Multicollinearity means predictor variables are correlated with each other, making it harder to determine the role each of the correlated variables is playing. Mathematically, it means the standard errors are increased. Multicollinearity can have counter-intuitive effects.

learn more… | top users | synonyms (1)

0
votes
1answer
13 views

Multiple linear regression: does BIC drop (vaguely) collinear variables?

Say I have the following multiple linear regression: Y ~ X1 + X2 + X3 + X4 All X variables are independent, but X1 and X2 look kind of linearly related when ...
1
vote
0answers
34 views

Which variable to drop due to collinearity

In some specifications of my model, I use third-level interaction terms (x * y * z, where x and z are dummy variables, and y is an ordered categorical variable that takes values between 1 and 10), all ...
2
votes
1answer
40 views

How to interpret VIF?

I am using the vif function in the R package car to test for multicollinearity. I am a little confused at the output given. For example, I have 5 variables (x1, x2, ...
0
votes
1answer
42 views

Does a decrease in standard error from one model to another suggest collinearity?

Say I have model 1 and model 2. y1 = b0 + b1x1 + u y2 = b0 + b1x1 + b2x2 + u If there is an increase in the standard error of x1 from model 1 to model 2, does this suggest collinearity between the ...
0
votes
0answers
26 views

How to interpret this?

Good day again! For my thesis, I used 2 types of test to measure 3 types of dimensions for Perefectionism. The results for the correlation is everything is correlated (p>0.01). Then when I computed ...
1
vote
0answers
25 views

Multicollinearity? Non-significant multiple-linear regression, highly correlated regressors but low variance inflation factor

I have a small sample (30 obs) and 4 independent variables, 3 of which are significantly correlated to each other. I have tried to run the simple linear regression on each of them separately and it ...
1
vote
1answer
32 views

Multicollinearity and interaction terms

My dataset has 2734 observations (but in some speficitations, that number reduces to 1280). I also have interaction terms (in some specifications, even fourth-order terms). As far as I know, ...
0
votes
1answer
55 views

How multicolinearity affect the prediction

In a linear regression model, if some of the predictors are correlated, then in the output of most software, you will see very large p-value in those coefficients and very high standard error. My ...
0
votes
0answers
7 views

Elastic net is being used in genome wide analysis. Similar approach would work for survey analysis?

I'm approaching the elastic net procedure for genome wide analysis (GWAS) because it allows for feature selection, groups detection and improved validity. It's a powerful technique when you have many ...
3
votes
2answers
360 views

How seriously should I consider the effects of multicollinearity in my regression model?

I have a model y ~ x + z and the correlation between x and z is 0.2. This is only weakly positive. So, how seriously should I consider the effects of ...
2
votes
1answer
82 views

Change in order of predictors breaks logistic model estimation (glm, R)

I am fitting a binomial logistic regression in R using glm. By chance, I have found out that if I change the order of my predictor variables, glm fails to estimate the model. The message I get is ...
0
votes
0answers
6 views

Technique for estimating sensitivity to multiple correlated variables

The problem is estimating linear coefficients (in this case, the output is neural firing rate, and the parameters represent sensitivity to different sensory inputs) to multiple potentially correlated ...
3
votes
0answers
57 views

VIF for generalized linear model

Is the variance inflation factor useful for GLM models. Below example shows OLS is showing VIF>5, but GLM lower. GLM shows instability in the coefficients between train and test set. ...
0
votes
1answer
16 views

Multicollnearity in backward selection approach

When I build my most parsimonious model using a backward selection approach, do I have to worry about multicollinearity. I mean, do I first check for multicollnearity and drop the variables which has ...
2
votes
2answers
38 views

Multiple regression - how to deal with mixed linear and non-linear variables

Say I have a bunch of explanatory variables to predict a continuous independent variable. Below, a simple toy example: I think it would be easiest to do a log-log transform and proceed with linear ...
1
vote
1answer
101 views

Linear regression model mistakenly gives $R^2$ equal to 1

I'm using R to create a linear regression model from survey data about public sentiment for a new technology. I am encountering a problem where the addition of a new explanatory variable raises the ...
0
votes
0answers
23 views

Co-linear covariate in regression what if take one out?

