Questions tagged [multivariate-regression]
Regression with more than one response (dependent) variable.
355 questions
1
vote
1
answer
81
views
Training by consecutive three days to predict day4
I have the following task to do: Training by the consecutive 3 days to predict the each 4th day. Each day data represents one CSV file which has dimension 24x25. Every datapoints of each CSV file are ...
1
vote
1
answer
37
views
Is a random intercept necessary for multivariate models?
I’m modeling height and weight as joint outcomes in a Bayesian multivariate model with brms, ...
1
vote
0
answers
12
views
Is penalized regression an appropriate way to analyze observational data in this space-for-time substitution study?
I am interested in understanding how a suite of response variables (soil metrics such as pH, element concentrations, rates of decomposition/minderalization, etc.) vary with 1) soil depth, and 2) time ...
1
vote
0
answers
10
views
Is there a link between a multivariate VAR specification and the bivariate ones arising when combining the variables in groups of two?
Consider $x_t=(x_t^1,x_t^2,x_t^3)$ and a simple Vector Autoregression (VAR) of order one for its dynamics, given by
$$
x_t=\Phi x_{t-1}+\epsilon_t,
$$
where $\phi\in\mathbb{R}^{3x3}$ satisfies the ...
0
votes
0
answers
7
views
Modeling a Multivariate Time Series with Non-Constant Intervals
The time series literature I've been exposed to usually assumes that multivariate data shares observation timestamps i.e. representing a VAR as $\mathbf z_t$ for $t \in \{1, \dots, T\}$. I'm currently ...
0
votes
0
answers
21
views
Can the derivation of the BIC be simply extended to multivariate observations?
Under the assumption that observations are univariate and i.i.d., the classical definition of the Bayesian Information Criterion for a model $\mathcal{M}$ and a dataset $\mathcal{D}$ is
$$
BIC = -2 \...
3
votes
2
answers
141
views
How compute a BIC for multivariate regression?
I would like to know if it is possible to compute a BIC for a multivariate regression (One predictor X and 3 responses outcomes Y). If yes, how?
In R, when I run:
...
0
votes
0
answers
12
views
Effect of Variable Disaggregation on Other Coefficients
Suppose that I do a multivariate regression of variable $Y$ on variables $X_1, X_2, \ldots X_k$ and find coefficients $\beta_1, \beta_2, \ldots \beta_k$.
Consider that variable $X_n$ can be dis-...
2
votes
0
answers
33
views
Bayesian multivariate regression with repeated measures
I am trying to estimate variance components (specifically, genetic correlations) using mixed-effects models. My random effect is subject id and my dependent variables y1 and y2 are categorical scores ...
1
vote
0
answers
43
views
Predicting continuous variable based on curve
I have a dataset of a set of curves measured at different frequencies, so it is composed of curves as the figure below for example. My dataset has many more curves of course. A curve is associated ...
0
votes
0
answers
81
views
Deriving orthogonality of residuals without normal equation?
In my reading I stumbled across this page which seems to prove the expression for the OLS estimator using the fact that $X^T\hat{\varepsilon} = 0$. However I cannot seem to find a proof of this former ...
0
votes
0
answers
26
views
Target encoding in linear regression
I have a dataset with the loss rates of each contract as dependent variable. As independent variables I have country (four values), profession (5 values) and income (continous variable). I apply ...
0
votes
1
answer
30
views
Understanding the significance of a few results derived in the course of linear regression
I am reading up on linear regression from 18.650 MIT. In the way of explaining it, the professor derives a few results and I have attached them in the image
The first result gets used along with the ...
3
votes
2
answers
162
views
A question about linear regression results
This is from the lecture slides of mit 18.650
Here $\sigma^2$ is the variance of the error term ($\epsilon$) in the true model $Y = \beta X + \epsilon$ and $\hat{\beta}$ is the model's estimate of $\...
0
votes
1
answer
76
views
Multivariate statistical criterion to select key variables
I have a complex dataset with several predictor variables $X_i$ ($i=1,...,m$) and several outcome variables $Y_j$ $(j=1,...,n$). The problem is that many of the predictor variables are correlated ...
0
votes
0
answers
43
views
Terminology: multivariable when multiple levels of categorical variable?
Oftentimes, one sees people use terms such as univariate and multivariate logistic regression, where they clearly refer to number of predictors rather than number of response variables. I know it ...
7
votes
2
answers
103
views
Univariate approach to a Bivariate logistic regression
Consider a situation where two independent agents (out of a set of many agents) look at the same problem and attempt to solve it with a yes/no response, obtaining $(Y_{i1},Y_{i2})$ for $i \in \{1,\...
