Count data are non-negative integers representing whole amounts. When such data are the dependent variable in a regression, Poisson or negative binomial regression may be appropriate methods. One common problem is "zero-inflation" (where the proportion of zero values is greater than predicted by a ...

learn more… | top users | synonyms

0
votes
0answers
26 views

Help running a Difference in Difference

I have a simple linear DiD model for patent count data $$ patent_{ut}=\beta_0 +\beta_1 grant_u +\beta_2ptreatment_t +\beta_3 interaction_{ut}+error_{ut} $$ where u denotes a university and t denotes ...
1
vote
1answer
34 views

Should OLS always have a lower RMSE than Poisson Regression?

I'm working on building a predictive model for the number of singles a hitter in baseball generates over the course of a single game. Since the number of singles a hitter scores per game is count data ...
1
vote
0answers
14 views

How to Test for Some Basic Assumptions of (Zero Inflated) Negative Binomial?

I am currently working with a T dominant panel --time-series cross-section dataset-- that has N = 8 (eight European countries) and T = 28 (28 quarters for each country). The dependent variable --...
2
votes
0answers
15 views

Which test can I use to compare two count data means with a lot of zeros?

Suppose I have two count datasets, lets say the count of tigers across different years at two places. Now for most of the years we have 0 tiger sightings. For eg. ...
1
vote
0answers
17 views

Poisson process (discrete counts) measured over varying time interval with many zeros

I am modeling forest inventory data. Forest plots are visited every 5-10 years. New trees that cross some threshold diameter between census intervals are classified as 'recruits' and counted. ...
3
votes
1answer
51 views

Relationship between Poisson, binomial, negative binomial distributions and normal distribution

When we have to define discrete counts distributions, we usually use : Poisson distribution, if mean = variance Binomial distribution, if mean > variance Negative binomial distribution, if mean <...
0
votes
0answers
13 views

Sample size determination for estimating a count

I want to estimate a simple variable: "**how many times my website is visited in 2015?". Suppose that I cannot count all visits to my website (it is expensive!), but I can count the connections on ...
0
votes
1answer
24 views

Poisson normal approximation for comparing means of count data

I'm trying to compare the values of two counts from an A/B test, $c_1$ and $c_2$. If I assume the data is Poisson distributed then the mean and variance are $\lambda$ and the standard error is $\...
7
votes
1answer
66 views

Fractional dependent variable: Why not use Poisson regression?

In many settings, we are interested in estimating a model with a fractional dependent variable. For example, Papke & Wooldridge (1996) http://faculty.smu.edu/millimet/classes/eco6375/papers/papke%...
0
votes
0answers
18 views

Conditional independent Poisson variables modelling count data

A study question I have been looking at for sometime has confused me somewhat. I have conditionally independent Poisson count observations with a hierarchical structure to the data. The format of ...
0
votes
1answer
29 views

How to operate on a count dataset (positive whole numbers with a lot of zeros) using neural networks for classification?

So i have some dataset, which is basically a count dataset. I have my own code for the classification using neural networks. Turns out that the data does not have a lot of correlation so accuracies as ...
4
votes
2answers
135 views

How to find the sweet spot

In R I have data where head(data) gives ...
1
vote
0answers
31 views

How to test the distribution of the transcripts per million (tpm) values and analyze ASE (allele specific expression) differences between haplotypes?

I have the TPM (transcripts per million) values generated for my RNAseq data. My overall goal is to identify genes that show allele specific expression differences. In the table below the TPM values (...
0
votes
0answers
21 views

Relationship between two (zero-inflated) count variables

TLDR: How can I model the relationship between two count variables that are both dependent on the same third, unobserved, continuous variable. Detail I am interested modelling the effect of an ...
2
votes
0answers
37 views

Comparing count data models?

