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)

0
votes
0answers
6 views

Interpreting results of a GLM used for eQTL analysis

I am having some issues interpreting the output of the glm model I am using for an eQTL analysis (an analysis of genotype vs. gene expression for a particular ...
0
votes
0answers
22 views

How to represent bayesian loss function in binary classification

I am studying classification using linear regression . Now, I want to map it in Bayesian regression. Let talk about binary classification using linear regression again. Assume that I have a set ...
1
vote
0answers
19 views

Logistic regression with multi-class features in R

I'm working with a data set like the following: X = ...
2
votes
0answers
28 views

R GLM verifying performance statistics for validation

I do not want to say my AUC is 0.77 and find out I am overlooking a lot. Below is my code and a two question at the bottom: ...
2
votes
1answer
98 views

What loss function can I use for linear classification?

I have a question about loss function in bayes classification. Let see similar case of loss function in linear classification: Given data $(x,y)=${$(x_1,y1)....(x_n,y_n)$} is map to label $T=${-1,1}. ...
2
votes
1answer
45 views

Multiplicative errors for linear model

I am trying to figure out the 'standard' way of handling multiplicative error in a linear model, i.e. my model reads: $$ Y_i = (ax_i + b)\varepsilon_i , \quad \varepsilon_i\sim\mathcal{N}(1, ...
1
vote
0answers
36 views

How does the cubic spline basis exactly look like

By the definition I'll have (1) $S(x)=\begin{cases} S_0 = a_0x^3 + b_0x^2 + c_0x + d_0, & \text{if }t_0\le x\le t_1\\ .....\\ S_{k} = a_kx^3 + b_kx^2 + c_kx + d_k, & \text{if ...
7
votes
1answer
127 views

Obtaining an estimator for z given an estimator for log z

As per gung's advice in Getting the equation from R's lm when using a product, I am starting a new thread for this question. I have a model $\widehat{\log z} = a + bx + cy + dxy$ for random ...
0
votes
0answers
10 views

What are, in the r function glm, the families “quasi” and “inverse”? [migrated]

The glm function in R takes a "family" argument, which can also be set to "quasi" or "inverse". I couldn't find anything in the docs...
0
votes
1answer
37 views

What is the z-value of glm model parameters?

I know what the z-value of a single observation is, that is explained in Wikipedia. But what is the z-value of a parameter in a glm model?
1
vote
0answers
14 views

error structure in Generalized linear models when y is continuous data and errors not normally distributed

Lets say I have continuous y and x variable and I run a linear regression: mdl1<-lm(y ~ x) A generalised linear model should also give me the same parameters ...
0
votes
0answers
11 views

How to obtain VIF values for independent predictors used in a loglinear poisson generalized linear model?

The correlationmatrix shows that some of my predictors are correlating (Pearson, 0,288 0,492 and 0,360) I think it is useful to have additional information to decide whether this is acceptable or not. ...
1
vote
0answers
8 views

Analysis of proportional data (Two-factor design)

I did an experiment looking at damage to marine organisms as a result of fishing. I sampled in three vessels A, B and C. In each vessel I sampled the catch before on-deck handling (Pre) by fishermen ...
0
votes
0answers
20 views

Correlation between independent variables in Generalized linear model

short intro: I wish to explain seedling abundance in a savanna ecosystem with two factors. one factor is 'canopy' which is either 0 (under a tree) or 1 (not under a tree). the other factor is distance ...
1
vote
0answers
22 views

fitting an exponential decay onto a regression line

I have data for adherence to medicines which follows a downward linear trend for about 6 months (from 100%) and then plateaus at about 50%. Another way of describing it is by saying that adherence ...
0
votes
0answers
13 views

Printing all glm coefficients in R [migrated]

How do I print glm coefficients for all factor levels, including reference level? summary(glm_obj) prints only the values that deviate from reference values. I know that those are 0's, but I need ...
1
vote
0answers
20 views

glm or glmm model with unequal variance

I am applying a GLM model with binomial family: glm(response ~ Treatment, family = binomial, data=dat) The only explaratory variable treatment is a categorical ...
1
vote
0answers
23 views

