Questions tagged [generalized-linear-model]

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 multivariate response.)

Filter by
Sorted by
Tagged with
-1
votes
1answer
17 views

Which statistical test to use in r when having different groups from different labs

I have counts coming from 7 different groups. Every of this count has been measured twice in two different labs. I want to see if in general lab 1 and lab 2 have statistically different results. This ...
1
vote
0answers
10 views

Checking for autocorrelation

I would like to check my GLM model for autocorrelation - I am wondering for Poisson, Negative Binomial and Binomial GLMs whether to use the deviance residuals or the Pearson residuals? This is how I ...
3
votes
1answer
64 views

GLM on non-integer data

I'm looking for a recommendation on what GLM I could do with non-integer data. Brief background of what I am doing: I'm wanting to combine calculated herbivory rates with abundance data, to compare ...
0
votes
0answers
7 views

compare two GLM models on test set using deviance reduction with offset prediction

I'm trying to compare the goodness of fit of two GLM models of claims frequency, one "baseline" and one with some more variables we recovered from external sources. The approach I'm following should ...
0
votes
1answer
27 views

Is GLM with one continuous variable of 4 levels a nested model of GLM with 3 dummy variables?

Y is just a binary variable 0 and 1. X is a variable with 4 levels 0, 1, 2, 3. We fit a logistic model A regarding X as continuous variable. Then we fit a logistic model B regarding X as categorical ...
2
votes
1answer
56 views

How to handle strongly correlated but not perfectly collinear dummies

I am using several dummy variables in a GLM model implemented in R with a logit link function. However, the coefficient of one of the dummy variables is not shown in the results with the warning ...
0
votes
0answers
19 views

Is there a hypothesis test that tells us whether we should use GAM vs GLM?

Is there a hypothesis test that's ideally uniformly most powerful or metric that tells us whether we should use GAM vs GLM? Does there exists some kind of metric i.e. AIC/BIC or loglikelihood to ...
0
votes
0answers
14 views

Combining PCAs group of variables

So I want to Research the importance of 6 Group of variables on my dependant variable. I have ~50 variables in 6 Groups (which i Need to keep for my hypothesis). I did a PCA on each Group of Variables ...
-1
votes
0answers
28 views

Multiplicative parameters in linear model [closed]

Suppose I have a linear model: $$ y_i = \sum_{j=1}^{p} \beta_{j} x_{ij} $$ Having $p$ variables, and $n$ samples. Moreover, predictor variables considered can be divided into two groups, where ...
0
votes
1answer
29 views

The identity link not used for binary response

Questions: The identity link is the standard one with normal responses but is not often used with binary or count responses. Why do you think this is? My idea: The range for a linear predictor, and ...
0
votes
1answer
20 views

Big outlier in dependent variable

I have my data from the official statistics office of my country and I rechecked multiple times already. I have a big outlier skewing all my glm (poisson) modells to the extreme (like 5 times the ...
0
votes
0answers
12 views

Conditional bar in the regression formula (in R) [closed]

When it comes to modeling a regression through R, I am seeing something like the following expression with a conditional bar (1|) often: ...
2
votes
1answer
55 views

Likelihood ratio, Wald, and Score are equivalent?

In Foundations of Linear and Generalized Linear Models, Agresti makes a comment on page 131 about likelihood ratio, Wald, and Score testing of regression parameters. For the best-known GLM, the ...
0
votes
0answers
10 views

Global test of the hypothesis, and ANOVA

I am trying to analyze the following results for the house selling price data. My questions are: a. How can I interpret the results of the global test of the hypothesis that none of the explanatory ...
0
votes
0answers
17 views

How is the classic Dunnett test, with strict assumptions, related to Dunnett comparisons run on a top of very liberal models, like GLM or GEE?

As far as I understand, the classic Dunnett test is based on the t-test, applied multiple times to all comparisons vs. control and then corrected. So the assumptions of the Dunnett test must agree ...
0
votes
0answers
14 views

How is the classic Dunnett test, with strict assumptions, related to Dunnett comparisons run on a top of very liberal models, like GLM or GEE?

