Questions on (linear or nonlinear) regression, the fitting of functions that best approximate empirical data.

learn more… | top users | synonyms

0
votes
1answer
17 views

standard error for the parameters of a linear regression model

Given a linear model $\mathbf{y} = \beta \mathbf{X} + \epsilon$, it is well known that the estimate for $\beta$ that gives the minimum residual sum of squares (RSS) is given by $\hat{\beta} = ...
0
votes
1answer
15 views

How to report significant digits in coefficient of determination?

Say that I fit some data with some model, for instance a linear function $y = mx+b$. What is the proper way to report the fitted coefficients and the goodness of fit? Specifically, if I do the fit in ...
1
vote
1answer
16 views

Interpreting linear regression.

I'm not very versed in statistics or anything so I'm in the dark for this. For my biology (Grade 12) class I've been looking at journals and papers and I've seen a lot of graphs expressed in the form ...
1
vote
0answers
33 views

Odd Ratio and Logistic Regression

Windy and Play Tennis = 9 Windy and Not Playing Tennis = 8 Not Windy and Play Tennis = 14 Not Windy and Not Playing Tennis = 8 I performed logistic regression in Weka and got odd ratio as 0.3448 for ...
0
votes
0answers
27 views

Chi Square Formula and Degrees of Freedom Questions

I have a population sample with 200 points of data and 3 degrees of freedom so am I supposed to do a chi square formula with all 200 points of data? I believe that is what I'm supposed to do but I'm ...
2
votes
1answer
43 views

Is it possible to have two lines of best fit?

Could you rig a data set to have two lines of equally good (and best) fit? Or is it impossible?
1
vote
0answers
28 views

Increase the probability of correct prediction using multiple regression

First off let me begin by saying that I'm brand new to statistics and I would appreciate it if you could dumb down any answers for my problem. I am trying to create a general prediction of how much a ...
0
votes
0answers
11 views

How do I get the proper p-value of a time series average of regression coefficients?

I have run cross-sectional regression on the returns of 50 companies on 16 regressors, for 128 days. The regression output looks something like this: ...
0
votes
2answers
30 views

How to find more than two coefficient for single variable nonlinear equation?

I don't have good knowledge on mathematics, but now I faced one problem with maths. That is, I have a data set which contains only one independent and one dependent variable. Now I have a equation ...
0
votes
0answers
21 views

Logistic regression - How to interpret a graph?

Can somebody help me to understand these two graphs. I don't know how to interpret them correctly. Thanks!
1
vote
0answers
34 views

Linear regression of time series data - moving linear regression

Situation A suitable analogy for my real-world problem would be a shop - customers arrive, spend a random amount of time in the shop and leave. The arrival behaviour of customers follows a Poisson ...
0
votes
0answers
10 views

Difference Between Three Similar Error Reducing Algorithms

I found a Least Square Error Recognition algorithm that finds the least mean square error from a 2-d matrix element by element. Logistic regression from this site, on the other hand, seeks to ...
0
votes
0answers
20 views

L1 regression statistics

Consider fitting the below dataset using L1 regression: x: 8.3 8.3 12.1 12.1 17.0 17.0 17.0 24.3 24.3 24.3 33.6 y: 224 312 362 521 640 539 728 945 738 759 663 Why do the regression estimates ...
0
votes
0answers
213 views

How do I find Sxx in a Simple linear regression model?

In a Simple linear regression model, I have only Sxy and Syy data with me. How shall I derive Sxx, linking Sxy and Syy based on first principles? I know the formulas separately. I want to find Sxx, ...
0
votes
0answers
25 views

Classical Regression Model: Combining linearity and strict exogeneity

I am studying the Classical Regression Model for random samples. Hence consider the random sample $(y_i,\mathbf{x_i})$ Where: ...
0
votes
0answers
15 views

How to derive F statistic for general linear hypothesis

I want to derive the F statistic for general linear hypothesis $H_0$ : T$\beta$ = c vs $H_1$ : T$\beta$ $\not =$ c where T is $p * q$ matrix with rank q I have tried to express $SS_{Res} (RM)$ - ...
0
votes
1answer
26 views

how to apply weighting factor to linear regression

Say if I have two sets of data, x and y. And I am required to apply a weighting factor,1/x, to the regression line. Does that mean I should plot 1/y versus 1/x and then get the regression? Could ...
0
votes
0answers
23 views

Difference in coefficient estimates

I have simple regression $y_i=\beta_0+\beta_1x+\epsilon$. Then I have estimates $\hat{\beta_0},\hat{\beta_1}$ computed from n observation and estimates $\beta_0',\beta_1'$ computed from n+1 ...
0
votes
1answer
20 views

Questions about Multi linear regression model.