I understand that there are a few ways to deal with correlated or co-linear covariates ( PLS or AIC, and Lasso) But my problem here is: If you have 2 covariates x1 and x2 that are correlated(you ...
0
votes
0answers
61 views

Edited: Glmer model won't run all factor levels due to multicolinearity - can you have pseudo-multicolinearity?

I have a repeated measures design in which I have tested 112 individuals each with three different 20 second playback stimuli. I used a random block design where an individual was assigned to 1 of 6 ...
1
vote
1answer
27 views

transform variables then check for collinearity or other way round?

I was planning to construct a model with around 19 explanatory variables and one response variable. I have some confusion on following thing: If transformation is required in case of explanatory ...
2
votes
1answer
51 views

Multiple regression with correlated variables

I am trying to do multiple regression analysis of a continuous health variable (yval) keeping age, gender, height (cm), weight (kg) and waist (cm) as predictor variables for a database of about 7000 ...
0
votes
1answer
34 views

What to make of countervailing spatial regression coefficients?

I am running regressions across a country's counties (N about 300). I divide the country in two regions A and B to control for potential unobservables. My explanatory variable varies at the county ...
3
votes
1answer
37 views

Principal Component Regression with an additional factor

I am looking to tease out the significance and contribution of a particular variable to 2 different continuous responses. I have 7 continuous variables I know to be influential on the two responses ...
1
vote
0answers
9 views

Three percentage indicators into one (or two measures) in regression moder

I am working with a data set resembling the extract below: ...
3
votes
1answer
54 views

Invertibility of $X^TX$ with severe multicollinearity in regression

I am studying about multicollinearity in regression and in the book it says, "if there is severe (but not perfect) multicollinearity, two or more predictor variables are highly correlated, so $X^TX$ ...
0
votes
0answers
12 views

What happens under the coexistence of biased estimation and multicollinearity?

I understand that multicollinearity induces inflated standard errors but doesnt bias coefficients while error-correlated omitted variables biases coefficient but what happens under the coexistence of ...
3
votes
2answers
63 views

Collinearity in multivariate regression with huge amounts of data

Take the following example. I wish to predict physical performance as a function of height and weight. I already know weight negatively affects performance. Height also negatively affects performance, ...
0
votes
0answers
21 views

high correlation between IVs, but VIF and tolerance normal?

In a multiple regression analysis: If two variables are correlated by more than .8, but the VIF for each of them are 1.005 and 1.006 and the tolerance numbers .994 and .995, what exactly does this ...
0
votes
1answer
158 views

Should we test error terms for auto correlation or multicollinearity

I understand the basic difference in definition between multicollinearity and autocorrelation. I.e multicollinearity describes a linear relationship between whereas autocorrelation describes ...
0
votes
0answers
23 views

Linear Regression - Number of Predictors - Negative Weight [duplicate]

I am trying to prep myself for data science interview & I saw the following question on a forum You have several variables that are positively correlated with your response, and you think ...
3
votes
0answers
49 views

Variance Inflation Factor less than 1 in ridge regression?

I was trying to determine the biasing constant in ridge regression when I came across a phenonomenon that seems quite puzzling, to me at least. I let the GCV criterion choose a constant for me and ...
3
votes
2answers
118 views

Predictor variables sum up to 1 but not necessarily correlated - is it a problem? [closed]

I am trying to fit hierarchical mixture model (using ML and MCMC, but this shouldn't matter) where the linear predictor part contains 17 independent variables. These are habitat variables: for each ...
1
vote
0answers
45 views

Principal component regression on polynomial terms

One of the data sets I am working upon had 3 variables which were having almost 100% correlation among themselves. Since I am learning regression modelling I thought I'll do principal component ...
0
votes
0answers
38 views

Multicollinearity? Weighted or unweighted covariance?

I am working with several regression models with different dependent variables where two of my independent variables of interest are correlated: I am wondering if the large standard errors associated ...
0
votes
0answers
9 views

What is the best way to test if an IV has a stronger effect on the DV than another IV that a subset of the first IV?

