Questions tagged [zero-inflation]

Excessive 0's in a variable compared to a specified reference distribution. Regression approaches include zero-inflated models and hurdle (2-part) models. For count data, zero-inflated and hurdle models based on Poisson or negative binomial distributions are common (ZIP/ZINB and HP/HNB).

Filter by
Sorted by
Tagged with
0
votes
1answer
42 views

Count Modelling and Rates and Zero Inflation

I am looking for some help modelling overdispersed (zero-inflated negative binomial) count data as a rate. I want to model the survivability of villages in different municipalities given guerilla ...
1
vote
1answer
47 views

beta binomial to reduce overdispersion for binomial data (zero inflation)

I know that a negative binomial model is often use to solve the problem of overdispersion in count data (poisson regression). Now, someone said that a beta binomial model can also be used to solve the ...
0
votes
0answers
17 views

MCMC when intervals are irregular

I have a count model that has irregular intervals. It's a collection of some events throughout a year. The data is confidental so I cannot present the actual data but it has the following structure. ...
1
vote
0answers
41 views

Zero-inflated Poisson with known inflation probability

I have a zero-inflated probit model but I know the inflation probability of each observation. So my model is: $P(y_i = 0|X) = (1-\pi_i) + \pi_i*(1-\Phi(X_i'\beta))$ $P(y_i = 1|X) = \pi_i*\Phi(X_i'\...
0
votes
0answers
31 views

Offsets variable subjects and behaviors

I have a set of behavioural data. It consists of about 600+ 50 mins long observations within 35 different bee nests, with many different numbers of observations per nest, and variable numbers of bees ...
2
votes
0answers
68 views

Mixed effect model with zero inflated binary (0,1) response where one level of fixed effect has all 0s. Won't converge

I am trying to use a mixed effect model to determine the relationship between year, season, and depth (my fixed effects) on nutrient outlier presence (dependent variable, 0 or 1). I have two random ...
0
votes
1answer
205 views

predicted counts for Zero-Inflated Poisson model differ from original samples

While experimenting with statsmodels' Zero-Inflated Poisson count model using artificially generated data, I noticed that although the parameters used to generate the data for fitting were ...
0
votes
1answer
39 views

Poisson Regression with overload of zeroes SAS

I am testing different models for the best fit and most robust statistics to my data. My dataset contains over 50000 observations, approx. over 99.3% of the data are zeroes - such 0.7% are actual ...
0
votes
0answers
25 views

Hurdle model: different results for 2nd stage and truncated regression

I am trying to estimate a hurdle ('zero inflated') model using the R package mhurdle to model farmers' participation & participation intensity in environmental schemes. For understanding, I have ...
0
votes
1answer
79 views

Zero-inflated Poisson Regression for Continuous data

I have a continuous variable that I'm trying to model but have a number of issues. The variable is continuous, positive, right skewed and has a large zero-inflation. Whilst the formulation of the ...
1
vote
0answers
33 views

Specification of AR1 correlation structure for multilevel zero-inflated Poisson model with sparse outcome

I am trying to specify an AR1 correlation structure for a multilevel zero-inflated Poisson model using glmmTMB. A sample of the ...
0
votes
0answers
26 views

Firm level data with many zeros

I'm working with some firm-level (cross-sec.) data where a substantial no. of firms (about 15%) report zero revenue for the given year. The rest of the data is fine (in fact normally distributed) ...
3
votes
1answer
106 views

Testing if coefficients are statistically significantly different across models

I will be building two zero-inflated negative binomial (ZINB) regression models, where each model is aiming to predict different disease count outcomes based on the exact same independent variables ...
0
votes
0answers
49 views

How to Combine Bernoulli Distribution with Exponential?

I understand a similar question has been asked before but it was closed because the OP left. I have a situation where I have a continuous variable, which can take values between 0.0 -> ~0.1. It ...
0
votes
0answers
54 views

Hurdle model “goodness of fit” statistics?

I apologise in advance if this sounds like a stupid question. I am used to GLM with continuous data. I've run a hurdle model in R (pscl:hurdle) with a negative binomial distribution for the "count" ...
2
votes
0answers
127 views

Zero-inflation with sklearn and continuous target?

