A generalization of linear regression allowing for nonlinear relationships via a "link function" and for the variance of the response to depend on the predicted value. (Not to be confused with "general linear model" which extends the ordinary linear model to general covariance structure and ...

learn more… | top users | synonyms (1)

1
vote
1answer
11 views

When to use zero-inflated poisson regression and negative binomial distribution

I have a fairly simple dataset looking at the relationship between the first nesting date of a bird in a given year (Date) and the birds overall fledgling production from that year (Fledge; count data ...
0
votes
0answers
5 views

Model selection using an artificially insignificant covariate

This is continued from my other post on model selection. Let me provide more details first. 1) I have a factorial design. Factor A has 5 levels, B has 2 levels, C has 2 levels. Let us assume that ...
1
vote
0answers
14 views

how to interpret Interaction term in generalized linear model [duplicate]

I have an experimental condition (dummy-coded) as an categorical predictor, and one continuous predictor variable (treatment frequency). The dependent variable (Y) is consumer satisfaction This is ...
0
votes
0answers
10 views

Partial pseudo $R^2$ with GLMs

Is a partial pseudo $R^2$ (pseudo $\eta^2$?) even a valid concept when dealing with a GLM? This, of course, presumes that partial pseudo $R^2$ is valid at all. If it is valid, how would one go about ...
0
votes
0answers
33 views

R: Prediction using glm() [migrated]

I am using glm() function in R with link= log to fit my model. I read on various websites that fitted() returns the value which we can compare with the original data as compared to the predict(). I ...
0
votes
0answers
10 views

Pareto two-tailed GLM regression

How can I perform a Pareto two-tailed GLM regression? Any reference to link functions and code in R?
2
votes
1answer
15 views

GLM Prediction Variance with Average Observations

Suppose I have data set where the observed values are averages and not necessarily individual data points. For example, suppose record 1 has the observed value of $Y_1 = 2.0$. However, I know that the ...
0
votes
1answer
17 views

Modeling remaining duration for prediction

Suppose we're in the business of repairing broken specialty widgets and reselling them. At each point in time, we want to predict how much cash we'll make in the next 30 days on the existing ...
0
votes
1answer
33 views

adjustment of covariates in linear model

I am trying to understand the adjustment of covariates in the linear model such as multiple logistic regression. How does adding a covariate adjusts the coefficients for that covariate (any intuitive ...
1
vote
1answer
60 views

linear regression intercept does not match

I have done a linear regression in R, using glm function. The calculated intercept says 0.98, but when I plot it, it does not seem to hit the estimated intercept on Y axis. Its far below. Here are my ...
0
votes
0answers
28 views

A non-negative definate matrix has a non-negative generalized inverse

I'm having trouble proving a N.N.D matrix has a N.N.D G-Inverse. So far I have: If we assume x = Az where x >= 0 and A is a nnd matrix. So if Y is a G-inverse than: x = Az = YAz = Yx >= 0 . Thus ...
0
votes
1answer
46 views

What is the difference between GLM and splines?

Suppose we want to predict $Y$ given the following $X$ observations: ...
2
votes
1answer
14 views

conditional independence in repeated measures design

How the responses are independent when conditioned on random effect in repeated measure analysis (linear mixed model)?
0
votes
1answer
41 views

Interpretation of $\theta$ in negative binomial regression

First off, a very similar question has been asked before. But the answers to this question did not explain what high/low values of theta mean. Here's my crack at trying to figure out what high/low ...
1
vote
1answer
24 views

model comparison when alternatives are not all nested within one another

I am running a glmm with three fixed effects: opponent 1 size ("1") opponent 2 size ("2") opponent 1 size - opponent 2 size ("diff") I am unable to run all three variables in the model at once ...
1
vote
0answers
13 views

What properties of a likelihood function are required for quasi-likelihood estimation?

