Techniques for analyzing the relationship between one (or more) "dependent" variables and "independent" variables.

learn more… | top users | synonyms (1)

0
votes
0answers
3 views

non significance of variables in my VAR estimate

I am running a VAR model with 7 variables, but less than 10 out of 49 independent variables are significance. What could be the problem please?
1
vote
0answers
7 views

Power of a Interaction term in R

I have analysed a dataset with a linear regression model, including a interaction term between a binary variable and a continuous variable. The interaction was significant, and latter, I have fitted 2 ...
0
votes
0answers
7 views

Beta Coefficient and correlataion

What is the interpretation of negative Beta coefficient with positive correlation? TNX
0
votes
0answers
6 views

Nagelkerke value equals 1. Why?

I have run a logistic regression model, which leads to acceptable results (e.g., McFadden's R2 >10%). However, the Nagelkerke value is always 1, which seems like a failure to me (using the comand ...
0
votes
0answers
9 views

Structural Break - Stata

I have used Stata to run a time series multiple regression. I know that there is in fact a structural break in the data and the point at which it occurs; therefore, I have estimated the regression ...
0
votes
1answer
65 views

When to not use R squared [duplicate]

I recently graduated graduate school and am looking for a proof on R squared. Specifically when to not use it. I really remember a professor impressing upon me multiple times not to report R squared ...
0
votes
1answer
48 views

PCA vs. Linear Regression

Am taking Ng's Machine Learning class on Coursera and in the below slide he distinguishes PCA from Linear Regression. He says that in Linear Regression, we draw vertical lines from the data points ...
0
votes
0answers
7 views

How can I ENTER a 4-way interaction in a hierarchical regression blocks in SPSS? [on hold]

I have 4 variables, and I want to compute their interaction in a hierarchical multiple regression. But I do not know how I put main and interaction of variables in blocks of hierarchical multiple ...
1
vote
1answer
33 views

Does one need to transform percentages/proportions for a multiple linear regression?

I am aware that one should transform percentages and proportions when using them in an ANOVA, due to the values being bounded by 0 and 1. I have seen suggestions that the best transformations are ...
3
votes
0answers
19 views

Interpretation of R-squared when using FGLS

Context: I am analyzing time series and cross-sectional data using Stata's xtpcse command which corrects for autocorrelation in panel data using a Prais–Winsten ...
0
votes
0answers
23 views

K-fold cross validation [on hold]

I'm working on a data set that contains used (value= 1; animal locations) and random locations (value = 0). I'm using logistic regression to assess non-random habitat selection. I have 6 continuous ...
0
votes
0answers
10 views

Adding Regression Lines to Multiple Scatter Plots [migrated]

Had a look around and couldn't find an answer to my question, so finally stopped lurking. I've been creating multiple scatter plots comparing each column to the others I used the script attach(...
0
votes
0answers
10 views

Multinomial logistic regression, how to treat conditions without variance?

Currently I need to conduct a multinomial logistic regression, but my output shows an error message and incomplete results. I expect this is due to the fact that in one of my conditions, all ...
0
votes
0answers
19 views

Classifier that learns provided by only positive examples?

I was wondering if any of you has ever worked with classification/regression using only positive examples (one class). I would need such a system. The basic idea is that it is going to accurately ...
1
vote
2answers
390 views

what does linear regression actually mean?

Wikipedia gives the following definition for linear regression: In statistics, linear regression is an approach for modeling the relationship between a scalar dependent variable y and one or ...
0
votes
0answers
19 views

K-fold cross validation dealing with an interaction term

I'm working on a logistic regression analysis and have a data set that contains ~12,000 data values (~6,000 values = 1; ~6,000 values = 0). I would like to use a k-fold cross validation process to ...
1
vote
0answers
27 views

Tennis Analytics: How to Build Model Predicting Player Service Point Win %

I have collected a large amount of tennis match data including player names, court surface, player ranking points at time of match, handedness of player, point by point breakdown of match etc. I ...
0
votes
0answers
9 views

What's a good robust approach to something like multi-variable local polynomial regression with known changing noise magnitude?

I have a sample-based estimator of a function $f(x,y)$ parametrized by two inputs. The region of valid $x$ and $y$ is an axis-aligned (bounded) rectangle. I have decided to create a grid of points in ...
0
votes
1answer
30 views

Comparing regression models with different coding of the same linear predictor

How can I determine whether one coding of a linear predictor leads to a better fit of the corresponding regression model than the other? In the following example, the restricted cubic spline coding of ...
3
votes
4answers
144 views

L2 regularization is equivalent to Gaussian Prior

I keep reading this and intuitively I can see this but how does one go from L2 regularization to saying that this is a Gaussian Prior analytically? Same goes for saying L1 is equivalent to a Laplacean ...
1
vote
0answers
27 views

Comparing more than two populations

I have a dataset of around 20 financial advisors and their customers. The customers have been divided into groups based on type of investment, as well as the size of their investment and whether the ...
0
votes
0answers
28 views

Why Removal of Outliers Does not Affect Confidence Interval [on hold]

I have a question regarding why confint(), a function in R which returns a 95% confidence interval when applied to a linear model, returns the same result even when I remove the single greatest or ...
1
vote
1answer
36 views

Using lm() with just one variable in R

I've got some baseball stats, RBIs by season, let's say: ...
0
votes
0answers
18 views

Use Logistic Regression Literature for Logit Discrete Choice Models

I'm currently developing a binary logit Discrete Choice Model (DCM) in the context of my thesis. Obviously, I want to develop the model following academic standards. A few questions have been arising: ...
0
votes
0answers
13 views

weighting regression models

I have a socio demographic variable (SDV) that should be included in a regression model to account for differences in variation in the way that the SDV impacts the dependent variable. I.e. to help ...
0
votes
0answers
12 views

insignificant Intercept becomes significant after inclusion of additional variables [duplicate]

How come the intercept of a multivariate regression become significant when two additional variables are added? And how do I interpret this change in significance? I realize that if the additional ...
1
vote
0answers
20 views

Estimating a plane from a set of 3D points

I am trying to estimate a midplane of a 3D model using the midpoints of paired landmarks, in order to reconstruct missing data. I therefore need to estimate a midplane from 27 3D points. I have looked ...
0
votes
0answers
26 views

Is there any objective criterion to determine the adequate degree of polynomial approximations?

