This tag is for questions about mean-square-error. In statistics, the mean squared error (MSE) of an estimator measures the average of the squares of the errors or deviations, that is, the difference between the estimator and what is estimated.

learn more… | top users | synonyms

3
votes
2answers
55 views

Is minimizing the squared errors optimal?

In least squares regression, we try to minimize the sum of the squares error terms. I was wondering if this would unfairly penalize a model for having terms that are too far away. For example, a term ...
2
votes
0answers
25 views

Impact of spurious regressors on out of sample prediction error

The true DGP is \begin{equation} y=\alpha_0 + \alpha_1 x_1 + \dots + \alpha_k x_k +\epsilon, \quad \epsilon\sim \mathcal{N}(0,1)\label{eq:1} \end{equation} but we instead estimate \begin{equation} y=...
0
votes
0answers
4 views

How to perform OLS on multivariate cointegration model?

So, I'm not too much of an expert in time series but here it goes ... Suppose there are time series X, Y, Z and the linear combination for some yet-unknown constants a,b,c of aX + bY + cZ forms a ...
0
votes
2answers
57 views

Find the variance and mean squared error of $T=\max(X_1, X_2, …, X_n)$

Let $X_1, X_2, ..., X_n$ be i.i.d. uniformly distributed on [$0, \theta$]. Consider the estimator $T=\max(X_1, X_2, ..., X_n)$ of $\theta$. Determine the variance and mean square error of $T$. My ...
0
votes
0answers
19 views

minimization problem: finding smallest deltas that satisfy equation.

After long derivations to find a better backpropagation algorithm for neural networks, I got this elegant optimization problem. Index $i=1..n$ given constants $c_i \in R, w_i \in R$ variables to ...
1
vote
0answers
10 views

Analysing error in Multiple Regression Analysis. [closed]

Hello everybody, I have the following multiple linear regression model LN(Number_of_person_in_househol)=1.514-0.13(Age_of_respondent)+0.486 (Married_PEOPLE)+0.25(Higestyearofschoolcompleted)+.097(...
1
vote
1answer
38 views

Error in average of $x^2$ from error in average of $x$?

Is there an easy way to obtain the error in $\langle{x^2}\rangle$ from $\langle{x}\rangle$ or are they independent? The values of x are from a molecular simulation application, I obtained a set of ...
0
votes
0answers
26 views

Number of measurements for least squares and relation to maximum likelihood

I have a simple overdetermined system of equations: $$ y = Xc + e $$ $y, e \in \mathbb{R}^n$, $c \in \mathbb{R}^m$, $X \in \mathbb{R}^{n \times m}$, $e \sim \mathcal{N}(o,\sigma^2)$, $n>>m$ ...
0
votes
1answer
44 views

Root Mean Square Error - How did he get this number?

So I am studying for a college final exam, and following a past exam paper at the moment. The lecturer has provided us with solutions to the previous years exam paper, not very clear in some cases ...
0
votes
0answers
16 views

PCA: MSE of projecting a set of points to a subspace

Let $\{x_1,\dots,x_n\}$ be a dataset of n vectors in $\mathbb{R}^d$ s.t. $\sum_{i=1}^n x_i = 0$. Let $p_1, \dots, p_k$ be a set of k orthonormal unit vectors and V the subspace that they span. Given ...
1
vote
1answer
32 views

how to find mininimum $f(x)$ using $\int_{-\infty}^{\infty} f(x)g(x)dx$?

I would like to know the $f(x)$ which minimizes the $\displaystyle\int_{-\infty}^{\infty} f(x)g(x)\,dx$. Actually, this question start from the MMSE (Minimize Mean square error) $$E[(X-g(Y))^2]=\...
0
votes
1answer
20 views

Derivation of MMSE from an estimator of two Gaussians

Suppose $X$ and $N$ are independent Gaussian with different variance but N has zero mean. Now $Y = X+N$. I am trying to find out the minimum mean square error estimator for $X$ given $Y$. I set the ...
0
votes
0answers
41 views

Minimise Mean square error(MMSE) proof procedure

I am awkard to understand the basic things so I have suffered from the procedure of proving the minimize the mean square error. the mean square error is $$ E[(X-g(Y))^{2}]=\int_{-\infty }^{\infty}...
0
votes
0answers
22 views

Absolute and relative errors

I am trying to compare two regression models, say $A$ and $B$ and calculate the absolute error measure (MAE, RMSE) and relative ones. But it turns out that both the absolute measures for $A$ are ...
0
votes
1answer
18 views

Is $Φ^T$ a linear operator which transforms simultaneous equations such that we obtain LMS solution?

