Stack Exchange Network

Stack Exchange network consists of 175 Q&A communities including Stack Overflow, the largest, most trusted online community for developers to learn, share their knowledge, and build their careers.

Visit Stack Exchange

Questions tagged [poisson-regression]

Poisson regression is one of a number of regression models for dependent variables that are counts (non-negative integers). A more general model is negative binomial regression. Both have numerous variants.

0
votes
1answer
7 views

Scoring rules for count models on: training data vs. validation data

In order to evaluate and compare count models (e.g. Poisson regression), we can calculate scoring rules (e.g. Brier Score, Dawid-Sebastiani score, etc.) which are explained here: Error metrics for ...
0
votes
1answer
12 views

Modeling Opioid Mortality Rates using Poisson Regression

This is a general statistics question about Poisson Regression. I have age-adjusted and crude rates for opioid mortality for the period 2014-2016. I want to use Poisson regression, but I am not sure ...
0
votes
0answers
10 views

Modeling count data (left skewed, underdispersed, right-censored)

I am seeking to model a count response variable-- number of times subject enacted a compensatory behavioral strategy-- as a function of cognitive and behavioral symptomatology, which are both ...
0
votes
0answers
8 views

Including or excluding a variable and what about the p-values when VIF = 5.2?

I'm writing my master thesis and run into a question about multicollinearity. I have two interaction effects which have a high VIF (5.2, 4.8). Both are interaction effects between categorical ...
0
votes
0answers
14 views

Can I use Poisson regression to model prevalence ratios if I only have information on events?

I often used Poisson regression models to estimate prevalence ratios. However, in these cases my data contained information on the whole population, including events (1) and non events (0). ...
1
vote
1answer
24 views

Comparing assault rates at one facility with two other facilities

Assaults on staff are fairly uncommon in our facilities with between 70-140 in a year at a given facility. Time, similar to 'person years' in epidemiology, is tracked as 'number of bed days' (i.e., ...
-1
votes
1answer
13 views

Interpretation of regression tree with Poisson data

Above is a decision tree made by following code ...
1
vote
1answer
17 views

Sum of two poisson regression on the same predictor

I have two Poisson regression models using same single feature. Model 1 is $$E[\log(y)| x] = a_1 + b_1 \log(x)$$ and Model 2 is $$E[\log(z)|x] = a_2 + b_2 \log(x) $$ When I build Model 3 on $y+z$...
0
votes
1answer
36 views

Exposure/offset variable in Poisson regression with many fixed effects

First time here on CrossValidated! My question concerns the inclusion of an offset variable in a Poisson regression. I have panel data and my outcome is 'count' distributed. My cross-sectional unit ...
1
vote
0answers
14 views

Confidence interval of Poisson distributed MLE using chi squared

There is a variable distributed as $X$~Poisson$(X_0 e^{-\lambda t})$. The value of $\lambda$ was estimated through maximum likelihood by fitting to the data $t=0,1,2,3,4$ and $X=[5000,3000,100,10,1]$. ...
0
votes
0answers
39 views

Inexplicable bad estimation in a Poisson regression (GLMM)

I need to use a Poisson regression to obtain the equivalent of a piecewise exponential estimation for the survival curve. So far so good. The problem occurs when I add a covariate to my time variable....
3
votes
0answers
91 views

Nonnegative identity-link Poisson regression with ridge or fused ridge penalty

I would like to fit nonnegative identity-link Poisson regression models with a ridge or fused ridge penalty, i.e. with nonnegativity constraints on the fitted coefficients, Poisson error noise & a ...
0
votes
0answers
18 views

Using log data with censored Poisson regression

I am trying to minimise a likelihood function and estimate the parameter value of $\lambda$ by fitting to the following data. $t$ is the time and $N(t)$ is the population measured at those specific ...
0
votes
0answers
10 views

Comparison of paired count data between two treatment periods with different length of follow-up

I am currently using SAS 9.4 to carry out a retrospective analysis of patients who switched from drug A to drug B. I am interested in assessing the hospitalization counts before and after switch to ...
0
votes
0answers
33 views

Is my data inappropriate for a zero-inflated regression model?