I have two questions about multi linear regression model. First question. Suppose 2 independent samples Sample1 : $y_1$, ... $y_{n_1}$ and $x_1$, ..., $x_{n_1}$ Sample2 : $y_{n_1 +1}$, ... $y_{n_1 ...
0
votes
0answers
11 views

relation within Gauss-Newton method for minimization

If we study model fit on a nonlinear regression model $Y_i=f(z_i,\theta)+\epsilon_i$, $i=1,...,n$, and in the Gauss-Newton method, the update on the parameter $\theta$ from step $t$ to $t+1$ is to ...
1
vote
1answer
84 views

Using the observation vector $ \vec{y}$ instead of the centered observation vector $ \vec{y_{d}} $ doesn't change the projection $\vec{\hat y}$

I'm wondering why the two statements below are equal regardless of using $\vec{y}$ in deviation form/mean-deviaton/centered form or not. In other words, why isn't the result changed when you use the ...
0
votes
0answers
20 views

Poisson distribution with normal informative priors

I'm Jia, a student of economics and finance. I was wondering if someone could help in understanding this problem. I've just started to attend a new course "Financial and nonlinear econometrics" and ...
0
votes
0answers
40 views

$\left(\sum_{i=1}^n1\right)\left(\sum_{i=1}^n x_i^2\right)-\left(\sum_{i=1}^n x_i\right)^2=\frac{1}{2}\sum_{i=1}^n\sum_{k=1}^n\left(x_i-x_j\right)^2$?

I am reading Widder's Advanced Calculus and on page 130 he states that \begin{align}\left(\sum_{i=1}^n 1\right)\left(\sum_{i=1}^n x_i^2\right)-\left(\sum_{i=1}^n ...
1
vote
1answer
21 views

An algebraic identity: $M(X_2)-M(X)=P(M(X_2)X_1)$?

Notation: for a matrix $Z$ of full column rank, we define $P(Z)=Z(Z'Z)^{-1}Z'$ and $M(Z)=I-P(Z)$. ($I$ is the identity of matrix with as many rows as $Z$.) Let's consider the linear regression model ...
0
votes
1answer
32 views

Advice to solve a system of 8th order univariate polynomials

I am struggling to solve a least square problem in which the tedious part is the initialization. Grid search methods are out of question. The initial problem I've stated my problem in a previous ...
0
votes
0answers
16 views

Fit derivative to a set of points

Let's say I have a set of discrete values $X = {x_1, x_2, x_3, ..., x_n}$ from the sampling at a rate $f_s$ of a continuous function. I scale some values in $X$ (in a different manner for each one), ...
0
votes
0answers
14 views

Determine the multi-dimensional relationship given the data

I have a dependent variable - A and 3 independent variables, H,V and N I have a data for all the variables and dependency relationship is based on my operational knowledge. I'd like to know what ...
1
vote
0answers
29 views

Estimate b when $\hat{y}$ and x are given

Using linear algebra for solving this linear regression problem, I've got the equation $\hat{y}$ = xb. Finding the projection $\hat{y}$ of y onto the columns of the matrix X containing the ...
0
votes
1answer
41 views

Linear Regression and finding Correlation Coefficient

In a Simple Linear Regression $y= \alpha + \beta x + \epsilon $, we gather this information: $S_y=20, S_x=5, \widehat{\beta} = 0.2 $ how I could find Instance Correlation Coefficient between x and ...
0
votes
0answers
14 views

How to calculate expected value (expected lifetime) when process partitioned into 2 distributions?

I have a cohort with data showing the number of users in some application. I see (and I know) that the process should be modelled: in its first $k$ time units with in the uniform distribution in ...
0
votes
1answer
14 views

Express in the form of general linear regression

I have to apply a transformation to the following to fit it to the general linear regression model $Y_{i} = \beta_{0} + \beta_{1}X_{i1} + \beta_{2}X_{i2} + ... + \beta_{p}X_{i(p-1)} + \epsilon_{i}$ ...
1
vote
0answers
26 views

Decomposition of matrix in a general linear model to find $\boldsymbol{\beta} = \mathbf{G}\mathbf{P}^{-1}$

In a simple least squares linear regression such as $y_{i} = \beta_{0} + \beta_{1}x_{i} + \epsilon_{i}$, there is a nice property that the slope of the regression line can be written $\beta_{1} = ...
0
votes
1answer
27 views

Regression coefficient in simple regression

Let's say we have two random variables $Y$ and $X$ used to form regression model $$Y=\alpha+\beta X+\mu$$ It also holds that $E(\mu)=0$, $\text{Var}(\mu)=\sigma_{\mu}^2$, $\text{Var}(X)=\sigma_{X}^2$, ...
0
votes
0answers
17 views

Relationship among parameters from models with different link function and scaled response variable