I am trying to fit Negative binomial, Zero Inflated Negative Binomial, Negative Binomial Hurdle, and Random effects negative binomial. Here is the value of AIC for different model: Negative Binomial: ...
1
vote
1answer
37 views

Forecasting a distribution for count data

I'm working on a project to forecast the distribution of a baseball player's "At Bats per game" (a baseball statistic w/ integer domain) using a player's position in his team's batting order as a ...
0
votes
0answers
17 views

Parameter interpretation for discrete weibull regression

Please can someone provide an accessible interpretation of the parameter estimates from a discrete weibull regression model, e.g in R: ...
3
votes
1answer
25 views

Poisson regression with different exposures dependent and predictor variables

I am trying to fit a Poisson regession in R, using rates: $\ln(\mathrm{rate}_i) ~= a + bx_i + c \ln(\mathrm{old\_rate})_i$ My issue is that the predictor variable $(\mathrm{old\_rate})$ is also a ...
1
vote
1answer
25 views

Determining if points out of control - non normal distribution

I am trying to create a process in which I can identify if a process is out of control. My idea was to do something similar to 6 sigma, where when a point is outside of the mean by +-3 sigma, then ...
0
votes
1answer
33 views

Difference between logistic regression and chi-square for analysis with no covariates?

I have a binary response variable (0s and 1s), the distribution of which that I want to compare to chance. I understand I could use logistic regression or a chi-square test to do this and that these ...
1
vote
0answers
23 views

Model for count data with different exposure time (some times are terminated by death)

I am looking for most suitable model for count data in the following case: we collect number of patient's visits in a hospital for $t_i$ days ($t_i$ varies across subjects) some patients died ...
0
votes
0answers
21 views

Obtaining AICc weights after glm.nb

I am performing negative binomial regression using glm.nb() function from MASS package and calculating AICc using package "AICcmodavg". I need also to obtain the (AICc) weights using aictab() function ...
1
vote
0answers
19 views

Most appropriate test for count data

So I've performed an experiment whereby I had 12 1km transects. 6 of these were along rivers running through agricultural land and 6 through woodland. These were arranged in pairs so that each agri ...
1
vote
0answers
26 views

Count regression for a response that have a strict upper bound

I wonder what is the optimal way to conduct count regression when the response variable has a strict upper bound. For example, I would like to relate some predictors to how many lung lobes are ...
0
votes
0answers
18 views

Standard error of mean for overdispersed count data

I have count data from survey transects at several sites (typical n ~10). I am interested in whether the sample mean exceeds a threshold at [1-alpha]% confidence level (...knowing I have low power), ...
0
votes
0answers
26 views

Count data that can take only 4 values

What is a good model for estimating a regression whose count dependent variable that only has 4 values: 0, 1, 2, 3? The variable is not truncated, it is just something that can only be from 0-3. I've ...
4
votes
1answer
37 views

Searching for a good book on count data

I am seeking recommendations for a good book on count data, with clear explanations of topics like Poisson regression. The level of the book should be suitable for a graduate math and statistics ...
0
votes
0answers
15 views

Count data regression model formulation

I am working on one of the discrete probability distribution having pmf as P(x)={p^log(1+x^c)}-{p^log(1+(x+1)^c)} 0<p<1; c>0; x=0,1,2,. It fits well ...
1
vote
1answer
123 views

Normalization of count data of time periods with different length

I have count-data from two time-periods which differ in length. The event I'm counting is in both periods the same kind of event. Period 1 is 120 hours Period 2 is 48 hours At the end I have ...
1
vote
0answers
40 views

Dependent variable is count data, which method to use?

Which method should I use to analyse the relationship between count variable (absent days) and other 4 variables? Should I standardise Size variable? Please recommend some further literature/ ...
1
vote
0answers
42 views

One-sample t-test on count data

I’m working with sports performance data (ice hockey). The question I’m trying to answer is: Does the number of duels player A won in a specific match differ significantly from the mean number of ...
0
votes
0answers
27 views

Modeling count data over years through poisson regression

I have the following problem. I am trying to use the poisson regression on my data, which look like this: ...
8
votes
3answers
693 views

What regression model is the most appropriate to use with count data?