I am working with count data where I have an abundance of zeros for one of my categorical factors (Day). I have generated two models, p1 and m1, with zeroinfl() and ...
2
votes
3answers
46 views

Modelling count data with time-series structure and predictors

I am doing an analysis of sales-data over a period of time (i.e. over a few years). Those sales-data are also dependent on some predictive variables (i.e. holiday, weekend, weather,...). The daily ...
1
vote
1answer
23 views

Why do I get so different estimations with glm and glmer?

I am using the glmer function (lme4 package) to get estimations in a Poisson regression model (generalized linear model). I ...
0
votes
0answers
15 views

Calculating the confidence interval for an incident rate ratio for a continuous spline variable from a Poisson GLM

I have a rather large and complicated Poisson GLM with a mix of categorical (many binary, yes-no) and continuous values. To calculate the incident rate ratios (IRR) for the binary variables, I simply ...
0
votes
0answers
10 views

Interpretation of average marginal effect for proportion outcome in Poisson model with offset

To see the association of malaria prevalence with village level risk factors, I ran a Poisson model in r with the prevalence of malaria(y) as a dependent variable, altitude(x1) and Forestation(x2) as ...
0
votes
0answers
75 views

Poisson Regression in R with individual fixed-effects and month/year fixed-effects

I'd like to use a fixed-effect Poisson Regression model to examine whether opting into 2 different schemes (specified as dummies in my model) can lead to increased exercise. I have longitudinal data,...
0
votes
1answer
14 views

comparing incidence rate

I have a data set of individual level data for the outcome in question. I also have aggregated data (at a national level) from which I'm obtaining the denominator. Using this information, I've ...
0
votes
0answers
18 views

Use MSE in cv.glmnet for Poisson models?

I want to compare different methods (like Poisson regression using Lasso, a convolutional NN, etc.) in terms of prediction error. As error measures I chose the MSE, the MdAPE (median absolute ...
0
votes
1answer
52 views

Zero-inflated vs not Zero-inflated models for count data

I am analyzing a small dataset (d) of urinary track infections in a group of residents of a long-term care institution over a period of 6 months. The total number of patients was 29. I had used ...
1
vote
1answer
23 views

Why is Gausian better then Quasi Poisson on the validation set while not on trainingset?

So we have a regression challenge here in which the dependent variable looks like this: It is overdispersed as mean = 10 and variance = 60 so we think quasi-poisson is best? We use the glm() ...
0
votes
0answers
31 views

Are fitted.values available in pglm?

I am using the pglm function in R to fit a Poisson fixed-effects model. According to the documentation, the pglm object should have fitted.values. However, fitted.values(model-name) returns "NULL". ...
0
votes
1answer
52 views

Is the methodology for my undergrad dissertation sufficient - should I use a hierarchical negative binomial model instead, despite beginner ability?

As said in the title, I know almost nothing about statistics. My hypothesis for my dissertation is that UK Members of Parliament with a larger margin of victory will do less work than those with a ...
2
votes
2answers
52 views

Poisson model appears overdispersed, but usual recommended approaches don't improve fit

Summary: I am trying to model some count data. I initially attempted to fit a poisson GLM, but diagnostics appear to indicate overdispersion. I have tried several different recommended remedies but ...
0
votes
0answers
17 views

Does it make sense to compare Cooks distance between two models

If I have a greater amount of observations that high values of Cooks distances in one model than another does that suggest that the model is not as suitable? For example, here ...
0
votes
0answers
27 views

Centering / standardizing leads to very different results for GLM (logistic, poisson, negative binomial distribution)

I have a dataset with count data and around 1 million observations. My regressions contain around 40 variables (binary and continuous) and 10 thousand fixed effects. I analyze this dataset with linear,...
0
votes
0answers
45 views

Why does pglm give different results thans log-plm?

I'm looking to regress a fixed-effects model on count data. My initial approach was to take the log of regressor on R's plm package. Then I found out about the pglm package, which enables general ...
0
votes
0answers
38 views

Poisson regression with continuous data [duplicate]

I have a time series of floating numbers, say, 0.1, 0.5, 1.1, 0.6, 2.0, 1.4, 0.4 Now, I would like to model this series with Poisson regression, since the numbers, even though they seem ...
1
vote
1answer
35 views

mixed effect model?

I have 365 days of bike sharing demand data for 15 stations. I am thinking of taking each day data as a data point (n=365*15=5475) and relate daily weather variable as well as land use variable. The ...
0
votes
1answer
20 views

Formula for deviance residuals for Poisson model with identity link function?

