Fdtxjr

Will the concrete slab in a partially heated shed conduct a lot of heat to the unconditioned area?

Is it appropriate to ask a former professor to order a library book for me through ILL?

Is it a Cyclops number? "Nobody" knows!

Short story about cities being connected by a conveyor belt

What is better: yes / no radio, or simple checkbox?

How to install "rounded" brake pads

How can I portion out frozen cookie dough?

The (Easy) Road to Code

Too soon for a plot twist?

Giving a talk in my old university, how prominently should I tell students my salary?

Are small insurances worth it?

Paper published similar to PhD thesis

An Undercover Army

Interpretation of linear regression interaction term plot

How does learning spells work when leveling a multiclass character?

What do you call someone who likes to pick fights?

Was this cameo in Captain Marvel computer generated?

What is Tony Stark injecting into himself in Iron Man 3?

Should I apply for my boss's promotion?

I am the light that shines in the dark

Is this Paypal Github SDK reference really a dangerous site?

Should I file my taxes? No income, unemployed, but paid 2k in student loan interest

Book where society has been split into 2 with a wall down the middle where one side embraced high tech whereas other side were totally against tech

How to distinguish easily different soldier of ww2?

Relationship between the optimal solution and the empirical solution with finite samples in linear least square regression

distinguishing two random distributionsPolynomial Regression and MulticollinearityLeast Squares in a Matrix FormExistence of a vector in a given basis of a vector space with increasing coordinatesHow can I prove that this matrix is nonsingular?Does this operation exist? What's its name?Prove that $[x_1,x_2,…,x_n]=[y_1,y_2,…,y_k]$.Jacobian matrix vs. Transformation matrixDetermine independence of functions of r.v.'s and compute joint distributionChange of basis in two dimensions, use order of transformation matrices?

0

$begingroup$

Consider a linear system $y_i=Wx_i+v_i$, where $x_iin R^dtimes1 sim N(0,Sigma_x)$, $v_iin R^ptimes1 sim N(0,Sigma_v)$, $y_iin R^ptimes1$ and $Win R^ptimes d$.

Now we consider a linear estimator $hatx_i=beta_1y_i+beta_0$. We know that the optimal theoretical least square solution of is given by:

$$beta^ast_1=Sigma_xW^top(WSigma_xW^top+Sigma_v)^-1$$

$$beta^ast_0=0$$

On the other hand, suppose we have a set consisting of $N$ ovservations pairs $(x_1,y_1),(x_2,y_2),..,(x_N,y_N)$. We denote $Y_N=[y_1,y_2,...,y_N]$, $X_N=[x_1,x_2,...,x_N]$ and $V_N=[v_1,v_2,...,v_N]$. the abover system and the linear estimator can be written as

$$Y_N=WX_N+V_N$$

$$hatX_N=[beta_1, beta_0]beginbmatrixY_N\1endbmatrix$$.

Therefore, the least square solution is given by :

$$[beta^astast_1, beta^astast_0]=X_N[Y^top_N, 1^top]left(beginbmatrixY_N\1endbmatrix[Y^top_N, 1^top]right)^-1$$

where $beta^astast_1$ and $beta^astast_0$ can be considered as random variables.

We know that when $Nto infty$, $beta^astast_1to beta^ast_1$.

My question is: when N is finite, can we describe the relationship between $beta^astast_1$ and $beta^ast_1$, e.g., the pdf of $beta^astast_1-beta^ast_1$, for a given $N$?

linear-algebra random-variables

share|cite|improve this question

edited 15 hours ago

czk32611

asked 2 days ago

czk32611czk32611

11

New contributor

czk32611 is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

$endgroup$

add a comment | 

0

$begingroup$

Consider a linear system $y_i=Wx_i+v_i$, where $x_iin R^dtimes1 sim N(0,Sigma_x)$, $v_iin R^ptimes1 sim N(0,Sigma_v)$, $y_iin R^ptimes1$ and $Win R^ptimes d$.

