Skip to main content

Questions tagged [log-linear]

The log-linear model is a form of Poisson regression that allows for the analysis of multi-way contingency tables.

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

Elasticity from differenced log-level regression

I have the regression $ \Delta \ln Y_i = \alpha + \beta \Delta X_i + \varepsilon_i $ where $\Delta \ln Y_i = \ln Y_{t,i} - \ln Y_{t-1,i}$ and $\Delta X_i = ((X_{t,i} - X_{t-1,i}) / T_{t-1,i} ) \cdot ...
Papayapap's user avatar
  • 363
2 votes
1 answer
39 views

Does OLS give the maximum likelihood estimation for a linear log model?

I'm fitting a model $y=a\times \log(x)+ b$ using standard scikit linear regression (wich uses OLS) and a transformation $x'=\log(x)$. My doubt is: the parameters I get for the model are the best one ...
Roger Danilo Figlie's user avatar
1 vote
0 answers
32 views

Help identifying a distribution

I'm seeing data whose rank-frequency curve is nearly log linear (b e^(a x)) but where the top few frequencies are higher than expected. The top fits a Bradford distribution well, and the middle is ...
Scott Deerwester's user avatar
4 votes
2 answers
117 views

Interpretation of interaction term in log-linear models

Given the model: $\log(y) = \beta_0 + \beta_1 x_1 + \beta_2 x_2 + \beta_3 x_1 x_2$ Which can be for example a Poisson or a Negative Binomial model ($y$ would be a count variable) or a logistic ...
robertspierre's user avatar
0 votes
0 answers
66 views

Natural logged dependent variable and the ratio problem with two-way fixed-effects panel model

In a non-peer-reviewed (yet?) paper, Bartlett and Partnoy (BP) (2020) discuss some under-appreciated issues related to using ratios as the dependent variable. Some but not all problems are dealt with ...
dcoy's user avatar
  • 362
2 votes
1 answer
48 views

Coefficients of log-transformed outcome

I would like to know what is the appropriate word for regression coefficients of log-transformed outcome(y) after taking the anti-log of regression coefficients. It is not an odds ratio or risk ratio. ...
Sundown Brownbear's user avatar
2 votes
1 answer
58 views

interpretation of a two-stage regression model

I am running a two-stage regression model, where the first model is a log-linear model he outcome is log(y) = Intercept + 𝛽1 * x + Error. I then calculate the residuals for each observation of x. The ...
four77's user avatar
  • 111
1 vote
1 answer
52 views

Why shows a two variable $\chi^2$-test a significant p-value while a log linear analysis on the same data does not?

I did an experiment to look at the influence of two categorial variables onto a categorial output. The input variables were T and ...
Claude's user avatar
  • 241
1 vote
1 answer
245 views

Test to compare multiple contingency tables

I have three contingency tables with the variables month and region that contain the frequency of the sighting of a particular bird. Additionally, the tables differ only by counting frequencies from ...
jjohn102's user avatar
0 votes
0 answers
17 views

Interpretation of proportion coefficient

I know that I should be able to work this out but I am struggling. My dependent variable is a log variable (call it y) and my independent variable is a proportion that takes a value between 0 and 1 (...
kieran's user avatar
  • 1
0 votes
0 answers
30 views

Multicollinearity in mixed log-linear model

I am currently running a mixed log-linear model which is in this form: Log yit = Xit + X2it + (1|individu) I suspect a multicollinearity ( cor (Xit , X2it) close to 1 ). Do you think it makes sense to ...
Ado's user avatar
  • 1
2 votes
0 answers
14 views

Power for hierarchical loglinear model

Can anyone point me in the right direction for doing sample size/power calculations for hierarchical log-linear analysis of nominal (frequencies) data? Would I get in trouble with reviewers for just ...
Steve's user avatar
  • 121
1 vote
1 answer
176 views

Contingency analysis of a 3x3 table via Chi2, log-linear and Poisson GLM - how to interpret this result?