I carry out a polynomial function approximation to a load duration curve (monotone decreasing function). I can approximate the load duration curve by using polynomial degrees from 4 to 12. I need an ...
-1
votes
0answers
14 views

What scale to use for likert data [on hold]

I am currently in the middle of writing my dissertation and I have reached the area where I am meant to be analysing the data. I used a likert scale for my questionnaire and now i have got the data ...
1
vote
1answer
13 views

Alternate terms, or definition for functional logistic regression

I have recently come upon a paper discussing "functional logistic regression." I could not find literature related to functional logistic regression. Is there a different name for this kind of ...
1
vote
0answers
10 views

Standard function for comparing regression (supervised learning) algorithms

I would like to do some Monte Carlo based comparisons of regression methods. I am looking for a general contnuous function or class of functions to generate training and testing data sets. The ...
-1
votes
1answer
24 views

Cross validation when only the regression equation is given [on hold]

Is there any function in R to conduct cross validation when you only know the regression equation?
2
votes
1answer
62 views
+50

Why is post treatment bias a bias and not just multicollinearity?

In this presentation by Gary King, he discusses post treatment bias as follows: Post treatment bias occurs: when controlling away for the consequences of treatment when causal ordering ...
0
votes
0answers
22 views

Best forecast method for my data

I have a large amount of statistical data on tennis matches over the last 10 years and want to be able to forecast the percentage of points a server will win on his own serve based on past data. For ...
1
vote
1answer
40 views

package {glmnet} too many variables with Lasso

I used the glmnet-package to do a regression + variable-selection with Lasso. I had n=100 oberservations and p=200 covariables. I always read that after variable-selection with the Lasso there a ...
1
vote
0answers
16 views

DLM, regression and multiple time series

I'm working with incoming traffic data at multiple spots along a long road. Let's denote the traffic at time t at point $j$ by $x_j(t)$. For each spot, a univariate model, such as local level plus ...
0
votes
0answers
16 views

Standard Deviation of multiple regression [on hold]

Taking into account the following regression statistics: multiple regression 0.950678 R square 0.903789 Adjusted R square 0.8763 Standard Error 0.573142 Observation ...
0
votes
1answer
24 views

Clarification on the rule of 10 for logistic regression

Been brushing up on my logistic regression and I've seen a couple of things about the one in ten rule. To illustrate my current understanding (or lack thereof) lets consider a case with only two ...
1
vote
0answers
9 views

Estimate growth rates in a probit/logit model

I consider a situation where k different kinds of bacteria grow together in a petri dish and each kind of bacteria exhibits exponential growth, i.e. the population size over time is given by $N_i(t) = ...
1
vote
1answer
17 views

Regression with double-counting

I am using regression to model production cost based on multiple regressors. Two of them are related, but may have different effects: number of products made and number of unique products made. I am ...
3
votes
3answers
67 views

Bayesian logit model - intuitive explanation?

I must confess that I previously haven't heard of that term in any of my classes, undergrad or grad. What does it mean for a logistic regression to be Bayesian? I'm looking for an explanation with a ...
2
votes
1answer
15 views

Is removing points from a calibration rigorous?

When a calibration is generated from a set of standards run on an analytical instrument, should the standards be remade and reanalyzed if not all of the points fit within 20%-30% (depending on ...
0
votes
0answers
13 views

R: AOV Test to Determine Correlation Not Showing Significance?

I am using an ANOVA test in R to determine if there is a correlation between income and a binary indicator variable $I$. So I did: aov(formula=I~income, data=df) ...
0
votes
0answers
7 views

Polynomial ANCOVA glm in R

I have a data set of success and failure counts with one continuous independent variable and one factorial variable: ...
0
votes
0answers
15 views

Multivariate linear regression with prior information on variances

I have a slight variation to a classic problem, which might have a simple answer - but if it does, I cannot find it. My problem is a multiple linear regression, of the type that is common in ...
0
votes
1answer
34 views

Bootstrap confidence intervals for regression and correlation coefficients

Take an example of a linear regression, $Y= \beta X$ where X and Y values are z-score transformed ($\mu$ = 0, $\sigma$ = 1). In this situation the correlation coefficient $r$ equals $\beta$ ...
0
votes
0answers
30 views

Is my regression model ok? [on hold]

I am trying to set up a model for determinants of CEO compensation. I am posting the residual graphs. They look unusual. Could you please tell me if my model is ok or should I make some changes? ...
0
votes
0answers
16 views

Is there a way to do logistic regression model selection of up to 5 variables each from a pool of ~70 variables

I'm trying to determine the best logistic regression model to estimate the probability of 0 in streamflow rates. My response for the glm object is one vector of the sum of all the days the recorded ...
0
votes
0answers
11 views

How to deal with a warning messages on lmer? [closed]

I ran a mixed model using lme4 for a logistic regression and got these warning messages. How to deal with it? Warning messages: 1: In checkConv(attr(opt, "derivs"), opt$par, ctrl = ...
0
votes
0answers
17 views

Calculating residuals for an exponential fit

We have a question about the proper interpretation of 'residuals' when doing an exponential fit. Right now we have the following R code: ...