Quasi-likelihood seems like a great way to use Iteratively Weighted Least Squares to fit linear linear models with a very general class of likelihoods. But what is that class? Obviously the ...
1
vote
0answers
15 views

Struggling with non-normality in generalized linear model

Dear statistics experts, I am looking for correlations between certain measures of brain structural integrity (fractional anisotropy, given as ratio between two hemisphere ==> rational data range ...
9
votes
1answer
118 views

Increased Type I error - GLM

Some of you might have read this nice paper: O’Hara RB, Kotze DJ (2010) Do not log-transform count data. Methods in Ecology and Evolution 1:118–122. klick. In my field of research (ecotoxicology) ...
0
votes
0answers
9 views

GLM post hoc with non-parametric tests?

I have a question regarding the appropriate use of comparisons for independent samples (3 factor levels). Overall sample size is N=546, subsamples: 218 or 228 or 100), convenience sampling, ...
0
votes
1answer
40 views

How do I choose between a simple and a mixed effect logistic regression?

I have a list of predictor variables to put in to a logistic regression model. How I know that should I do a simple logistic regression (using glm function in R) or ...
0
votes
0answers
19 views

How to model when actionable data is generated on a daily basis

Trying to build a predictive model for attrition prediction of service desk agents using logistic regression. Data available: Daily performance metrics such as call quality,avg. call ...
0
votes
0answers
11 views

How to do planned comparisons on repeated measures (GLM repeated measures) using SPSS?

I have issues figuring out how to perform planned comparisons using a GLM for repeated measures analysis. More specifically, I have one group of subjects, assessed with 2 different scales (3 subscores ...
1
vote
3answers
139 views

How to choose data for training a predictive model for attrition prediction

Trying to build a predictive model for attrition prediction at service desk/call center. Have daily data on the following parameters: 1.Call quality - QTM (0-100%), 2.No. of calls - Calls(Number) ...
1
vote
1answer
28 views

Multiplicative error and additive error for generalized linear model

If the following generalized linear model was used, how should I interpret the error term? link function: natural log distribution: Gamma distribution i.e., $\ln E(Y)=X\beta$ and $E(Y)=\exp(X\beta)$ ...
1
vote
1answer
60 views

How to model a count dependent variable with upper limitation

I have a dependent variable, which have 0, 1, 2, or 3 for its value. I asked participants to choose three items and coded 1 if it is in a certain category and 0 otherwise. I add the three binary ...
0
votes
0answers
15 views

Zero inflated model problem: system is computationally singular

I'm using R.After getting an error asking me to provide starting values for a glm (poisson family), I took a look at my data and realized I had quite a bit of zeroes. So, I tried zeroinfl from pscl. I ...
1
vote
0answers
30 views

Confidence interval for a regression parameter via prediction

Consider a simple Poisson-regression - GLM - model. There $\exp\left(\beta\right)$s are used as Incidence Rate Ratios (IRR), but their calculation is sometimes not completely straightforward, for ...
0
votes
0answers
14 views

GLMM - time or day/date as a random factor

I have searched for many days trying to find the answer to this question, and am still not 100% sure I am happy with my conclusion. I am interested in looking at the effects of environmental variables ...
5
votes
0answers
52 views

Identifiability in generalized linear random effect model?

Suppose I observe binary $Y_{ij}$ for $i = 1, ..., N$ and $j = 1, ..., J$ and I want to model $$\Pr(Y_{ij} = 1 \mid \lambda_{i}) = \Phi(\lambda_{ij}), \qquad [Y_{ij} \perp Y_{ij'} \mid \lambda_i]$$ ...
0
votes
1answer
38 views

Regressing, analysing data with points rather than polynomial?

I am looking into making a regression of a bunch of data that is contained on some range of real numbers. In my case, x is between 0 and 1 and y is between 0 and 10. If I have 150 data points on this ...
2
votes
1answer
30 views

Is it acceptable to not include high-order interactions (3-way and above) in the model when they are not by themselves of interest?

Is it acceptable to not include high-order interactions (3-way and above) in the model when they are not of interest and not part of the hypothesis that is being tested? NB. I am not talking about ...
-1
votes
0answers
28 views

Am I using the correct model, if so what do I need to fix?