1
vote
1
answer
34
views
Multivariate Regression - Categorical and Continuous Outputs?
I am performing process characterization of a welder and want to put together a model of the inputs vs outputs of the system.
Currently I am performing individual multiple regressions with 4 inputs (...
-1
votes
2
answers
64
views
Logistic regression - When to include or exclude a confounding variable from the model?
I am working on determining if there is an association between a medication (yes/no) and a health outcome (yes/no).
However, the lines between what is a confounding variable to include in the model, ...
5
votes
1
answer
47
views
How can I quantify uncertainty for a least squares estimator in a multivariate linear regression with covariance structure?
Suppose that we have
$$\mathbf{y}\sim\text{N}(\mathbf{X}\boldsymbol{\beta},\sigma^2\mathbf{M}\mathbf{M}'),$$ and let $\boldsymbol{\hat{\beta}}$ be the least squares estimator for $\boldsymbol{\beta}$. ...
1
vote
1
answer
31
views
How do I find all the independent variables for a time series regression model?
Suppose I have a single time-dependent variable $y_{t}$ (e.g. stock price) and a few hundred independent variables $X_{it}$ with data available for the same time frame as $y_{t}$ (e.g. company revenue,...
4
votes
1
answer
38
views
meta-analysis of prognostic factor for models with different parameters
I am trying to meta-analysis the OR of a variable (troponin) for a dichotomous outcome (mortality). There are several multivariate logistic regressions out there, but none of them share the exact same ...
1
vote
0
answers
35
views
How to model the additive components of a random variable whose value is known
I would like to model the variables $Y_1, Y_2, …, Y_n$, which satisfy the constraint $Y_1 + Y_2 + … + Y_n = Y$; where $Y$ (or at least an accurate estimate $\hat{Y}$ thereof) is readily available. ...
1
vote
0
answers
41
views
"Smooth" multivariate regression
I'd like to model
$$y_t = X \beta_t + \epsilon$$
where the predictors are powers of a single variable $x$ (this should be polynomial regression), and I have data for multiple time points $t$. I know ...
1
vote
1
answer
46
views
What does small optimism in predictor effect mean?
I'm reading the following paper by Burke et al.
Minimum sample size for developing a multivariable prediction model: Part I – Continuous outcomes
The paper discusses the minimum number of samples ...
0
votes
0
answers
36
views
Hyperparameter tuning and initialisation doubts in multivariate gaussian process model
I'm trying to train a multivariate Gaussian Process model using the code here https://github.com/Magica-Chen/gptp_multi_output. However I noticed how problematic is to initialise the length scales of ...
1
vote
0
answers
15
views
estimate household expenditure pattern using a multivariate regression model, or other approach?
I am working on my school project, is about the study of household expenditure pattern using regression approach. Say that I having following linear ols regression model, where y is household ...
1
vote
0
answers
86
views
How can I combine model parameter uncertainty and input uncertainty?
Suppose I have a finite data sample $\mathbf{S} = \{ (\mathbf{x}^{(1)}, \mathbf{y}^{(1)}), \dots, (\mathbf{x}^{(N)}, \mathbf{y}^{(N)}) \}$ from an unknown data-generating function of the form
$$ \...
5
votes
1
answer
255
views
Minimum number of observation in multivariate regression
Given a multivariate regression, in a form bellow, what would be the minimum number of observations ($n$)?
$$\mathbf{Y}=\mathbf{X}\mathbf{B}+\mathbf{E},$$
where $\mathbf{Y}, \mathbf{X}$ and $\mathbf{E}...
0
votes
1
answer
128
views
How can I generate bootstrap confidence intervals for a multivariate regression network?
I am reading "Confidence Intervals and Prediction Intervals for Feed-Forward Neural Networks" by Richard Dybowski. In this paper, an ensemble of neural networks are trained on bootstrapped ...
2
votes
1
answer
110
views
Test for multivariate regression coefficients
Given a multivariate regression, how can I test if each element in the coefficient matrix is statistically significant? Would doing a t-test be right?
$$\mathbf{Y}=\mathbf{X}\mathbf{B}+\mathbf{E},$$
...
1
vote
3
answers
214
views
Performing 3 multivariate linear regressions at once
I have 3 variables X, Y and Z. I want to perform 3 OLS regressions: X dependent on Y and Z, Y dependent on X and Z, and Z dependent on X and Y.
Instead of doing the 3 of them sepparately, I want to ...
4
votes
1
answer
344
views
Heteroscedasticity robust variance-covariance matrix for weighted multivariate regression
I need heteroscedasticity robust standard errors for a multivariate linear model (MLM) with weights. In R we usually use sandwich::vcovHC with type ...
