Skip to main content

Questions tagged [tobit-regression]

Tobit regression is used to estimate a linear regression model when the dependent variable is censored, i.e. when it is only observed over an interval of its support.

Filter by
Sorted by
Tagged with
2 votes
1 answer
31 views

Regression with known upper bounds and lower bounds of predicted variables

I have three variables $x_1$, $x_2$ and $x_3$ to predict $y$. Simplest regression setup is to run regression $y \sim x_1 + x_2 + x_3$. Then I have prediction $\hat{y} = \hat \beta_1 x_1 + \hat \...
Matt Frank's user avatar
0 votes
0 answers
43 views

Understanding the reasoning behind Tobit composite likelihood

The Tobit model defines a likelihood for what amounts to a censored normal distribution - i.e. the tails are clipped - which is meant to be applied to data that has undergone censoring and thus has an ...
anymous.asker's user avatar
0 votes
0 answers
30 views

censored gee model

Does anyone know if it is possible to fit a left censored GEE model with autoregressive correlation structure ? I know censReg can handle left censored repeated ...
Ahir Bhairav Orai's user avatar
1 vote
0 answers
10 views

heterogenous treatment effects - a question

So I conducted a framing experiment - 4000 people received either framing A or B, and donated $ to a charity if they wanted to. Now I want to check if framing A or B had specific efffects on ...
Guestquestion's user avatar
0 votes
1 answer
254 views

Which model for highly skewed data

The response variable in the dataset is highly skewed with a "ceiling effect". The errors of a fitted regression model, will thus also be skewed. I tried to fit a regression but as expected ...
Simone's user avatar
  • 252
0 votes
1 answer
57 views

Post-hoc analysis for Tobit model using Censreg in R

I have a blood biomarker (BHB) in my dataset with censored distribution (i.e., lower detection limit of 96). I want to use Tobit regression with the Censreg package in R. My objective is to see if ...
Falco's user avatar
  • 149
0 votes
0 answers
36 views

What is pseudocomplete data?

Skimming Huang et al 2019 I see references to a term "pseudocomplete-data" that I am not familiar with. It looks like they are dealing with a data censoring problem which they approach with ...
Galen's user avatar
  • 9,229
2 votes
0 answers
172 views

Mixed model with censored data in R?

My objective is to see if there is a significant difference in BHB concentration between age categories in farm animals. Farm should be a random effect in the model. The issue is that BHB ...
Falco's user avatar
  • 149
0 votes
0 answers
18 views

r tobit regression with random intercept [duplicate]

I apologize my knowledge in the field of statistics is limited as I am a newcomer to this area. I am trying to expand my understanding to concepts beyond simple linear regression and simple mixed ...
Emily Fassbender's user avatar
0 votes
1 answer
42 views

What is the difference between a Latent variable model and a Tobit model?

Wooldridge Introductory Econometrics: A Modern Approach (2018), pages 561 and 572, gives the following definitions: Latent variable model (LVM): $$ y^*=\beta_0+\mathbf{x} \boldsymbol{\beta}+e, y=1\...
Tomas R's user avatar
  • 177
1 vote
0 answers
77 views

How to estimate latent variable in Tobit Model

I have a Tobit model of the form: Yi* = latent variable; Yi = censored (observable) variable; Yi* = β0 + β1*Xi + ϵ where ϵ is a random variable normally distributed with mean of zero and variance of ...
Dave Rock's user avatar
0 votes
0 answers
131 views

Left censored regression bounded at zero

I've been handed some data that is obviously left-censored. Many zeroes, probably due to insensitivity of the assay. However, since it is a protein level assay, it is theoretically impossible for any ...
Bryan's user avatar
  • 1,099
1 vote
0 answers
89 views

About adjustment to Tobit regression model output

I am using Tobit regression approach to build a prediction model with a dependent variable censored at 0 and 1. Several R packages provide nice functions to train a Tobit model, such as censReg, vglm, ...
simohayha's user avatar
0 votes
2 answers
685 views

Average marginal effects for censored regression (Tobit) in R

I would like to calculate average marginal effects for a Tobit regression in R. margEff.censReg can calculate marginal effects at the mean, but not average marginal ...
Christian Zimpelmann's user avatar
1 vote
0 answers
40 views

Possible censored data and Tobit regression

I want to study the impact of highways on deforestation. I am using annual data on forest cover. I define my deforestation/forest loss variable as a change in forest cover and if the change is zero or ...
Impala's user avatar
  • 11
1 vote
1 answer
365 views

What statistical test compare truncated distribution

I have been taking measures of two populations of mice. One population runs for 10minutes and the other can barely run for 2-3 minutes. The problem is that I have too many mice to keep testing them ...
Mike JJ's user avatar
  • 13
0 votes
1 answer
540 views

Analysing a small data set with lots of zeros? Dependent variable is (semi?) continuous, one fixed (categorical) factor

I have a small data set looking at the level of a particular protein (heat shock protein 70) in individuals exposed to different thermal treatments. There are 5 different thermal treatments with 10 ...
statshelp's user avatar
1 vote
1 answer
148 views

Is using a tobit regression appropriate for structured missing data?