I am seeking to model the number of high tunnels on farms with 13 other factors. Factors include: lattitude, percent of the population with food access, percent of vegetable acres per county, ...
1
vote
0answers
39 views

Help with complex model formula in lmer (lme4) for R

Most examples about lmer formula description in R target rather simple study designs. However, sometimes one is confronted with more complex designs and there is no ...
2
votes
2answers
88 views

Sine link with binary regression

I have used the SIN link to estimate probabilities, mostly with Program MARK. However, I am not sure how the SIN link works. I know the SIN link enables parameter ...
0
votes
0answers
21 views

How to deal with categorical features.

Recently I am playing in the famous Big-Data website Kaggle. There is a Display Advertising Challenge. In this competition, you are giving a training file which include huge records. the records is ...
3
votes
1answer
44 views

Numerical stability of IWLS for Gamma models with log-link

The combination of a $\Gamma$-distribution with the log-link function in a generalized linear model can be a useful model. However, in my experience the iterative weighted least squares (IWLS) ...
-3
votes
1answer
38 views

code for ordered probit model

I have a data set with 7 predictor variables and one dependent variable. The dependent variable has 4 categories so it's not binomial. I need to fit a probit model. I need codes for probit model in ...
0
votes
0answers
12 views

package in R for BMA of a logistic model?

I am trying to perform analysis similar to Gerlach et al. (2002). it involves predicting the posterior probability of a particular binary outcome using the previous 5 observations. I was just ...
0
votes
0answers
11 views

rebuild model based on what columns a record has

I've built a model in R using glm, and in the new dataset that I need to predict, there exist some new levels for the columns that are non-numeric. I know there are so many approaches to deal with ...
2
votes
0answers
33 views

What GLM family and link function for “proportion of time”?

A simple question to which I don't seem to find the answer anywhere. I have a response variable duration of time spent doing A of individuals tested for ...
-1
votes
0answers
33 views

In the glm function for logistic regression, where is the likelihood function stored? Is it in family? [migrated]

I am currently trying to run a logistic regression on my own, using the functions optim, nlm, etc. However, I am somehow getting ...
1
vote
2answers
56 views

Best Fit for Exponential Data

I'm trying to better understand some of the theory behind fitting models that have a nonlinear link between the response and the predictors. ...
1
vote
0answers
22 views

How to structure data for SPSS (percentages for log-linear analysis)?

I am a bit desperate because I am writing my Msc thesis and I am not sure how to organize my data for an SPSS usage. My research examines the performance of mobile banner campaigns and how the 3 ...
1
vote
1answer
68 views

Testing the variance part of a Generalized Linear Model out of sample

Suppose I have a response vector and a factorial design (for simplicity, assume it’s a one-way ANOVA with two treatments). A few Generalized Linear Models (Poisson, Negative Binomial, etc) are fitted ...
1
vote
1answer
32 views

Interpret GLM Output (Gaussian - identity) with B0 close to zero

I am doing a GLM (guassian - identity) using R. I am modeling different variables (8) to try to understand what creates brand value in an organization. Some extracts from the output are: ...
4
votes
1answer
231 views

Likelihood and estimates for mixed effects Logistic regression

First let's simulate some data for a logistic regression with fixed and random parts: ...
2
votes
0answers
24 views

Derivation of normalizing transform for GLMs

How is the $A(\cdot) = \int\frac{du}{V^{1/3}(\mu)}$ normalizing transform for the exponential family derived? More specifically: I tried to follow the Taylor expansion sketch on page 3, slide 1 of ...
0
votes
0answers
25 views

General Linear Model (GLM) with Continuous Variable and Categorical Variable (SPSS)

I would like to perform a GLM with a continuous variable and categorical variable as fixed factors. For e.g. Weight predicted by Height and Gender. From what it seems, the univariate GLM option in ...
2
votes
2answers
26 views

AR terms and independent variable as regressors

After trying several models with my data, R^2 and p values are showing my model looks like below. ACF plot tells me AR term is significant. Insights into data tells me change in 'x' would have ...
0
votes
0answers
20 views

SAS syntax to find differences in regards to a control treatment

I am working with a data set of bacterial cell counts, using flow cytometry. I recorded the cell number in 3 different species of bacteria, all treated with 3 different compounds (L-aspartic acid, ...