I am trying to get a little into statistics, but I am stuck with something. My data are as follows: ...
1
vote
0answers
4 views

Validation of prediction interval for count data

I have developed a random-effects (frailty) survival model for repeated events which enables calculating individual-specific mean and prediction interval for the cumulative incidence (rate) of future ...
0
votes
0answers
20 views

Formula logic of Croston's method

In an article of Willemain et al (2014) (doi:10.1016/S0169-2070(03)00013-X) do they give an explanation of the Croston's method in which they use the following equations: How can the forecast of <...
1
vote
1answer
41 views

Measure of central tendency for periodic variable (hour of day)

I have a dataset that shows, for each group, the number of times a certain action was completed during each hour of the day. ...
0
votes
0answers
21 views

Which statistical test is most appropriate for my count data?

I did a study looking at how the number of times a specific behaviour is performed during a courtship ritual is affected by temperature treatment, while trying to control for the body size of the male ...
4
votes
1answer
104 views

Forecasting Poisson, accuracy and prediction intervals

I'm trying to forecast Poisson data, divided in groups, of 1-26 months of data, depending on the group. Of the pooled data ...
0
votes
1answer
53 views

Analysis of Categorical and Likert-Like Survey Data

I'm about to have data from intercept surveys conducted in parks. The goal of the survey is to determine which characteristics of parks users find most important to park quality (do they care a lot ...
1
vote
0answers
41 views

Selecting Link Function for Negative Binomial GLM

I'm trying to model insect abundance data with a variety of vegetation/site related covariates. Because it is count data that is over-dispersed, I've decided to use the negative binomial distribution. ...
0
votes
0answers
9 views

Modeling different rates with same offset

I'm working on my PhD and trying to analyze some data and would appreciate anybody's two cents. I'm going to trying to explain my issues with a simplified example below. Generally, I am trying to ...
1
vote
0answers
26 views

Can I sum up my count data instead of performing some repeated measures analysis?

I want to analyze establishment of plants in created gaps (plots): I have 10 treated plots, which are divided into an outer section and an inner one and I have been looking at these plots over a ...
0
votes
0answers
10 views

Poisson regression with days per week as the DV

I am estimating a poisson model (and negative binomial for comparison) with the number of days in a week that a person made a fishing trip as the dependent variable. The range of this variable is ...
0
votes
0answers
18 views

Smoothing weekly count data

I have samples of weekly count data for shoppers. The counts are based on hourly observations For example, for week 1 the hours of observation were Monday 1 PM Wednesday 4 PM Thursday 11 AM ...
0
votes
1answer
51 views

Nonparametric methods for count data?

I have data where the dependent variable are counts of an event. I am modeling the relationship between the dependent and independent variables using a negative binomial model, but I was also hoping ...
0
votes
0answers
52 views

Discretizing count data (poisson distribution)

Hi I am using next generation sequencing data (Chip-seq) for a machine learning problem. The data is represented as counts of fixed sized regions of genome (in this case 1000 bp) each 1000 bp bin ...
0
votes
0answers
24 views

Mixed effects model with missing count data

I have bird count data over a period of ten years from 15 different sites. For each site I have the month of the count, the year of the count, and the count number of birds. I need to analyse the data ...
0
votes
1answer
32 views

How to test repeated, nested, count data

I have samples from an experiment in which I have counted cells. I took 2 pictures of each kidney, photographing both kidneys of each subject. Each individual belongs to a group (infection). My ...
3
votes
1answer
20 views

Multinomial Count Models

Is it possible to model a dependent variable which is both multinomial and count? If so, how would one do so with a tool such as R? For example, suppose that my dependent variable looks like this: ...
0
votes
0answers
26 views

Comparing Two Count Variables Within-subjects

I have data where I asked participants to list 5 people that they thought fit a particular category. We then coded whether the people were men or women and counted the number of men and the number of ...