The below explanation is long winded, if you already know about using pseudo inverse to find the best fit solution to a set of simultaneous equations please go down to the tl;dr The Problem Given a ...
0
votes
0answers
26 views

orthogonality condition in Minimum MSE linear estimator

I have questions about orthogonality condition in minimum MSE linear estimator. When estimating $X$ by a linear function $g(Y)= aY+b :$ $min_{\text{a,b}} E[(X-aY-b)^2].$ $b^*=E[X-aY]=E[X]-aE[Y]$ $...
0
votes
0answers
13 views

error on the median

I have a set of values ${x_i}, i=1, \dots ,N$ of which I calculate the median M. I was wondering how I could calculate the error on this estimation. On the net I found that it can be calculated as $1....
0
votes
0answers
21 views

error calculation when the error is not constant

I have to calculate the error on the following quantity: $$f(\epsilon^M,\epsilon^S)= \sqrt{ \frac{1}{N}\sum_{i=1}^N (\log{\epsilon_i^M} - \log{\epsilon_i^S})^2 } $$ Usually I would use this standard ...
0
votes
0answers
16 views

Minimizing error of estimation in a differential equation system

I have a system of equations which describe dynamic nature of a system. There is no closed form solution for this system. System of equations is as follow: $$I_c=I_1 + I_2 + I_3$$ $$R_3 = \frac{V_3}{...
0
votes
0answers
43 views

How to solve this vector MSE equation?

Let's assume an error at time $k$ is: $e_k = \mathbf{c}^T \mathbf{r}_k - a_{k-d} - \mathbf{b}^T \mathbf{a}_k$, where $\mathbf{c} = [c_0, ..., c_{N_c-1}]^T$, $\mathbf{r}_k = [r_0, ..., r_{N_c-1}]^T$, ...
1
vote
1answer
97 views

On normalized error measures

I have function values $f_1,\ldots,f_n$ that are approximated by data $y_1,\ldots,y_n$. I am looking for a measure that describes the error in the data $y_1,\ldots,y_n$ and I want the measure to take ...
0
votes
0answers
12 views

Is the weighted mean of residuals over another variable equal to $0$?

I understand how residual errors must sum to zero around in a random sample (e.g. $y$-axis price of diamond predicted by x-axis weight of diamond). However, why must the weighted sum of residuals with ...
0
votes
0answers
17 views

What is the best formula to calculate percentage area of low-volume data (i.e. values close to 0)

I initially used the MAPE to calculate the percentage error between the actual data, and the data I got based on a model (forecast). However, near the values close to 0, the graph/percentage error got ...
0
votes
1answer
35 views

A way to calculate the error of a model?

I am currently making a model for a set of raw data of sea levels from the NOAA data base. On the site, the sea level is recorded every 6 minutes. Because I wouldn't have time to copy data every 6 ...
0
votes
0answers
25 views

Finding estimator with the smallest MSE

There is an estimator $\hat{\theta}$ of $\theta$ which has expectated value $\frac{3n}{3n+1} \theta$ and $E(\hat{\theta}^2)=\frac{3n}{3n+2} \theta^2$. Now I need to pick another estimator $X$, such ...
0
votes
1answer
75 views

Negative Mean Square Error

For simple random sampling, I have calculated somemean square errors for ratio-type estimators such as Isaki estimator, and Prasad Singh estimator. But, Mean Square Errors i obtained are negative. ...
0
votes
1answer
124 views

How to minimize the minimum mean square error of this difference

I am trying to minimize the mean square error. More precisely, I am trying to minimize the following optimization problem $$\arg \min _{\bf{w_1},\bf{w_2}}\mathbb{E} \,\,[\|{\bf s} - {\bf Wy}\|^2 ]$$ $...
4
votes
1answer
1k views

Matlab code for finding the curvature of a curve using given data points

I have data points $(x,y)$ for a plane curve, and I would like to find its curvature. Wwhile I was googling to check how could I start, I found this matlab code: ...
0
votes
0answers
18 views

Finding the closest vector to an observation

I have a collection of vectors (a codebook in hand) which are presented within a matrix $A$ $$ A = [ a (\theta_1), \, a (\theta_2), \, a (\theta_3), \, a (\theta_4), \,\cdots]$$ We have obtained ...
1
vote
1answer
172 views

Expected mean squared error and MSR

In a small-scale regression study, five observations on $Y$ were obtained corresponding to $X = 1,4,10, 11$, and $14$. Assume that $\sigma=0.6,B_0=5,B_1=3$ a. What are the expected values off ...
1
vote
0answers
40 views

Can the error term variance ever be estimated without fitting a regression line in a basic linear regression model?

Can the error term variance ever be estimated without fitting a regression line in a basic linear regression model? I don't understand how this would be possible and why. Because wouldn't you always ...
1
vote
0answers
124 views

Mean squared error consistency of estimator

Given is the following distribution: $f_\theta(x)=\frac{1}{\theta}$ if $0<x\leq\theta$, and $0$ otherwise; $\theta<0$. I need to show that the maximum likelihood estimator of $\theta$, $\hat{\...
0
votes
0answers
18 views

MMSE detector for elliptical distribution.

Suppose we have $Y=HX+W$ where dimension of $Y$ is $N$ and $W$ is elliptically distributed $H$ is also elliptically distributed $X$ is uniformly distributed. We want to estimate $\hat{X}$ using MMSE ...
0
votes
2answers
53 views

Estimation, bias, and mean square error

Let $X$ be a continuous random variable with pdf $f(x) =\frac{1}{2}(1+ \theta x)$, for $-1 < x < 1$, and $-1 < \theta < 1$ (a) Show that $E(X) = \frac{\theta}{3}$. (b) Given a random ...
0
votes
0answers
18 views

What are some error measures used for fitting PMFs?

