Variables that are counts (non-negative integers) often have an excess of zeroes. Zero-inflated regression models (e.g. zero inflated Poisson, zero inflated negative binomial) are designed to deal with this. Less commonly, continuous data can have this issue, and there is zero-inflated normal ...

learn more… | top users | synonyms

0
votes
0answers
10 views

How to mitigate risks for an oversampled training and validation set for a Zero-Inflated Poisson model?

I have a data set, with training, validation, and test already decided for me. It is a mailing list response project so it has a lot of zeroes representing no response, and some ones representing a ...
0
votes
0answers
8 views

How to improve the fit of a zero-inflated, negative binomial glmmADMB model

I have been trying to fit count data that is zero-inflated and overdispersed using generalized linear mixed models. My research led me to the glmmadmb function in the glmmADMB package. I am fitting ...
0
votes
0answers
3 views

How to interpret negative fractional incidence risk ratio?

I'm using a Zero-Inflated Poisson regression to model a count outcome with lots of zeroes. However, I'm having trouble understanding estimates in the count model that are both negative and smaller ...
0
votes
0answers
15 views

Estimating unconditional effects in double hurdle models

I trying to implement a double hurdle model in JAGS and am struggling to understand how to estimate the unconditional effects of each predictor variable on the count process. I have implemented the ...
1
vote
1answer
17 views

How to calculate variance contribution in a Zero-Inflated Poisson regression?

I was wondering if anyone has an idea on how to calculate the contribution to variance of each independent variable in a Zero-Inflated Poisson. How would it even work if you actually have two models ...
0
votes
0answers
4 views

Glm planned comparison fail to compare identical samples

I am dealing with several treatments, binary dependent variable and lots of zeros. When running a glm with pairwise comparison the model fail to compare two different treatments that have actually ...
0
votes
0answers
20 views

Double Hurdle model with continuous DV and two sources of zeros

I want to regress a data set that contains a lot of zero's (~55%) and is determined by a typical 2-stage decision process generating the zeros: Consumer decides to apply for a bank loan or not (0-1) ...
0
votes
1answer
63 views

Help with zero-inflated generalized linear mixed models with random factor in R

My study has a complicated design and I am not sure if I am modeling my zero-inflated data correctly. I have seed abundances and seedling abundances for 11 species. I have one main "treatment" with ...
1
vote
0answers
48 views

zero-inflated negative binomial in Stata

I am trying to run a zero-inflated negative binomial analysis in Stata (zinb). My question/problem is this: the model's convergence seems dependent on which and how ...
1
vote
0answers
30 views

Zero-Inflated Poisson Regression – Warning message: In sqrt(diag(object$vcov)) : NaNs produced

I'm trying to model the following data: using zero-inflated poisson regression: model <- zeroinfl(dv ~ c1 + c2 + session | participant, data = dat) where ...
1
vote
1answer
45 views

ZIP Fit Indices Calculated from an EM Algorithm

I am working through @ben-bolker's owls example available here:https://groups.nceas.ucsb.edu/non-linear-modeling/projects/owls/WRITEUP/owls.pdf In particular, I am making use of the R ...
0
votes
0answers
46 views

Zero Inflated Versus Negative Binomial Models Conundrum

I have a count variable that represents the number of new band foundings in a country-year. However, there is zero inflation as there are no foundings for most country-year. There is also ...
2
votes
0answers
43 views

Measure of “deviance” for zero-inflated Poisson or zero-inflated negative binomial?

Scaled deviance, defined as D = 2 * (log-likelihood of saturated model minus log-likelihood of fitted model), is often used as a measure of goodness-of-fit in GLM models. Percent deviance explained, ...
0
votes
0answers
23 views

Dealing with sampling zeros

I would like to perform a $\chi^2$-test, but due to low sample size in some cases, I have sampling zeros. One example of such a case: ...
0
votes
1answer
41 views

Rules for Percentage of zeros in a zero inflated model

What percentage of zeros in the data should make us consider trying the sequence of models: Poisson -> Negative Binomial -> Zinf-Poisson -> Zinf-Negative Binomial, etc? I have two datasets with about ...
0
votes
1answer
54 views

Calculating OR and IRR for a zero-inflated negative binomial model from estimates

I used the PSCL package to run a zero-inflated negative binomial model on some count data I have. This package gives the following output: for the zero part of the model: ...
1
vote
0answers
67 views

What is effect on PCA of having too many zeros in the data?

