epsilon$ vector appears.

regression multiple-regression linear-model residuals

share|cite|improve this question

edited 3 hours ago

Benjamin Christoffersen

1,264519

asked 4 hours ago

DavidDavid

24311

$endgroup$

add a comment | 

$begingroup$

I'm reading through my professor's lecture notes on the multiple linear regression model and at one point he writes the following:

$$E[(b-beta)e']=E[(X'X)^-1epsilonepsilon'M_[X]]. $$

In the above equation, $b$, $beta$, $e$, and $epsilon$ are all vectors, $X$ is a regressor matrix and $M$ is the residual maker matrix. In general, I have no idea why these expressions are equivalent, and I'm particularly confused at how the $e$ vector disappears and the $epsilon$ vector appears.

regression multiple-regression linear-model residuals

share|cite|improve this question

edited 3 hours ago

Benjamin Christoffersen

1,264519

asked 4 hours ago

DavidDavid

24311

$endgroup$

share|cite|improve this question

edited 3 hours ago

Benjamin Christoffersen

1,264519

asked 4 hours ago

DavidDavid

24311

share|cite|improve this question

edited 3 hours ago

Benjamin Christoffersen

1,264519

asked 4 hours ago

DavidDavid

24311

edited 3 hours ago

Benjamin Christoffersen

1,264519

edited 3 hours ago

Benjamin Christoffersen

1,264519

asked 4 hours ago

DavidDavid

24311

asked 4 hours ago

DavidDavid

24311

2 Answers
2

active

oldest

votes

3

$begingroup$

I am assuming $b$ is the OLS estimate of $beta$ and $e$ is the corresponding estimate of $epsilon$. Also I believe you have a typo above in your expression, as there should be $X'$ in front of $epsilon epsilon'$ and behind $(X'X)^-1$.

Start with the definition of $b$:
$$b=(X'X)^-1X'Y.$$
Replacing $Y$ with $Xbeta+epsilon$ in our expression above, we get
$$b=(X'X)^-1X'(Xbeta+epsilon)=beta+(X'X)^-1X'epsilon.$$
It follows that
$$b-beta = (X'X)^-1X'epsilon$$

Now turn to the defintion of $e$:
$$e=Y-hatY=Y-Xb=Y-X(X'X)^-1X'Y.$$

Notice $X(X'X)^-1X'$ is the projection matrix for $X$, which we will denote with $P_[X]$.
Replacing this in our expression for $e,$ we get
$$e=(I-P_[X])Y=M_[X]Y.$$
Replacing $Y$ in the expression above with $Xbeta+epsilon$, we get
$$e=M_[X](Xbeta+epsilon)=M_[X]epsilon,$$
since $M_[X]X$ is a matrix of zeros.

Post-multiplying $b-beta$ with $e'$, we get
$$(b-beta)e'=(X'X)^-1X'epsilon epsilon' M_[X],$$
since $e'=epsilon'M_[X].$

share|cite|improve this answer

answered 2 hours ago

dlnBdlnB

81011

$endgroup$

• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  Ah. The key thing I was missing was what you wrote in the last line.
  $endgroup$
  – David
  2 hours ago
  

  
  
  
  

add a comment | 

3

$begingroup$

Assuming that the coefficient estimator $b$ is calculated by OLS estimation, you have:

$$beginequation beginaligned
b-beta
&= (X'X)^-1 X'y - beta \[6pt]
&= (X'X)^-1 X'(X beta + epsilon)- beta \[6pt]
&= (X'X)^-1 (X'X) beta + (X'X)^-1 X' epsilon - beta \[6pt]
&= beta + (X'X)^-1 X' epsilon - beta \[6pt]
&= (X'X)^-1 X' epsilon. \[6pt]
endaligned endequation$$