I have a given PMF, $f_X(x)$, and am trying to create a fitted PMF, $g_X(x)$, that comes "as close as possible" to it, but am not sure what to use as a measure of fit. Simply minimizing standard error ...
-1
votes
2answers
177 views

What is the Difference between Variance and MSE

I know that Variance measures the dispersion of an estimator around its mean i.e. $\sigma^2=E[X - \mu]^2$ or Second central moment (moment about the mean) But I'...
0
votes
1answer
58 views

Matrix of vector-by-vector sum-squared deviations of two matrices of column vectors

Context I'm working on a Python program in which I will calculate some number $r$ of matrices $\mathbf{A}^i$ with identical dimensions $m\times n$. For this application, each matrix is probably best ...
4
votes
1answer
119 views

Properties Least Mean Fourth Error

I am interested in whether a quantity \begin{align*} E[(X-E[X|Y])^4] \end{align*} has been studied in the literature before. I am not even sure if "least mean fourth error" is a correct name, since $...
0
votes
1answer
50 views

Least-squares solution to a linear matrix equation

Let $\\A$ be a matrix of size $\\(m, n)$, $\\b$ a column vector of size $\\m$, $\\x$ a column vector of size $\\n$ and $\\a$ a real number. If $\begin{bmatrix} x \\ a \end{bmatrix}$ is the least-...
1
vote
1answer
280 views

comparing MSE of estimations of binomial random variables

$X$ is a binomial random variable defined over 12 Bernoulli trials with a success probability of $p$ in each (i.e. $X\sim\operatorname{Bin}(12,p)$. Consider $\hat p=\frac X{10}$ Determine the range ...
0
votes
1answer
49 views

mean square error comparison

Do you have any idea about how i can solve the question below? $X_1$ and $X_2$ are random variables that satisfy $E[X_1]=E[X_2]=\mu$ and $Var[X_1]=Var[X_2]=1$. Show that when $|\mu - 10| \leq \frac{\...
0
votes
1answer
159 views

Variance with minimal MSE in normal distribution

Given $X_1,...,X_n$ ~ i.i.d. $N(\mu, \sigma^2)$ where the mean is unknown, let the estimator for $\sigma^2$ be $\hat{e} = p\sum_{i=1}^n(X_i-\overline{X})^2$ How do I choose $p$ so that this estimator ...
2
votes
0answers
90 views

How to fit normal cumulative distribution functions

For a normal distribution $N(\mu,\sigma^2)$, we know its cumulative distribution function is $F(x)=\Phi(\frac{x-\mu}{\sigma})$ where $\Phi(x)$ is $cdf$ for standard normal distribution which means $$ ...
0
votes
2answers
153 views

How to find the bias, variance and MSE of $\hat p$?

If $X_1,\dots,X_n$ are iid $\mathrm{Binomial}(3,p)$, then the maximum likelihood estimator of $p$ is $$\hat p = \frac{1}{n}\sum_i X_i$$ Find the bias, variance and MSE of $\hat p$? We are asked to ...
1
vote
1answer
41 views

Standard error of RMSE?

If I want to calculate the RMSE between an estimated value $\hat{x}$ and its reference value $x_{\textrm{ref}}$, let \begin{equation} y_i = \hat{x}_i-x_{i,\textrm{ref}} \end{equation} Since \begin{...
2
votes
0answers
32 views

minimizing mean square error with type 1 and 2 error weights

Suppose we have a random variable $X$ with a pmf that puts strictly positive probability only on integer values $0,1,2,\dots,n$. The objective is to choose a $z\in\mathbb{Z}$ that minimizes $$c\sum_{...
0
votes
1answer
52 views

How to find the minimal MSE?

I'm confused as in how to find $⍴$ in c) and why $σ^2$ gives a smaller MSE than $s^2$ I know $MSE(θ) = E(θ - θ_0)^2 = Var(θ) + Bias(θ)^2 $ and that $ Bias(θ) = E(θ) - θ_0$ But I don't get what θ is ...
0
votes
1answer
120 views

linear regression, expectation and mean squared error

Let us assume that data is generated according to a true model $$y_i = \beta_{true}x_i + \epsilon_i$$ for $i = 1, ..., n$ Assume that $x_i$ are fixed, and $\epsilon_i$~ N(0, $\sigma^2$) independently....
0
votes
0answers
204 views

Finding a relative error measure on a data set proportional to another

I have a set of exact data points $\mathcal{X}=\{X_i\}$ and another approximate one $\mathcal{Y}=\{Y_i\}$ where there is a correspondence between $X_i$ and $Y_i$ for all $i$. If $\mathcal{Y}$ was ...
0
votes
1answer
145 views

Finding the best linear predictor

How do I find the best linear predictor of $X_{n+1}$ in terms of $X_{n-1}, X_n$, if $X_t$ is the MA(1) model $X_t = Z_t + \theta Z_{t−1}$.