I want to use Principal Components Analysis to derive dietary patterns. However, my data have many zeros (no intakes) for many observations. I'm unable to find relevant literature to know how biased ...
0
votes
0answers
25 views

Gamma/ inverse.gaussian glmer with zeroes that matter

I'm trying to analyze continuous non-negative data with real zeroes that matter. The data are either gamma or inverse.gaussian distributed (from gamlss package) and ...
0
votes
0answers
21 views

How to model Zero-inflated count vector with random parameters?

I am trying to estimate a parameter vector $(\theta_1, \ldots, \theta_n)$ from a vector of observations $(y_1, \ldots, y_n)$ where $Y_i \sim Poi(\theta_i)$. The data is zero-inflated in the sense that ...
0
votes
0answers
22 views

Right censored data, abundant in zeros for regression analysis

I am looking at conditioning to stimuli and there in the time taken to perform a certain task. The IV for this data is Conditioning periods ranging from 1-34 periods and the DV is the time taken for ...
1
vote
1answer
70 views

Modelling zero-inflated continuous data

I'm currently trying to apply a linear model (family = gaussian) to an indicator of biodiversity that cannot take values lower than zero, is zero-inflated and is continuous. Values range from 0 to a ...
0
votes
0answers
21 views

SEM with zero-inflated outcome

I'm working on a project and my advisor wants me to do SEM in MPLUS because we can do latent modeling, but I have no clue where to start. I've only ever done regressions but I said I'd be up for ...
0
votes
0answers
90 views

Set G in prior for MCMCglmm in R

I am new to the MCMCglmm package in R, and rather new to glm models in general. I have a dataset of species traits and whether or not they have been introduced outside of their native range. I would ...
1
vote
1answer
44 views

Multicollinearity in Zero Inflated Negative Binomial Regression

I am trying to model counts govt, based on the counts lp,const,...
0
votes
0answers
39 views

Modeling with zero-inflation models for prediction

Below is the summary of my dataset: ...
1
vote
1answer
66 views

Prediction from Zero Inflated Models?

I have fitted a two stage generalized additive model to zero inflated data ("hurdle model"). I am modeling fishery spatial data (catch rates) as a function of different environmental variables ...
2
votes
1answer
45 views

Regression problem in data with many zeroes

This is my first question here, so please bear with me. I am working on a regression model to estimate the long term value of users of a certain website. For example, I would like to estimate the ...
0
votes
0answers
13 views

Regression coefficients versus marginal probabilities

I ran a negative binomial regression model and found significant coefficients for several key variables. I also ran the model as a zero inflated negative binomial model, and didn't find significance. ...
0
votes
0answers
60 views

How to model these data? (zero inflated, positive skew,

- The variable depicted in the histogram is a sum of 11 items. Each item asks about the frequency of occurrence of a particular type of event (a negative consequence of drinking) on the following ...
1
vote
0answers
25 views

Canonical Link Function in Zero-Inflated Poisson Model

For a zero-inflated Poisson model, I understand that the Poisson Model uses the canonical link of log(mu). For the logistic portion of the model, I usually see the equation written as logit(phi), and ...
0
votes
0answers
71 views

Zero-inflated Poisson regression Vuong test: Raw, AIC- or BIC-corrected results

I'm analyzing count data for a set of ten species and found that for the five species with highest detection rate, the zero-inflated poisson (ZIP) regression fits the data significantly better than ...
3
votes
1answer
73 views

Zero-inflated Poisson regression: how can I calculate contrasts for BACI (Before-after-control-impact) experiment?