As far as I understand, the classic Dunnett test is based on the t-test, applied multiple times to all comparisons vs. control and then corrected. So the assumptions of the Dunnett test must agree ...
1
vote
0answers
41 views

Proper Average Treatment Effect estimators (and standard errors) for Generalized Linear Models with log link?

What is the proper formula for estimating the Average Treatment Effect with a simple main effects generalized linear model? My first pass at defining the Average Treatment Effect for a GLM with a log ...
0
votes
0answers
13 views

For the house selling price data, interpretation of the ANOVA and lm

I am trying to analyze the following results. My questions are: a. How can I interpret the results of the global test of the hypothesis that none of the explanatory variables has an effect? b. ...
0
votes
0answers
8 views

Calculating Log2 Fold Change from Regression Model

I'm reading through Chapter 8 of Modern Statistics for Modern Biology and I'm having trouble understanding the exact computation that goes into estimating the $log_2$ fold change between 2 conditions. ...
0
votes
1answer
42 views

GLM - Interpret residuals vs fitted plot

I realised a within-subject experiment and each participants went through three conditions and in each condition they performed a series of tasks of their choice (number of tasks is different for each ...
1
vote
0answers
12 views

Degree of Freedom of Null Model in Logistic Regression

I built a logistic regression in R using 6 predictor variables and the output is as shown: ...
2
votes
1answer
42 views

May “offsets” be used in mixed-effects poisson regression?

Mixed-effects poisson regression studies counts for example of the incidence of a disease given the individual's random-intercept/slope. Mixed-effects regression studies individuals rather than ...
0
votes
0answers
10 views

Linear discriminant analysis accuracy issues

I have generated a normally distributed sample along with 3 classes to perform classification. I got very low accuracy. I was wondering if you could give me your valuable feedback to improve my LDA ...
0
votes
1answer
27 views

When using a gaussian link in GLM, what are the assumptions?

In R, when I am fitting a model glm(y~x, family = gaussian(link="log")), do I assume that $Y \stackrel{iid}\sim N(\mu, \sigma^2)$ or do I assume that $Y \stackrel{...
0
votes
1answer
29 views

Explanation of the model used in the following glm commands

In my textbook, the following two models were used. I understand the theory of glms, but I'm not too sure as to the specifics of the options and parameters you can play with in the R glm function. I ...
0
votes
1answer
44 views

Generalization for poisson regression

I will really appreciate if anyone could help me to find correct reference about the following problem. Assume we have some observations with respect to, two variables $t$ and $p$. But we don’t have ...
0
votes
0answers
27 views

Estimating coefficients of a large categorical variable

I'm trying to fit a GLM model with a categorical variable with 400 categories, and I'd like to reduce the number of categories. There are some categories with a lot of data, and a lot of categories ...
1
vote
2answers
33 views

Negative Count Variables in Data — modeling migration

I'm trying to explain migration rates in Europe with my regression using pca/pcr in glm. Of course some of the count data has to be negative in regions people move out of. This presents a problem for ...
0
votes
1answer
49 views

Repeated Measure ANOVA, GLM,GEE, Linear mixed model, Generalized linear mixed model?

I have a table like below (it is a small subset of my data. In this table, I measured one variable over 4 different time points (T1,..., T4), now I would like to check is there any significant ...
0
votes
0answers
6 views

geeglm giving error “incompatible types (from language to character) in subassignment type fix” [migrated]

I have a problem using geeglm form the geepack library. I don't understand what is wrong: ...
1
vote
0answers
46 views

Regression model with (almost) non-negative residuals

I would like to fit a regression model with continuous response and predictors. A fraction of the response is a non-negative linear combination of several predictors. What is not covered by this ...
0
votes
1answer
56 views

Confusing results from lsmeans and pairwise tests

Experiment: I collected data from N participants, each was shown 50 photos and asked to provide sharing likelihood (dependent ...
2
votes
1answer
49 views

Do good Cross-Validation results imply good QQ-plot results?

In Edward Frees' book Predictive Modeling Applications in Actuarial Science, Volume 2 the first chapter goes over how to build a frequency GLM model (using a Poisson distribution) on sample auto-...
0
votes
1answer
26 views

How to interpret goodness of Fit of GLM with gamma?