I have a dataset describing age of wine in 3 classes of quality. ...
CroissSant's user avatar
1 vote
0 answers
91 views

"Percent change" interpretation when we $\log$ the expected value instead of taking the expected value of the $\log?$

When we take the log of the $y$ variable of a regression and then fit the OLS estimator via $(X^TX)^{-1}X^T\log(y)$, we can interpret the regression in terms of percent change in $y$. However, this ...
Dave's user avatar
  • 65.1k
0 votes
0 answers
20 views

Help determining model and interpreting coefficients of log-linear relationship

I am trying to determine if the hospital I work at should open a new unit for admissions. I intend to do this by correlating patient assigned unit and length of stay in days. So far, I have determined ...
HanSwet's user avatar
1 vote
1 answer
17 views

Compressing vectors by using log-linear modeling?

I have $k$ vectors, each consisting of $2^n$ positive reals adding up to 1, and I'd like to compress them by only saving $n$ reals per vector. One approach is a no-interactions log-linear model to ...
Yaroslav Bulatov's user avatar
0 votes
1 answer
42 views

Resources to help conduct a log linear (logit) model in spss

Does anyone know of any resource about how to conduct a loglinear (logit) analysis in spss? There are some youtube videos but not specifically about the logit one.
user avatar
1 vote
2 answers
206 views

Choosing the best type of analysis for my variables and objectives

I am struggling to identify the best analysis for my design. My two independent variables are binary (dichotomous) and my dependent variable is also binary (dichotomous). The goal is to find whether ...
user avatar
1 vote
0 answers
20 views

Ranking log-linear distributions and the Lucas numbers

The wikipedia page on rank-size distributions claims: "When any log-linear factor is ranked, the ranks follow the Lucas numbers, which consist of the sequentially additive numbers 1, 3, 4, 7, 11,...
agnosticmantis's user avatar
0 votes
0 answers
1k views

Calculation of the standard deviation of the power in dB

I wanted to find out the stability of my system so for that i calculated standard deviation of power samples data which is in dB but I am not sure whether i have used correct formula or not. As far as ...
ruggeinstein's user avatar
2 votes
1 answer
215 views

Iterative proportional fitting with constraints

I am trying to determine if it is possible to conduct iterative proportional fitting with some constraints. To give a dummy example of my goal: Say I had data for two towns, A and B, on the ice cream ...
sofiaaj's user avatar
  • 45
8 votes
1 answer
197 views

Why does log-linear analysis seem to ignore the Poisson regression equidispersion assumption?

As far as I understand it, log-linear analysis is based on the use of a Poisson regression. This is what I understood from various online resources, like this online tutorial or this text whose intro ...
J-J-J's user avatar
  • 4,974
2 votes
0 answers
135 views

How do I choose which variable transformation (logY~logX/logY~X/etc)? [closed]

I'm doing a linear regression assignment using a variable transformation using R. and I have several questions. What is the criteria of choosing which type of variable transformation? We've learnt &...
angie's user avatar
  • 21
0 votes
0 answers
34 views

Visualizing relationships in log-link/exponential distribution models by placing the linear predictor on the Y axis?

I'm visualizing results from a negative binomial regression. I don't want to the graph of Y vs X to look exponential, I want it to look linear. In SPSS, the value provided for the linear predictor is ...
user351354's user avatar
1 vote
1 answer
195 views

How to correctly perform a goodness-of-fit test for a contingency table (two-way, three-way, or more), in situations other than independence testing?

Let's say I have the following table from a sample of 462 people: Gender Happy Meh Sad Men 70 32 120 Women 100 30 110 I don't want to test it against the hypothesis of independence, but against ...
J-J-J's user avatar
  • 4,974
0 votes
0 answers
14 views

taking log of a variable with values of 0 [duplicate]

I have an outcome variable 'expenditure' which I believe may be non-linear in nature so I am running a log-linear regression after taking log of the variable. However, there are values under ...
Nikita's user avatar
  • 3
1 vote
0 answers
27 views

Clarification on likelihood maximisation

From Eisenstein Natural Language Processing textbook, a discriminative log-linear model is defined as $$p(y|x,\theta) = \frac{\exp(\theta^Tf(x,y))}{\sum_{y'} \exp(\theta^Tf(x,y'))}$$ To estimate the ...
Dime's user avatar
  • 125
5 votes
2 answers
1k views

Log-linear and GLM (Poisson) regression

I am afraid I am asking a stupid question... but... I would like to study the spending (my outcome variable) of a company by department, number of staff, activity, etc. I have collected my data and ...
Mat's user avatar
  • 99
0 votes
0 answers
1k views