Presumably $e$ is the residual vector (different to the error vector $epsilon$) so we have $e = M_[X] Y = M_[X] epsilon$. Substituting this vector gives:

$$beginequation beginaligned
(b-beta) e'
&= (X'X)^-1 X' epsilon (M_[X] epsilon)' \[6pt]
&= (X'X)^-1 X' epsilon epsilon' M_[X]' \[6pt]
&= (X'X)^-1 X' epsilon epsilon' M_[X]. \[6pt]
endaligned endequation$$

(The last step follows from the fact that $M_[X]$ is a symmetric matrix.) So the expression given by your professor is missing the $X'$ term.

share|cite|improve this answer

answered 2 hours ago

BenBen

26.8k230124

$endgroup$

• 
  
  
  

  
  2
  

  
  
  
  
  
  

  
  $begingroup$
  Nice, I think we both must have been typing our answers at the same time. I'm glad you also found the mistake.
  $endgroup$
  – dlnB
  2 hours ago
  

  
  
  
  


• 
  
  
  

  
  1
  

  
  
  
  
  
  

  
  $begingroup$
  @dlnb: Jinx! Buy me a coke!
  $endgroup$
  – Ben
  2 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');

var $window = $(window),
onScroll = function(e)
var $elem = $('.new-login-left'),
docViewTop = $window.scrollTop(),
docViewBottom = docViewTop + $window.height(),
elemTop = $elem.offset().top,
elemBottom = elemTop + $elem.height();
if ((docViewTop elemBottom))
StackExchange.using('gps', function() StackExchange.gps.track('embedded_signup_form.view', location: 'question_page' ); );
$window.unbind('scroll', onScroll);

;
$window.on('scroll', onScroll);

);

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%2f398797%2fwhy-does-this-expression-simplify-as-such%23new-answer', 'question_page');

);

Post as a guest

Name

Email

Required, but never shown

3

$begingroup$

I am assuming $b$ is the OLS estimate of $beta$ and $e$ is the corresponding estimate of $epsilon$. Also I believe you have a typo above in your expression, as there should be $X'$ in front of $epsilon epsilon'$ and behind $(X'X)^-1$.

Start with the definition of $b$:
$$b=(X'X)^-1X'Y.$$
Replacing $Y$ with $Xbeta+epsilon$ in our expression above, we get
$$b=(X'X)^-1X'(Xbeta+epsilon)=beta+(X'X)^-1X'epsilon.$$
It follows that
$$b-beta = (X'X)^-1X'epsilon$$

Now turn to the defintion of $e$:
$$e=Y-hatY=Y-Xb=Y-X(X'X)^-1X'Y.$$

Notice $X(X'X)^-1X'$ is the projection matrix for $X$, which we will denote with $P_[X]$.
Replacing this in our expression for $e,$ we get
$$e=(I-P_[X])Y=M_[X]Y.$$
Replacing $Y$ in the expression above with $Xbeta+epsilon$, we get
$$e=M_[X](Xbeta+epsilon)=M_[X]epsilon,$$
since $M_[X]X$ is a matrix of zeros.

Post-multiplying $b-beta$ with $e'$, we get
$$(b-beta)e'=(X'X)^-1X'epsilon epsilon' M_[X],$$
since $e'=epsilon'M_[X].$

share|cite|improve this answer

answered 2 hours ago

dlnBdlnB

81011

$endgroup$

• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  Ah. The key thing I was missing was what you wrote in the last line.
  $endgroup$
  – David
  2 hours ago
  

  
  
  
  

add a comment | 

3

$begingroup$

I am assuming $b$ is the OLS estimate of $beta$ and $e$ is the corresponding estimate of $epsilon$. Also I believe you have a typo above in your expression, as there should be $X'$ in front of $epsilon epsilon'$ and behind $(X'X)^-1$.