I am analyzing count data with a lot of zeros and found that although the data do not fit a poisson glm, they fit the zero-inflated poisson (ZIP) regression significantly better than the standard ...
0
votes
1answer
38 views

Relationship between two zero-inflated counts varying in space

I have two variables where each observation represents counts at some point in a discrete 1D space (along an RNA sequence). The space is finite, and the counts are highly zero-inflated compared to a ...
0
votes
0answers
21 views

estimating probably of false zeros using ziP GAM

I pulled the code below from Zuur et al. 2009 (was used to estimate probability of false zeros with a zeroinf() model) and applied it to a ...
0
votes
0answers
28 views

Statistical Procedures in Heavy Zero Density Data

How do procedures such as Principal Component Analysis, Logistic Regression, Cross Validation perform under Zero under Zero Heavy Data? Are they sub-optimal or simply inadequate?
0
votes
1answer
48 views

Dual Quasi-Newton Optimization on Zero Heavy Data (in SAS)

I am using PROC FMM in SAS, in attempt to use hurdle models on a data set with many zeros. There is one response variable and it's continuous, there are ~90 predictors (continuous - but contain many ...
2
votes
2answers
231 views

Modelling Data with Many Zeros - Principal Component Analysis vs Zero Inflated Models

I have a data set (many continuous predictors, single response variable that is also continuous) with many zeros. I first used PCA and found the results to be very helpful. I further thought that the ...
0
votes
1answer
57 views

Zero-inflated models how to get predicted values = 0 stata

I'm fairly new at Stata and this is the main reason of my question. I did a longitudinal zero-inflated poisson model: ...
0
votes
0answers
16 views

zero inflated negative binomial versus earth to describe data

Hi is earth function in the earth package appropriate for zero inflated negative binomial data? Is the apparent exponential curve an artifact of erroneous application by me? Opinions very welcome. I ...
0
votes
0answers
49 views

How to manually calculate fitted values in zero count models?

I'm looking to see if I can manually calculate the fitted values for a Hurdle model (from the pscl package) to ensure I understand what's going on, but so far I ...
1
vote
0answers
69 views

Zero Inflated Poisson Regression in R

I have a zero inflated Poisson regression model I want to run R, as my data are over-dispersed and I have many zeros, but I am not sure how to set up the model in R and interpret the output. First, is ...
0
votes
1answer
137 views

Non-parametric test of difference for zero-inflated data

I have zero-inflated (~90% zeros) data which is distributed like the left-hand figure above (the right-hand figure shows how when log-transformed, the non-zero component of the distribution is ...
0
votes
1answer
71 views

How do you deal with overdispersion in a zero-inflated negative binomial regression AND when you expect data to have zeros?

Background: I am analyzing the effect of multiple variables (lineage, ancestral plant species, plant species reared from, larval density, body mass) on different traits: ovigeny index (initial egg ...
0
votes
0answers
65 views

Choosing between Zero Inflated Negative Binomial model versus Logistic Regression

Context: this is in the field of genome wide association studies. The norm in the field is logistic regression, but we have high quality radiographic data that gives us counts of damaged joints, so I ...
1
vote
1answer
68 views

linear mixed model on continuous, zero-trunctated data

I have a dataset with one continuous response variable (time), a 'treatment' explanatory variable and 5 other fixed factors: ...
1
vote
0answers
19 views

How to use ln-transformation with loads of zeroes?

I came across a method of ln-transforming exogenous variables in non-negative data sets with loads of zeroes in a lecture. With the method proposed, one simply ln-transforms the variable in question ...
2
votes
0answers
275 views

Gamma hurdle model for continuous response

I am modelling invertebrate.biomass ~ habitat.type * calendar.day + habitat.type * calendar.day ^ 2, with a random intercept of transect.id (50 transects were repeated 5 times) My response is ...
1
vote
2answers
273 views

Penalized regression with zero-inflated models

I'm currently building zero-inflated Poisson & negative binomial predictive models using the zeroinfl() function from the pscl package in R. Incorporating penalized regressions into my model to ...
0
votes
1answer
100 views

A model for technical measurement data with many zeros - pros and cons of Tweedie

I analyze technical measurement data with the aim of developing a forecasting model. The data is given as a non-negative time series (data per hour). The data looks quite wilde and contains many ...
0
votes
1answer
98 views

Dealing with zero-inflation if the data are not count data type

In the literature I found that for the count data with a lot of zeros so-called zero-inflated distributions (models) and so-called hurdle-at-zero distributions (models) could be used. The differences ...