How to report log linear models of contigency tables

I am using log linear models (loglm function, library MASS of R) to evaluate if 3 variables ...
0
votes
0answers
40 views

Tukey for GLM can't find data in model

I fit a GLM to a dataset. Now I want to see where the difference between my groups is, so I tried to run a Tukey HSD as a post-hoc test. Because of it is a GLM, I can't use ...
0
votes
0answers
14 views

Fisher Scoring v/s Coordinate Descent for MLE in R

R base function glm() uses Fishers Scoring for MLE, while the glmnet uses the coordinate descent method to solve the same equation ? Coordinate descent is more time efficient than Fisher Scoring as ...
0
votes
0answers
21 views

In linear regression the prediction error range is increasing while the the mean of the error is decreasing

I conducted a linear regression on a large and highly skewed data set that contain 80 variables,about 1.0 Million of users that didn't spent money and about 15k of users that spend different amount of ...
1
vote
0answers
20 views

Methods to analyze a cross-over interaction between a factor and a continuous variable?

I'm wondering what would be the best method to analyze a "cross-over" interaction between a factor and a continuous variable. Here's my experimental set-up and hypotheses in a nutshell: 58 ...
6
votes
3answers
148 views

GLM with data piled up at zero

I am trying to run a model to estimate how well catastrophic illnesses such as TB, AIDS etc affect spending on hospitalization. Now I have "per hospitalization cost" as the dependent variable and ...
4
votes
1answer
135 views

GLM analogue of weighted least squares

The short version: I can fit a model using Weighted Least Squares, given a diagonal matrix of weights $W$, by solving $(X^TWX)\hat{\beta}=X^TWy$ for $\hat{\beta}$. Is there a GLM analogue? if so, ...
-2
votes
0answers
18 views

how to test for fit of model for zeroinfl() models in R [on hold]

I have got two models using zeroinfl(). How do I find out which one is better since the summary() does not return a AIC value.
4
votes
1answer
41 views

Estimating Poisson process intensity using GLM

Suppose I want to build an explanatory model for events generated by an inhomogeneous Poisson process with unknown intensity $\lambda$. Each entry in my dataset represents the registration of an ...
1
vote
0answers
19 views

How to model a multiplicative effect of a parameter

I am having difficulty in fitting a model on data. Basically, I have data about the evaluation of phenotypic property (i.e. hard) of 65 palm trees by 5 judges. As an evaluation scheme, each judge ...
1
vote
0answers
9 views

SPSS GENLINMIXED for crossed groups

thank you for any help you might offer. I have data in which the groupings are crossed, not nested. Each player responds to the same set of items. In MIXED, I give a separate intercept to each ...
1
vote
1answer
36 views

How to promote a regression tree over a GLM?

Does anybody have any suggestions about promoting the use of a regression tree over a GLM when the two models fit the data almost exactly the same? My team's current arguments are a) a tree is ...
2
votes
1answer
62 views

Generalized linear model: link function Power(-1)

During study our of statistics in my psychology coursework, we had to teach ourselves how to use generalized linear models in SPSS (only basic knowledge). For an exam we may also use generalized ...
0
votes
0answers
25 views

GLM with multiple categorical variables in R : how to interpret the result?

I have a binomial variable that I regress against different categorical variables which I have contrasted to build a reference of an individual Female, Married, aged 35-45, High education : ...
3
votes
2answers
171 views

What is the justification for unsupervised discretization of continuous variables?

A number of sources suggest that there are many negative consequences of the discretization (categorization) of continuous variables prior to statistical analysis (sample of references [1]-[4] below). ...
4
votes
1answer
304 views

Why do we use GLM?

I'm trying to justify using of GLM model in my project instead of a simple linear regression. A lot of sources that I've seen contain the statement that "GLM allow us to build regression models for ...
0
votes
0answers
18 views

What are the best criteria to select the model for Lasso regression?