Start with the definition of $b$:
$$b=(X'X)^-1X'Y.$$
Replacing $Y$ with $Xbeta+epsilon$ in our expression above, we get
$$b=(X'X)^-1X'(Xbeta+epsilon)=beta+(X'X)^-1X'epsilon.$$
It follows that
$$b-beta = (X'X)^-1X'epsilon$$

Now turn to the defintion of $e$:
$$e=Y-hatY=Y-Xb=Y-X(X'X)^-1X'Y.$$

Notice $X(X'X)^-1X'$ is the projection matrix for $X$, which we will denote with $P_[X]$.
Replacing this in our expression for $e,$ we get
$$e=(I-P_[X])Y=M_[X]Y.$$
Replacing $Y$ in the expression above with $Xbeta+epsilon$, we get
$$e=M_[X](Xbeta+epsilon)=M_[X]epsilon,$$
since $M_[X]X$ is a matrix of zeros.

Post-multiplying $b-beta$ with $e'$, we get
$$(b-beta)e'=(X'X)^-1X'epsilon epsilon' M_[X],$$
since $e'=epsilon'M_[X].$

share|cite|improve this answer

answered 2 hours ago

dlnBdlnB

81011

$endgroup$

• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  Ah. The key thing I was missing was what you wrote in the last line.
  $endgroup$
  – David
  2 hours ago
  

  
  
  
  

add a comment | 

$begingroup$

I am assuming $b$ is the OLS estimate of $beta$ and $e$ is the corresponding estimate of $epsilon$. Also I believe you have a typo above in your expression, as there should be $X'$ in front of $epsilon epsilon'$ and behind $(X'X)^-1$.

Start with the definition of $b$:
$$b=(X'X)^-1X'Y.$$
Replacing $Y$ with $Xbeta+epsilon$ in our expression above, we get
$$b=(X'X)^-1X'(Xbeta+epsilon)=beta+(X'X)^-1X'epsilon.$$
It follows that
$$b-beta = (X'X)^-1X'epsilon$$

Now turn to the defintion of $e$:
$$e=Y-hatY=Y-Xb=Y-X(X'X)^-1X'Y.$$

Notice $X(X'X)^-1X'$ is the projection matrix for $X$, which we will denote with $P_[X]$.
Replacing this in our expression for $e,$ we get
$$e=(I-P_[X])Y=M_[X]Y.$$
Replacing $Y$ in the expression above with $Xbeta+epsilon$, we get
$$e=M_[X](Xbeta+epsilon)=M_[X]epsilon,$$
since $M_[X]X$ is a matrix of zeros.

Post-multiplying $b-beta$ with $e'$, we get
$$(b-beta)e'=(X'X)^-1X'epsilon epsilon' M_[X],$$
since $e'=epsilon'M_[X].$

share|cite|improve this answer

answered 2 hours ago

dlnBdlnB

81011

$endgroup$

share|cite|improve this answer

answered 2 hours ago

dlnBdlnB

81011

answered 2 hours ago

dlnBdlnB

81011

answered 2 hours ago

dlnBdlnB

81011

3

$begingroup$

Assuming that the coefficient estimator $b$ is calculated by OLS estimation, you have:

$$beginequation beginaligned
b-beta
&= (X'X)^-1 X'y - beta \[6pt]
&= (X'X)^-1 X'(X beta + epsilon)- beta \[6pt]
&= (X'X)^-1 (X'X) beta + (X'X)^-1 X' epsilon - beta \[6pt]
&= beta + (X'X)^-1 X' epsilon - beta \[6pt]
&= (X'X)^-1 X' epsilon. \[6pt]
endaligned endequation$$

Presumably $e$ is the residual vector (different to the error vector $epsilon$) so we have $e = M_[X] Y = M_[X] epsilon$. Substituting this vector gives:

$$beginequation beginaligned
(b-beta) e'
&= (X'X)^-1 X' epsilon (M_[X] epsilon)' \[6pt]
&= (X'X)^-1 X' epsilon epsilon' M_[X]' \[6pt]
&= (X'X)^-1 X' epsilon epsilon' M_[X]. \[6pt]
endaligned endequation$$

(The last step follows from the fact that $M_[X]$ is a symmetric matrix.) So the expression given by your professor is missing the $X'$ term.