My current data have quite a large amount of zeros (~60%), and I'm thinking of trying to implement a zero-inflated model of sorts with sklearn. While I've used zero-inflated poisson/negative binomial ...
0
votes
1answer
86 views

How to correctly include offset in Bayesian Zero-Inflated Poisson model in winbugs

I am trying to fit a Bayesian Zero-inflated model and I want to include an offset term. When I compared the output of the pscl package; the result of the count model from the winbugs and pscl package ...
1
vote
0answers
101 views

Problems with boxplots and many zeros

I am having a problem making box plots in R. I have several datasets which measure the vocalization of a species (in "Detection Positive Minutes", the number of times a cetacean was calling per hour) ...
4
votes
1answer
158 views

How can I run a Zero-Inflated Poisson/Negative Binomial Mixed Model with Gaussian Process

After having visited stats stack exchange countless times, I'm finally asking a question! For my research, I am try to run a model of the form: $$ Y = f(X,B)+ g(X) + \epsilon$$ Where $f(X,B)$ is a ...
0
votes
1answer
46 views

How to interpret the hurdle or zero-inflated model

I have 137 data points that are inspection and I'm trying to find the hurdle negative binomial distribution that fits. Here is how the data looks I have the following code ...
2
votes
0answers
44 views

Can we perforn a permutation test with zero-inflated data?

In a collaborative problem-solving task, I would like to check if the mean number of communicative exchanges emitted by a person is different following whether they shared an emotion just before or ...
1
vote
1answer
78 views

Zero Inflated Poisson model, estimation of vectors beta and gamma

I'm working on zero inflated poisson models but I have a doubt on the estimation of the coefficients. Suppose that I have a small sample of data (just for an example, 10 policies with just 4 ...
0
votes
0answers
33 views

Nested Negative Binomial (or zero-inflated) Regression

I am currently working on methods for a thesis project. I will be modeling the outcome of disease incidence for two different diseases using negative binomial regression. It will most likely be zero-...
1
vote
0answers
76 views

Zero-Inflated Negative Binomial Theta and Incident Rate Ratios (IRR)?

I am trying to determine the best regression model for data with many zeros; I have about 200 with non-zero DS scores and 600 with zero DS scores. ...
1
vote
1answer
144 views

What is the difference between a Zero-inflated negative binomial regression and a Heckman-two-step regression model?

The title of my question says pretty much what I'm struggling to understand: What is the difference between a Zero-inflated negative binomial (ZINB) regression and a Heckman-two-step regression model?...
6
votes
1answer
234 views

Interpreting random effects in zero-inflated models

For context, I have a longitudinal study measuring counts of bacterial sequences in human stool collected during a dietary intervention. Initially, I was going model the change in each bacterium (...
4
votes
0answers
109 views

Zero inflated and hurdle models - is it common do 'build your own' with e.g. ensemble model?

I have been given a new analytics problem to solve. The context is app analytics where we would like to predict total revenue per app install after 30 days from install based on just 7 days of data. I....
0
votes
2answers
358 views

One group has only zero values, should I use parametric or non-parametric test?

I have 3 groups (n=5 per group) from biological data. I have checked the normality of my groups using the Shapiro-Wilk test and two of my groups are normally distributed. However, the 3rd group values ...
1
vote
0answers
25 views

Handling large percentage of zero-valued observations in a continuous dependent variable in a panel dataset

I am writing a paper using a panel dataset in which my depepent variable is continuous has an large percentage amount of zero values observations. Those zero values are real zeros, I mean they are not ...
1
vote
0answers
112 views

Multivariate zero_one_inflated_beta regression

I want to run a zero_one_inflated_beta regression with brms on the following multivariate formula: ...
0
votes
0answers
93 views

JAGS code for Poisson or negative binomial hurdle (zero-altered) model with autoregressive residual

I am using Bayesian zero-altered Poisson and negative binomial models analyzing time-series data with JAGS. Because the ACF of the Pearson residuals showed autocorrelation, I decided to apply ...
0
votes
1answer
207 views

Statistical tests for count data with many zeros

I have to compare three groups (each group is a customer to a subscription box company). Group A received treatment A. Group B received treatment B. Group C received no treatment. We count the ...
0
votes
0answers
30 views

Unusual residual artefacts in GLMM, is GAM or another model more appropriate?