Now we consider a linear estimator $hatx_i=beta_1y_i+beta_0$. We know that the optimal theoretical least square solution of is given by:

$$beta^ast_1=Sigma_xW^top(WSigma_xW^top+Sigma_v)^-1$$

$$beta^ast_0=0$$

On the other hand, suppose we have a set consisting of $N$ ovservations pairs $(x_1,y_1),(x_2,y_2),..,(x_N,y_N)$. We denote $Y_N=[y_1,y_2,...,y_N]$, $X_N=[x_1,x_2,...,x_N]$ and $V_N=[v_1,v_2,...,v_N]$. the abover system and the linear estimator can be written as

$$Y_N=WX_N+V_N$$

$$hatX_N=[beta_1, beta_0]beginbmatrixY_N\1endbmatrix$$.

Therefore, the least square solution is given by :

$$[beta^astast_1, beta^astast_0]=X_N[Y^top_N, 1^top]left(beginbmatrixY_N\1endbmatrix[Y^top_N, 1^top]right)^-1$$

where $beta^astast_1$ and $beta^astast_0$ can be considered as random variables.

We know that when $Nto infty$, $beta^astast_1to beta^ast_1$.

My question is: when N is finite, can we describe the relationship between $beta^astast_1$ and $beta^ast_1$, e.g., the pdf of $beta^astast_1-beta^ast_1$, for a given $N$?

linear-algebra random-variables

share|cite|improve this question

edited 15 hours ago

czk32611

asked 2 days ago

czk32611czk32611

11

New contributor

czk32611 is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

$endgroup$

add a comment | 

$begingroup$

Consider a linear system $y_i=Wx_i+v_i$, where $x_iin R^dtimes1 sim N(0,Sigma_x)$, $v_iin R^ptimes1 sim N(0,Sigma_v)$, $y_iin R^ptimes1$ and $Win R^ptimes d$.

Now we consider a linear estimator $hatx_i=beta_1y_i+beta_0$. We know that the optimal theoretical least square solution of is given by:

$$beta^ast_1=Sigma_xW^top(WSigma_xW^top+Sigma_v)^-1$$

$$beta^ast_0=0$$

On the other hand, suppose we have a set consisting of $N$ ovservations pairs $(x_1,y_1),(x_2,y_2),..,(x_N,y_N)$. We denote $Y_N=[y_1,y_2,...,y_N]$, $X_N=[x_1,x_2,...,x_N]$ and $V_N=[v_1,v_2,...,v_N]$. the abover system and the linear estimator can be written as

$$Y_N=WX_N+V_N$$

$$hatX_N=[beta_1, beta_0]beginbmatrixY_N\1endbmatrix$$.

Therefore, the least square solution is given by :

$$[beta^astast_1, beta^astast_0]=X_N[Y^top_N, 1^top]left(beginbmatrixY_N\1endbmatrix[Y^top_N, 1^top]right)^-1$$

where $beta^astast_1$ and $beta^astast_0$ can be considered as random variables.

We know that when $Nto infty$, $beta^astast_1to beta^ast_1$.

My question is: when N is finite, can we describe the relationship between $beta^astast_1$ and $beta^ast_1$, e.g., the pdf of $beta^astast_1-beta^ast_1$, for a given $N$?

linear-algebra random-variables

share|cite|improve this question

edited 15 hours ago

czk32611

asked 2 days ago

czk32611czk32611

11

New contributor

czk32611 is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

$endgroup$

share|cite|improve this question

edited 15 hours ago

czk32611

asked 2 days ago

czk32611czk32611

11

New contributor

czk32611 is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

share|cite|improve this question

edited 15 hours ago

czk32611

asked 2 days ago

czk32611czk32611

11

New contributor

czk32611 is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

asked 2 days ago

czk32611czk32611

11

New contributor

czk32611 is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

asked 2 days ago

czk32611czk32611

11