I'm using SPSS to create a model of y (dependent variable: 0,11;0,234;0,2324) and five independent variables. I get the following results: ...
1
vote
0answers
19 views

Which model fit best colinear indepent variables?

I have one dependent variable ($y$) and $200$ linear independent variables. However, some of them are related (exists multicollinearity). Therefore, I can't use multivariable linear regression. I ...
5
votes
1answer
62 views

Is there a bootstrap 're-sampling the residuals' equivalent for GLM?

In linear regression, I have read of a non-parametric bootstrap being done by 're-sampling the residuals (errors)'. The general idea being that you perturb the mean response by simulated values of the ...
0
votes
1answer
19 views

How to handle potential ambiguity when one-hot encoding?

Let's say I have two categorical features: Movie, Director. I one-hot encode both the Movie and Director features for use in a linear regression model. The problem is that two or more movies may be ...
0
votes
0answers
31 views

Predicted probabilities very close to 0 and 1 in GLM model

I've added new attributes to the binary GLM model. AUC climbed to 98%, logistic loss decreased to 0.45. Training set has ~50 cases. I can see that predicted probabilities are extremely close to 0 and ...
6
votes
1answer
279 views

How to show that a random factor is not needed in the model?

I collected data from an experiment where I showed one of four videos (condition) to a person and asked them to predict how it ended / assign one of three labels to ...
0
votes
0answers
11 views

Time series analysis video resources

I am kinda new in Data Science. My background is in Mathematics. I took some graduate-level statistics courses like the generalized linear model. I am interested to forecast future student enrollment ...
0
votes
1answer
30 views

How to improve the fit for a GLM model?

I am fitting a glm model to examine associations between some predictors and a 3-levels outcome variable (see data below): ...
0
votes
1answer
15 views

Model validation with GEE-GLM

I am trying to find some resources on model validation for GEE-GLMs. Unfortunately I can't afford to purchase expensive textbooks and many of the books address GEEs using other software such as Stata. ...
0
votes
0answers
16 views

Count data: Linear model vs generalized linear model

To play a little bit with GLMs, I tried this simulation: I generated a variable $x$ with two levels, $A$ and $B$. I generated a variable $y$ by drawing from a Poisson distribution with parameter $0.1$...
1
vote
1answer
30 views

Generalized linear model: variance vs mean

I have just read this blog: Linear Models, ANOVA, GLM etc The author tries to explain in which situations it is better to use a generalized linear model instead of linear regression. At a certain ...
2
votes
0answers
31 views

ANCOVA: Measured weight of 5 participants 5 times on 3 different weight scales. Should I use participant ID as a covariate?

I measured weight of 5 participants, 5 times each, on 3 different scales accurate to 5 places after decimals. In total, I took: [5 participants] x [5 times each] x [3 different scales] = 75 ...
0
votes
0answers
16 views

GEEs and GLMs: what can I do about the auto-correlation?

I want to run a model that somehow incorporates temporal autocorrelation. I have a dataset which consists of the minutes of Species A vocalizing at a single site. This is data recorded continuously ...
0
votes
0answers
11 views

How can I group my factors for post-hoc test in Minitab?

I've recently been using R for my data analysis, but was struggling so I've turned to Minitab for the first time. The data I'm using can be seen here - Is it possible to do a post-hoc test on a ...
0
votes
0answers
26 views

Differences between ML Type I, and ML Type II, and full Bayesian inference?

Can someone please point me to a good note (or tutorial) that explains the difference between the three common types of statistical inference techniques: (a) ML Type I estimation, (b) ML Type II ...
1
vote
1answer
33 views

Non-independence in data and GLMMs

I am working with a dataset that consists of categorical variables and count data. My response variable is DPM SpeciesA (detection positive minutes of Species A, where for each hour I have a count of ...
0
votes
0answers
8 views

What is the name of this design/model? (Age-period-duration, Lexis cells)

We have an observational study of the relationship between diabetes and cancer. In order to handle multiple time scales, we use Lexis cells as observational units, i.e. a row in our data set as ...

1 2 3 4 5 61