I wish to investigate the effect of general international experience of a corporation measured as the number of foreign subsidiaries it own vs. the effect of local experience in a region measured as ...
2
votes
0answers
93 views

Should fixed effect dummies be included in multicollinearity diagnostics (VIF calculations) for regression?

I am currently in the progress of performing multicollinearity diagnostics for a logistic regression model using tolerance and VIF calculations based on recommendations in Allison (2012) (Logistic ...
5
votes
1answer
86 views

Why do we use the term multicollinearity, when the vectors representing two variables are never truly collinear?

When two vectors $a$ and $b$ are collinear, then $a = xb$, (where $x$ is a scalar) so in linear algebra, collinearity is a narrowly and clearly defined (and binary) concept. Two vectors -- in my ...
1
vote
0answers
13 views

Variable selection multiple data types

I'm working on a data set containing 45 predictors that cover metric, ordinal and nominal variables. Aiming to finally build a model, which explains the interacting effect of a set of predictor ...
1
vote
1answer
186 views

what if response variable is 'yes or no' in R?

How to analyze above the data to predict the probability that people have disease with a model? Factors thought to influence infection include city, age, and diet. BUT, I don't know how to do ...
2
votes
0answers
54 views

Logistic principal component regression where PCs are correlated with an additional binary predictor

My scenario is this: I collected a bunch of vegetation data (% cover counts in a quadrant at different heights) in patches where birds were seen foraging and also in control patches where no foraging ...
2
votes
1answer
21 views

Covariate related to independent variable - best solutions

I have 2 groups (tinnitus sufferers and controls) who are significantly different in age - I would normally control for age as a covariate (as it is a cognitive task) but it violates the assumption of ...
0
votes
0answers
102 views

Multicollinearity test for panel data

I am using the within estimator (R, plm package) on an unbalanced panel with stock returns as the dependent variable and a number of financial ratios as the independent ones. I want to test for ...
0
votes
1answer
72 views

About stepwise regression and correlation

I am trying to fit a model to some observed data with the least squares method. Now, I am at the stage where I have run a stepwise regression (traditional), with Entry level $=0.025$ and Stay level ...
1
vote
1answer
30 views

Linear regression with redundant features (perfect multicolinearity)

Suppose $X \sim N(0,1)$, $Z=X$, and $Y=X$. An ordinary least squares regression problem is solved: $min_{(b1,b2)} \|Y-(b1*X+b_2*Z)\|_{2}^2$ This is a strictly convex function which must have a ...
1
vote
2answers
77 views

Multicollinearity in multiple regression

I really hope you can help! I'm in the last stages of my PhD. My supervisor is keen on including all variables in the multiple regressions I am running. Some of the scales are intercorrelated (some ...
1
vote
0answers
10 views

Correlation between offset and predictor in count data

I am fitting a Poisson model that requires an offset term to account for sampling effort. However the offset term is highly correlated with one of the linear predictors that is central to my ...
0
votes
0answers
8 views

Coefficients flip sign in general linear model depending on what predictors are included: collinearity is NOT a problem [duplicate]

I have a general linear model with several predictors (~10). The sign (beta) of one of the predictors (Pred1) is negative when all predictors are included. It's STILL negative when the most correlated ...
0
votes
0answers
71 views

Combining collinear continuous predictor variables in GBM

I'm dealing with a dataset (n=254) with one dependent variable (Y), and three independent variables (X1, X2, X3), all continuous. I would like to compare the contribution from each IV to Y. I've been ...
1
vote
0answers
15 views

Centering my variables decreases the condition indices

In my regression model, one of my condition indices is very high, but only the intercept and one of the eplanatory variables have a large variance decomposition proportion for this index. The VIF is ...
2
votes
0answers
70 views

Very low VIF values, but extreme high condition index

In my multiple linear regression model, all of my explanatory variables have a VIF score, lower then 3, but the highest condition index is 709. The constant and one of the explanatory variables have ...
0
votes
0answers
44 views

Regarding analysis of regression result and vif result

I am working on building a regression model. There are 51 points. The number of predictor variables is 37. The following is the result of running lm result. When trying to detecting the ...