I have a data set with a significant amount of missing data and that missing data is not random. I decided to change these NA values to 999 and apply a Tobit with right censoring after a cut-off point ...
Nonya's user avatar
  • 347
1 vote
1 answer
57 views

Two part model - using the output of first as feature to second?

I am working on a two-part model to predict a continuous target variable $Y$, given a feature set $F$. $Y$ is product of two continuous variables - $A$ and $B$, where $A \epsilon [0, 1]$ and $B \...
Karup's user avatar
  • 113
0 votes
2 answers
366 views

How to do LASSO regression with a dependent variable that has two limits

I would like to estimate a LASSO regression for a dependent variable that has a lower limit at -0.661 and an upper limit at 1 in R. I have already estimated a tobit regression without LASSO with the ...
Nerd's user avatar
  • 49
1 vote
1 answer
432 views

Tobit panel data or panel data with truncated dependent variable

Does anyone know if it is possible to use the Tobit model and the data panels model together, especially in the R language? I tried the censReg package, but it didn'...
Vitor De Vasconcelos Lima's user avatar
1 vote
0 answers
97 views

Estimating Right Censored Data

I'm a newbie at Math, and I am just getting my feet wet when it comes to understanding math and statistics so please forgive my ignorance or question if it's already been answered or if materials are ...
drizzle123's user avatar
2 votes
1 answer
2k views

How to write a random effect in tobit models in R using the censReg package?

To analyse right-censored data, I'm using the tobit regression package called censReg in R. When assuming a fixed effect model, this works fine. ...
Anthony's user avatar
  • 441
0 votes
1 answer
90 views

likelihood function of tobit model when y can only be 0 or 1

As you can see, , here is the likelihood function of tobit model when observed y equals 0 when it is smaller then $y_L$. What is the form when observed y equals 0 when it is smaller then $y_L$, AND y ...
Joy Hu's user avatar
  • 23
1 vote
1 answer
34 views

Baseline adjustment when both pre- and post values are subject to left-censoring

Assume $X$ is a binary treatment variable, $Y$ is a continuous variable measured pre- and post-treatment $(Y_{pre}$, $Y_{post})$, and $Z$ represents the remaining covariates. Both $Y_{pre}$ and $Y_{...
andrjens's user avatar
1 vote
0 answers
69 views

Zero Hidden layers + ReLu-Activation + Gradient Descent = Tobit?

when I train a neural network with zero hidden neurons and ReLu activation functions using gradient descent, can it be expected that the resulting weights are approximatly equal to those of a tobit ...
Funkwecker's user avatar
  • 3,092
2 votes
1 answer
135 views

What type of model(s) can I use for my (definitely not linear) dependent variable?

I have dependent variable, measured with a range of 0-100% (nevertheless it takes on fairly few variables). It reflects the amount of sales reported for some purpose. The distribution looks as in the ...
Tom's user avatar
  • 528
0 votes
0 answers
45 views

Do I have a censored variable or not? What is the mean of my data?

I have a variable variable from a survey, which has a range from never (0) to always (100) in 10 steps (0 -100). It is obviously a discrete (ordinal) variable, but I want to try to treat is as ...
Tom's user avatar
  • 528
3 votes
1 answer
264 views

Wikipedia's likelihood function of tobit model

This is the likelihood of the tobit model on Wikipedia. To my understanding, the first is the normal density when y is greater than the threshold and the second is the cdf of y for everything below ...
user avatar
0 votes
0 answers
48 views

Tobit Regression

I have a data set of Arsenic (As) in rice grain which is dependent of As in soil and also As in irrigation water. The permissible limit of As in rice grain is 400 ppb however in reality more than that ...
Jajati's user avatar
  • 1
1 vote
0 answers
150 views

Manual calculation - instrumental variable with a tobit distribution in the 2nd stage, different results with robust errors

Cross Posted at Stack Exchange. I am trying to correct my standard errors, when using an ols distribution in the first stage and using a tobit distribution in the second. For some reason, I am getting ...
Tom's user avatar
  • 528
1 vote
0 answers
168 views

Predicted values well outside of the censored range

I am working with an endogenous independent survey variable, $x$, which has a value range from 0 - 10, where 0 is always and 10 is never. Because the question pertains to wrongdoing, the answer to the ...
Tom's user avatar
  • 528
2 votes
1 answer
750 views

2SLS or IV with a tobit distribution in the first stage

I would like to use a two stage least squares approach (2SLS), where the first stage would benefit from a Tobit specification. I cross posted this on stackoverflow because there might be quite some ...
Tom's user avatar
  • 528
2 votes
1 answer
1k views

Is it practical to use Tobit models predictively for censored latent variables?