I have two different formulations of the Lasso regression for the same problem. For each formulation, I selected the best model based on cross validation error. But Now, I want to compare two models ...
1
vote
0answers
45 views

Poisson regression on the means of count data

I just finished a small research project about hummingbirds and the effect of hummingbird feeders. I am a bit unsure about how to proceed with the statistics. We placed 15 points in a distance ...
0
votes
1answer
35 views

Cluster analysis on time series samples

In the follow-up to this Ways to understand 2-dimensional time-series data I'm working on 2D time series data where two attributes are depth and temperature. When I plotted depth-vs-temp curve and ...
3
votes
0answers
56 views

How to create appropriate number of data points that would be accurate enough for creating regression equations?

I found a similar question in this forum. As a rule of thumb, since there are 4 independent variables in my case, I need 4*10=40 data points. However, my question differs slightly, since I want to ask ...
-2
votes
1answer
35 views

Predict y value from glm for a x vector larger than data used in the model [closed]

I have fitted a Poisson regression model using, model <- glm(y ~ x, family = "poisson", data = df) where length of df is 50 ...
1
vote
0answers
32 views

Left skewed distribution implementation generalized linear model

I am very new to modelling and I have a question. I am using a generalized linear model (glm) for my data in R. My response variable is however skewed to the left ...
1
vote
2answers
77 views

Ways to understand 2-dimensional time-series data

I'm working on 2D time series data where two attributes are depth and temperature. When I plotted depth-vs-temp curve and saw its variation over time, the fluctuation occurs at few places only. I'm ...
0
votes
1answer
35 views

What are appropriate tests for goodness of fit on glm with a small sample size?

I've thought quite a lot on large sample size inference where the strong law of large numbers is easily validated. In my case however, I'm trying to infer the sign and magnitude of an outcome where ...
1
vote
1answer
35 views

Why does a binomial glm give negative predictions?

I'm using count data in quite a simple way, but I cannot understand how a binomial glm can return negative predictions example code, where count of successes increases with responce variable: ...
2
votes
1answer
40 views

“Zero-inflated continuous covariates”, Can they cause problems in logistic regression?

I pose a very similar question to this, although I felt the advice given does not apply to my particular situation; I am using logistic regression models for an animal habitat occupancy study, and ...
3
votes
0answers
60 views

Generalized linear model with lasso regularization for continuous non-negative response

I have a big data problem with a large number of predictors and a non-negative response (time until inspection). For a full model I would use a glm with Gamma distributed response (link="log"). ...
0
votes
0answers
18 views

GLM poisson regression and some independent variables are itself poisson distributed

How can we deal with in GLM regression, when some variables of the independent variables (the x) are itself poisson distributed? Suppose we have two random poisson distributed variables X,Y with ...
1
vote
0answers
33 views

Reporting generalized linear model results

I am looking for help phrasing/reporting the results of a Generalized Linear Model. I have received some feedback that my current format is difficult to understand. I have multiple predictor variables ...
1
vote
0answers
23 views

Model averaging effect sizes of Gamma family GLMs

I'm trying to get some model averaged effect sizes from a set of candidate models, all of them assuming a Gamma error distribution, according to the theory given by the book from Burnham and Anderson ...
1
vote
0answers
47 views

Creating observed/expected ratio using logistic regression

I am using logistic regression to benchmark the performance of some students in different years. I created a scenario as below: ...
0
votes
0answers
16 views

Question about Dummy Variable in Cross Level Interaction - GENLINEMIXED (SPSS)

Hi I am running linear GENLINEMIXED in SPSS 22. What does it mean when one of the dummy variables you are using in a model is significant when one group is coded as a reference group, and when you ...
0
votes
1answer
31 views

Post-hoc after GLM

I am running a GLM, using the function glm.nb (pscl package) trying to figure how what could influence a particular trait in several locations and years. The output as follow (with slight modification ...