share|cite|improve this answer

answered 2 hours ago

BenBen

26.8k230124

$endgroup$

• 
  
  
  

  
  2
  

  
  
  
  
  
  

  
  $begingroup$
  Nice, I think we both must have been typing our answers at the same time. I'm glad you also found the mistake.
  $endgroup$
  – dlnB
  2 hours ago
  

  
  
  
  


• 
  
  
  

  
  1
  

  
  
  
  
  
  

  
  $begingroup$
  @dlnb: Jinx! Buy me a coke!
  $endgroup$
  – Ben
  2 hours ago
  

  
  
  
  

add a comment | 

3

$begingroup$

Assuming that the coefficient estimator $b$ is calculated by OLS estimation, you have:

$$beginequation beginaligned
b-beta
&= (X'X)^-1 X'y - beta \[6pt]
&= (X'X)^-1 X'(X beta + epsilon)- beta \[6pt]
&= (X'X)^-1 (X'X) beta + (X'X)^-1 X' epsilon - beta \[6pt]
&= beta + (X'X)^-1 X' epsilon - beta \[6pt]
&= (X'X)^-1 X' epsilon. \[6pt]
endaligned endequation$$

Presumably $e$ is the residual vector (different to the error vector $epsilon$) so we have $e = M_[X] Y = M_[X] epsilon$. Substituting this vector gives:

$$beginequation beginaligned
(b-beta) e'
&= (X'X)^-1 X' epsilon (M_[X] epsilon)' \[6pt]
&= (X'X)^-1 X' epsilon epsilon' M_[X]' \[6pt]
&= (X'X)^-1 X' epsilon epsilon' M_[X]. \[6pt]
endaligned endequation$$

(The last step follows from the fact that $M_[X]$ is a symmetric matrix.) So the expression given by your professor is missing the $X'$ term.

share|cite|improve this answer

answered 2 hours ago

BenBen

26.8k230124

$endgroup$

• 
  
  
  

  
  2
  

  
  
  
  
  
  

  
  $begingroup$
  Nice, I think we both must have been typing our answers at the same time. I'm glad you also found the mistake.
  $endgroup$
  – dlnB
  2 hours ago
  

  
  
  
  


• 
  
  
  

  
  1
  

  
  
  
  
  
  

  
  $begingroup$
  @dlnb: Jinx! Buy me a coke!
  $endgroup$
  – Ben
  2 hours ago
  

  
  
  
  

add a comment | 

$begingroup$

Assuming that the coefficient estimator $b$ is calculated by OLS estimation, you have:

$$beginequation beginaligned
b-beta
&= (X'X)^-1 X'y - beta \[6pt]
&= (X'X)^-1 X'(X beta + epsilon)- beta \[6pt]
&= (X'X)^-1 (X'X) beta + (X'X)^-1 X' epsilon - beta \[6pt]
&= beta + (X'X)^-1 X' epsilon - beta \[6pt]
&= (X'X)^-1 X' epsilon. \[6pt]
endaligned endequation$$

Presumably $e$ is the residual vector (different to the error vector $epsilon$) so we have $e = M_[X] Y = M_[X] epsilon$. Substituting this vector gives:

$$beginequation beginaligned
(b-beta) e'
&= (X'X)^-1 X' epsilon (M_[X] epsilon)' \[6pt]
&= (X'X)^-1 X' epsilon epsilon' M_[X]' \[6pt]
&= (X'X)^-1 X' epsilon epsilon' M_[X]. \[6pt]
endaligned endequation$$

(The last step follows from the fact that $M_[X]$ is a symmetric matrix.) So the expression given by your professor is missing the $X'$ term.

share|cite|improve this answer

answered 2 hours ago

BenBen

26.8k230124

$endgroup$

share|cite|improve this answer

answered 2 hours ago

BenBen

26.8k230124

answered 2 hours ago

BenBen

26.8k230124

answered 2 hours ago

BenBen

26.8k230124