I understand the deviance residuals $r_D$ for a Poisson GLM with log link function are given by $r_D = \mu_{ij} \log(\mu_{ij}/\hat{\mu}_{ij}) + (\hat{\mu}_{ij} - \mu_{ij})$ I was wondering though ...
1
vote
0answers
21 views

Poisson Regression vs. Exponential_Weibull vs. Cox Regression vs. Negative Binomial [closed]

Problem: I would like to predict the number of days a student continues with school using student and school level covariates (no censor data). Data includes the number of days that the student ...
1
vote
0answers
57 views

How do you stratify a Poisson regression in GLM?

I would like to obtain a stratified baseline hazard in a Poisson regression model. What is the correct way to do it ? Let A (=0/1) be the binary covariate on which I wish to stratify my baseline ...
0
votes
0answers
26 views

POISSON REGRESSION AND OFFSET VARIABLE [duplicate]

I am using a Poisson regression model with a count data. More specifically, my dependent variable is the number of children dead. My feeling is that I could use a Poisson model with an offset ...
0
votes
0answers
34 views

Interpretation of Conway Maxwell Poisson regression coefficients

For a simple Poisson regression, I would interpret the coefficient as (1-exp(coef))*100 for percentage change in y given a unit change in x So for a Conway-Maxwell Poisson regression, Sellers and ...
1
vote
0answers
29 views

Modeling daily purchase events / website traffic, time series or independent events?

I've been thinking about how best to model sequential events like purchases on a website, or website traffic. I'm curious if people think this is best modeled as a poisson process (or something like ...
0
votes
0answers
38 views

Visualising Generalised linear models

I read about linear regression where we assume, the response is linear and the noise $\epsilon$, follows $N(0, \sigma^2)$ (Gaussian noise model), this leads us to conclude $E[Y|X] = b^*x$ and that the ...
0
votes
0answers
38 views

How do I model count data (Poisson regression) that has a seasonal pattern?

I'm rather new to R and poisson regression and have a few questions. I have count data of incidents per month, a couple years prior to an intervention and 1 year after. I want to use poisson ...
0
votes
0answers
9 views

Variable selection in Bayesian spatio-temporal count regression

I am estimating a Bayesian spatio-temporal Poisson model. I have a relatively large set of explanatory variables (20ish) and each time I run the model it takes a few hours to complete. I have seen ...
1
vote
1answer
48 views

Residuals still zero inflated after running zero-inflated poisson mixed effect model with glmmTMB

I am working with observational data which has a right skew in the dependent variable. This is a mixed effect model with a poisson distribution as based on discrete data. After finding the residuals ...
1
vote
0answers
27 views

Statistical analysis for quasi-experiments

This is my first message on this forum. I hope I am not doing any mistake. I must analyze data obtained after a quasi-experiment and I am not sure how to proceed. The experiment has been carried out ...
2
votes
0answers
37 views

Contradiction between zero-inflated poisson model coefficients and graph of the model?

EDIT: Added an reproducible example For one of my models, it seems the coefficients and the graphed out model do not agree. I'm working with adverse effects data, in which intense reactions are rare ...
13
votes
2answers
540 views

Are over-dispersion tests in GLMs actually *useful*?

The phenomenon of 'over-dispersion' in a GLM arises whenever we use a model that restricts the variance of the response variable, and the data exhibits greater variance than the model restriction ...
0
votes
0answers
16 views

Spatio-tempral Bayesian Poisson model convergence investigation

I am fitting a spatio-temporal Bayesian Poisson model with 22 explanatory variables, an offset variable, 2200 observations and non-informative priors. I am using the package ...
0
votes
1answer
42 views

Which regression used for normalized count data

I am working with social network data. I have multiple networks of various sizes and I'm calculating indegree (the number of connections between people) in each of the networks. I've been told to ...
0
votes
1answer
37 views

How to isolate the effect of dichotomous predictor?

I want to isolate gender differences in preferences for a particular attribute of a product based on data available about their product purchases. I understand that I have to use a mixed Poisson ...
0
votes
1answer
18 views

Fitting a (maybe Poisson) regression to my data in R

I'm trying to understand the probability distribution for my data. Each point represents an individual patient, the 0 or 1 label indicates whether they have a particular disease, and the number of ...