I'm having trouble finding an appropriate model for my data. The data comprises behavioural observations of chimpanzees, where I instantaneously sampled their locomotor behaviours and parameters of ...
1
vote
0answers
341 views

Interpretation of zero-one-inflated beta models in brms

I have 20 participants who have watched 18 clips. Every clip belongs to one category of pleasure (p_cat: negative, neutral, positive) and one category of intensity (i_cat: low, medium, high). I have 2 ...
1
vote
1answer
25 views

How to analyze data with unequal length of observations and many zeros?

I want to analyze the impact of the rain on smoking probability. I observed people in two cities on the streets and marked the following parameters: city, gender of the person, duration of observing ...
0
votes
0answers
17 views

How to obtain different values of “parameter k” in a mixed-effects negative binomial model?

I have a dataset with two level factors - fertilizers ("Nitrogen" or "Phosphorous") that differed in their concentration level("...
2
votes
1answer
48 views

Poisson on frequency data with many 0, underestimated output

I have got a frequency table of how many events occur within a 5-minute time window. ...
0
votes
0answers
62 views

Extracting the right summary statistics from zero-inflated data sets (i.e. a sparse matrix where everything non-zero is a statistical outlier)

I'm a consumer tech startup founder with rudimentary background in statistics. I need help in processing a large, sparse matrix. I'm logging all actions users are undertaking in my app. I then ...
3
votes
0answers
153 views

How to deal with zero-inflated proportional data in GLMM?

I have proportional data, i.e. number of individuals out of 6 that choose a certain option in a multiple choice experiment, so there are just 7 possible outcomes for each option: 0/6; 1/6; 2/6; 3/6; 4/...
1
vote
1answer
66 views

Inferences from a zero-inflated negative binomial distribution?

Frogs are generally known to spatially aggregate during egg-laying. I manipulated their egg-laying sites with different fertilizers ("Nitrogen" or "Phosphorous") that differed in their concentration ("...
1
vote
1answer
138 views

analysis of variance on zero inflated semi continuous data

I have a fairly fundamental problem with my data, they do not suggest that they were sampled from a normal distribution. This is problematic because I would like to run some sort of analysis of ...
0
votes
0answers
42 views

What model is appropriate when a non-negative, continuous dependent variable has frequent zero-values because of limited data?

I'm modeling how likely a song is to occur in a playlist with a particular title. I can calculate a simple probability based on my current data, but it's highly zero-inflated because my data is ...
0
votes
0answers
21 views

zero inflated interval data

looking at the survey my data set is based on, my dependent variable originally is given in percentage ranging from 0 to 100. Howewer, in my dataset the information is categorized in to 9 intervals. 0 ...
1
vote
1answer
21 views

What is the impact of excess zeros on poisson regression coefficient estimates?

The background I have a dataset with some zeros - based on how I segment my data, it is either 50% of the observations or 80% of the observations. The data is not actually count data, but from what i ...
3
votes
1answer
496 views

Variable selection in zero-inflation models

I am trying to understand how to perform model comparison between different count models. In this example the author performs a zero-inflated poisson model testing the effect of number of people in a ...
1
vote
0answers
85 views

How to plot estimate + raw data of a Bayesian zero inflated poisson?

GENERAL QUESTION: How to back-transform estimates from a zero-inflated poisson to obtain the original scale in R? (I tried exponential like for poisson but the results are wrong) DETAILED ...
0
votes
0answers
40 views

R - zero biased data, glmer.nb, properly counting confidence intervals

any suggestions how to count confidence intervals from zero biased data? I've counted generalized linear model using glmer.nb function. I have to make graph but I was told that confidence intervals ...
2
votes
1answer
415 views

How to model a zero-inflated 'continuous' response data in r 'without' assuming an underlying normal distribution?

I have a weather data set with rainfall as response. It has 56% observations as 0, while the rest as continuous rainfall data. I can't use tobit, hurdle or any other zeroinfl() model as they require ...
3
votes
1answer
54 views

Approach to Analyzing Semi-Rare Events

I am often faced with analyzing data that follow a pattern as shown in a mock example in the image below. Key data characteristics: for any value of the predictor (e.g. temperature), the most ...
1
vote
1answer
131 views

Hurdle model vs left censored model

When dealing with response variables that have lots and lots of zeros, is there a clear argument for when hurdle models are preferred and when left censored or tobit models are preferred?

1
2
3 4 5
9