Given the model, $\log(A_i) = \alpha + \beta \, covar_i$, with $i=1,\dots,1000$, $\alpha=4$, $\beta=0.2$, and covariate $covar \sim U(-1,1)$, I derived $\log(A)$ values (in $\texttt{R}$) as: ...
1
vote
0answers
18 views

Appropriate regression test apart from MLR for crime data?

thanks in advance. I'm looking to run some statistical methods to find the correlation of crime rates to crime factors. I know about MLR, which is pretty simple to run in SPSS, but what are the other ...
0
votes
0answers
15 views

curve fittin with non-gaussian noise

Fitting with the least squares method results in the ML fit assuming the given points have a gaussian distributed noise. What methods are there for non-gaussian noise distributions, especially ...
0
votes
2answers
32 views

How to start using R (or free alternatives)?

How to start using software R to make regression analysis and forecasting? Are there any other free software to work with this kind of analysis?
0
votes
1answer
38 views

Linear Regression Application

I have a linear equation as follows: $B_0*x_0 + B_1*x_1 + ... + B_8*x_8 = result$ And i have about 200 different situations that are categorized into two different groups, depending on whether ...
1
vote
1answer
29 views

Multicollinearity: Why does highly correlated columns in the design matrix lead to high variance of the regression coefficient?

I came across the term "Multicollinearity" in statistics, particularly statistics. However, I never really understand mathematically why highly correlated (almost linearly dependent) columns in the ...
0
votes
1answer
27 views

Relationship between Kriging and Gaussian process regression models

In the science of Bayesian modeling one method involves using Gaussian processes to derive regression functions on data. I notice in looking at the plots for such regressions that they resemble ...
0
votes
2answers
26 views

Expected Value of an inefficient estimator of the $\beta$ parameter of a simple linear regression

A simple linear regression is defined as follow: $$y_i=\alpha+\beta x_i+\epsilon_i \qquad i=1,...,n$$ An inefficient way of estimating $\beta$ is defined as follow: ...
0
votes
1answer
21 views

Is the regression model Identified? (is it possible to obtain a least squares estimator of the parameters?)

$y_t$ is the dependent variable, $x_t$ and $z_t$ are explanatory variables, and $α$, $β$ and $γ$ are unknown parameters. $y_t$ = $α$ + $β$$x^3_t$ + $γ$/$log$($x_t$) + $u_t$ $y_t$ = $α$ + $β$$x_t$ + ...
0
votes
2answers
27 views

Calculate $m_1, m_2 $ for $y = m_1x_1 + m_2x_2$

Given these values: $$x_1 = \left\{1, 3, 6, 8\right\}$$ $$x_2 = \left\{2, 8, 5, 10\right\}$$ $$y = \left\{8.6, 30.8, 34.1, 53.8\right\}$$ And this formula $$y = m_1x_1 + m_2x_2$$ How do I ...
0
votes
0answers
19 views

Can we see the beta coefficients in OLS as mean values?

Can we see the beta coefficients in OLS as mean values? I mean the estimator β alone. y=Xβ+ε
1
vote
1answer
18 views

Find the OLS estimator $β_1$ when a new variable is added to the regression

Suppose $y_t$ = $β$$x_t$ + $u_t$ , where t = 1, 2, ..., n. We know, in this case, the OLS estimator is $\hatβ$ = ∑$x_t$$y_t$ / ∑$x_t^2$ . Now suppose one more observation $x_{n+1}$ is added. At the ...
0
votes
0answers
18 views

Regression model, find $Var(y_i-\hat y_i)$

For the model of $y_i = \beta_0 + \beta_1x_{i1} + e_i$ for $i = 1,...,n$, where $e_i \sim N(0,\sigma^2)$ Find $E(\hat y_i)$ and $Var(\hat y_i)$. Hence or otherwise, find $E(y_i-\hat y_i)$ and ...
1
vote
2answers
64 views

Factoring a multivariate linear polynomial

I'm a computer programmer trying to solve a particular toy problem, and my understanding of linear algebra is far too lacking to solve it! I have a data set that can be modeled using this function: ...
0
votes
1answer
31 views

Multilinear fit vs Polynomial fit

I have a program that generates some physics data in 1D and 2D functions. In this program, the user defines a number of models that are used to compute a 2D function. That 2D function, and it's ...
1
vote
0answers
28 views

Predictive models

Given a set of temperatures of different cities for a month, which prediction model should I use for a two day look ahead prediction? Regression models or Time series?
0
votes
1answer
97 views

The $\alpha$ estimation for the model $x_i = \xi_i \cdot \alpha$

We have $n$ sensors $X_i$ which estimate the scalar value $\alpha$ with different relative accuracies $\delta_i \ll 1$: $$ x_i = X_i(\alpha) = \xi_i \cdot \alpha, \ \ \ \xi_i \sim N(1, \delta_i) $$ ...