2
votes
1
answer
970
views
Logistic Regression models with two or more response variables in R/SAS
There are a lot of inconsistencies in the literature over what should be the appropriate term(s) for the regression models involving two or more responses, and if they are binary/continuous, for more ...
0
votes
0
answers
81
views
MSE for multivariate case
This is very basic, but I want to clarify the MSE in a vector-valued setting.
Given observations
$$ \begin{bmatrix}
[x_1, y_1,z_1] \\ \vdots \\ [x_n, y_n,z_n]
\end{bmatrix} $$
And estimations
$$ \...
1
vote
1
answer
157
views
Python / R package for multivariate gaussian process regression for circular data?
I have two circular predictor features (two angles between 0 and 360 degrees) and a circular outcome (another angle, between 0 and 360 degrees). I'd like to be able to fit a model and get predictions ...
1
vote
1
answer
29
views
Which Cox PH model for different treatments and sites
I am building a Cox PH model in r to analyze my data and I am unsure what the best way to do it is.
It is observational data and the idea is that we want to know the effect of a treatment A used at ...
1
vote
0
answers
34
views
Can I use the multivariate response predictions of some variables as covariates to predict another correlated response?
I have covariates to predict 3 multivariate response variables, and would like to use those 3 predictions to predict another forth variable that is also correlated with the other variables:
...
0
votes
1
answer
352
views
Can I combine dichotomous and continuous outcomes into a single regression model?
I am doing analysis on an educational product that aims to predict what impacts whether or not a student gets a question correct or incorrect. The DV includes item scores from four different question ...
1
vote
0
answers
62
views
How do I model relative time spent doing different behaviours?
I have a dataset comprising observations of ducks performing different behaviours. Specifically, ducks were observed for 1 minute each, and during each 1 minute observation the amount of time that ...
2
votes
1
answer
381
views
Multivariable Cox Regression Analysis
I would like to know if in multivariable Cox regression analysis there is a way to yield only models that include a variable of interest (and if no model is statistically significant to just answer ...
0
votes
1
answer
83
views
Multivariate regression and process control
I have a question regarding process control with the use of multivariate regression.
The setup is as follows: say we have some data, representing the results of a plant process. Specifically, several ...
1
vote
1
answer
103
views
interaction term in Cox PH model
I have a question with regard to interaction term in Cox PH model.
I'd like to analyze the impact of variable A on cardiovascular (CV) event.
Variable A levels are different according to sex, although ...
1
vote
2
answers
55
views
How to calculate a cross-product like R^2?
$\lbrace Y_1, Y_2, \boldsymbol{X} \rbrace$ are jointly normally distributed (it is not essential to assume normality, I think). Let $\Sigma_{X}$ be the variance-covariance matrix of $\boldsymbol{X}.$ ...
5
votes
1
answer
345
views
How to construct a confidence interval for the coefficients of a multivariate regression with dependence between dependent variables?
Suppose we have two linear regression models $y_1=a+bx+\epsilon_1$ where $\mathbb[\epsilon_1]=\sigma_1$ and $y_2=c+dx+\epsilon_2$ where $\mathbb[\epsilon_2]=\sigma_2$. In other words, I am using the ...
1
vote
0
answers
13
views
Extracting factors of a large (dimension m,n) matrix M which correlate with a vector P (length m)
So I'm dealing with a large gene expression dataset (m sample by n genes, where m ~ 1000 and n ~ 20,000). For each of these samples, a phenotype of interest P exists. I'd like to be able to say ...
0
votes
0
answers
276
views
Adjusted $R^2$ (R-squared) for multivariate regression
For univariate or single independent variable regressions, this formula can be used (details here):
$$R^2_{adjusted} = 1- \dfrac{SSRes}{SSTotal}\dfrac{n-1}{n-p}$$
However, I cannot find a similar ...
0
votes
0
answers
42
views
Working with a Dataset containing multivatiate numerical Timeseries which is highly sparse
I am working currently on a private dataset that has a similar structure to MIMIC-III. The dataset has following structure:
p Patients,
e Examinations,
t Timepoints
For every patient there are ...
1
vote
1
answer
31
views
I have set of features to relate to two different values. When I made a regressor for only one it worked well but if i use two it does not?
I have a set of 33x1 features (x) and they can be related to different two values in (y) and I have 1203985 observations. Using np.shape() you can see the dimensions of x and y.
x= (1203985, 33) y=(...
3
votes
3
answers
6k
views
Visualizing multivariate multiple regression of continuous data in R
I have created a multivariate multiple regression model with 3 dependent and 3 independent variables in R, and would like to generate meaningful visualizations. All variables are continuous. When ...