I'm developing a model in R estimating vehicle miles traveled (VMT) using Tobit specification, since my data include a cluster of zero VMT values. I understand that the coefficients given by a Tobit ...
gabbyaz's user avatar
  • 23
2 votes
2 answers
383 views

best regression model for a percentage of function variable

I am trying to choose the best regression model for a dependent variable 'percentage of normal shoulder function'. This variable is non normal and clustered at the high end of the possible range, ie ...
mconnor14's user avatar
1 vote
0 answers
776 views

Tobit model for continuous zero inflated data?

I would like advice on how to apply an appropriate linear model to my data. I have several continuous independent variables, and a dependant variable with continuous distance measurements. This ...
OskMal's user avatar
  • 21
0 votes
0 answers
175 views

Asking: interpret tobit regression to estimate willingness to pay from payment card

I have a research question, that I have to evaluate the Willingness to pay data for conservation. My input data in the type of payment card : $0, <\$2, \$2-\$4, \dotsc, >\$10$. I use middle ...
bi_hop's user avatar
  • 1
2 votes
0 answers
198 views

Predictive Margins After Mixed-Effect Tobit

I'm hoping to get advice on the difference between two predictive margins outputs after running a mixed-effect tobit regression (in Stata 16.0). Here is a sample output (modified from my actual case),...
aquameer's user avatar
  • 111
1 vote
0 answers
339 views

2-stage selection model with censoring: Heckman selection model with second stage censoring

I am seeking to get some insights on the application of two-part Tobit-type models to a distribution with potentially selection (from 0 into +ve) and upper truncation (censoring of data at 100%). ...
Spaniel Boone's user avatar
1 vote
2 answers
917 views

A workaround for using linear models (rather than Tobit) with censored data?

I have a left censored dependent variable where many of the observations have a value of zero. The data is clustered (multiple measurements over time for each person). I initially decided to use a ...
GXR200's user avatar
  • 11
0 votes
0 answers
124 views

Estimation of censored regression model

I am refreshing my knowledge with respect to econometric modelling in general. I came across page 201 of the book 'Enjoyable Econometrics by Philip Franses' and I had some difficulties interpreting ...
Nadia Merquez's user avatar
4 votes
0 answers
181 views

Multiple regression for left-censored independent and dependent variables

I am interested in developing a predictive multiple regression model which predicts a concentration of one compound based on the measured concentrations of several other compounds. Both the dependent ...
Ryan Conway's user avatar
1 vote
0 answers
17 views

Unbiased estimation of regression coefficients conditional on a range of the dependent variable

I am interested in the relationship between a set of explanatory variables and a particular outcome variable for values of the outcome above a certain cutoff. Can I simply regress the outcome on the ...
andrewH's user avatar
  • 3,127
0 votes
0 answers
313 views

Conditional heteroscedasticity for the tobit model in Layman's terms

I have been using the crch package for modelling censored data with the tobit model. I noticed early on that the errors (by far) are not normally distributed by ...
Nadia Merquez's user avatar
0 votes
1 answer
57 views

Question about deriving probabilities in the Tobit model

In the Tobit model: Why do you divide by σ when deriving the probability that y = 0? Is it something to do with the assumption that ε is distributed N(0,σ^2) and not N(0,1)? If this is the case why ...
William's user avatar
6 votes
1 answer
3k views

What is really the Scale or Sigma parameter of a tobit regression?

In this most upvoted CV answer on that topic the "scale" parameter (aka "sigma" in Stata) thrown in a tobit regression output is explained to be "the estimated standard ...
jay.sf's user avatar
  • 846
1 vote
1 answer
550 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?
sea83's user avatar
  • 31
3 votes
1 answer
574 views

Picking from Logistic vs Survival Model

I have a health data set for measuring the effectiveness of a drug. (Age, Gender(0,1), Morbidity(1,2,3), Dosage(0,1), Group (a,b), Effect (Not effective =0, effective = 1), and Time (days needed for ...
Ares's user avatar
  • 31
1 vote
1 answer
826 views

How to get rid of zero standard error values, missing t-values and p-values

I was running a couple of Tobit regressions on SAS. Surprisingly, I found that estimates from one model show 0 standard errors, missing (.) t-values and p-values. Why did this happen? What does this ...
Deepan Das's user avatar
1 vote
0 answers
863 views

Comparing the output and fit of an OLS and a Tobit model, and comparing Tobit models

I am trying to estimate a quite complicated model (many variables with different structures), with a limited dependent variable, which ranges from 0-100% with about 45% of the sample having an ...
Tom's user avatar
  • 528