Using Log-Linear Regression to calculate the growth rate

I am learning the formula of growth rate and how to calculate this Growth rate is $y = a * (1+x) ^ b$ Log-linear regression: $log y = log_a + b * log (1+x)$ Then b is considered as coefficient What I ...
linh tran's user avatar
2 votes
1 answer
36 views

What is the best way to test of draws ( 10,000 unique possibilities) from multiple sample are random?

say I have 6 people drawing from their own box, each box contains 10,000 unique barcodes. Now at the end of the experiment each person has drawn roughly 10-20 barcodes. How do I test if the barcodes ...
Ahdee's user avatar
  • 331
1 vote
0 answers
103 views

log-linear model in R under multinomial scheme

I am trying to fit a log-linear model. In short, we can fit a log-linear model when family=poisson in R. But when we condition on N, we have multinomial ...
Dihan's user avatar
  • 175
3 votes
2 answers
434 views

Scale Parameter in a Log-Linear Accelerated Failure Time Model

Let the logarithm of the random varible $T_i$, associated with the lifetime of the $i$th individual in a survival study, follow the disitribution $$log(T_i) = \mu + X_i\beta + \sigma\epsilon_i$$ with $...
Benykō-Zamurai's user avatar
0 votes
0 answers
121 views

Mean Log10-Linear regression

In field experiment I have gathered data for X and Y with the aim to fit a regression and use X to predict Y in the future. Based on physics, I know the relationship should be of the form $y = 10^{a \...
Vicky's user avatar
  • 1
0 votes
0 answers
553 views

How do you change log-linear transformed prediction interval values for a regression back to original scale in r?

I have a simple regression model where I needed to log-transform the dependent variable because the model residuals were non-normal. Now my model is ok in that respect. So, I ran the model. But, ...
EMC's user avatar
  • 1
1 vote
1 answer
550 views

Differing AAPC and Confidence Intervals Using the Joinpoint Regression Trend Analysis Software vs R

Let's say I have a data-set with trend data looking at an adjusted rate by year from 1980-2000, with a standard error associated with it: ...
chicago_bioinformatics's user avatar
1 vote
0 answers
165 views

Does benfords law imply a log scale for the distribution?

We see Benfords Law in a lot of real world data sets, with the general derivation that if things are distributed symmetrically on a log scale, then the law holds. However, it's not obvious to me: Why ...
John Targaryen's user avatar
1 vote
1 answer
2k views

Why AIC for log-linear model in glm returns Inf?

I am trying to calculate the AIC for log-linear model in R, but i get Inf as a result. The model aim is to predict sales in euros based on some variables. As far as ...
AAAA's user avatar
  • 143
2 votes
1 answer
213 views

Can't find loglinear model's corresponding logistic regression model

I have the loglinear model with parameters x, y, z, v, xy, xv, and z*v. As far as i understand there should exist a logistic regression model that essentially is equivalent to this, using v as ...
Polarni1's user avatar
2 votes
1 answer
176 views

Can $G^2$ statistic in log-linear model for contingency tables be negative?

Can $G^2$ statistic of log-linear (unsaturated) model in contingency tables be negative? Since saturated model with perfect fit has $G^2=0$ I don't think the unsaturated models can get negative $G^2$. ...
Nuclear241's user avatar
1 vote
1 answer
106 views

log-linear modelling: transforming y variable

I am conducting a study on graphical log-linear modelling and my aim is to fit a log-linear model to data. I am using R studio to carry out the analysis and I am using the glm function. When first ...
Ng123's user avatar
  • 53
0 votes
0 answers
119 views

How Can I Interpretation in loglinear regressions with coefficients greater than 1

I run a loglinear regression and got dummy variable coefficient for education level bigger than one. It's also significant and my depend variable's log wage. How would I go about to interpret the 2.21?...
Max Payne's user avatar
1 vote
0 answers
41 views

Correlation of categorical data to binomial response in R

I'm looking to analyze the correlation between a categorical input variable and a binomial response variable, but I'm not sure how to organize my data or if I'm planning the right analysis. Here's my ...
Crawdaunt's user avatar
0 votes
0 answers
180 views

Mean of predicted values in a log-linear model

I run a log linear model $$\log(Y)=\alpha + \beta X + \epsilon$$ and wonder how to calculate the mean of predicted values, in the same dimension as the initial (untransformed) variable Y. I would ...
thogs's user avatar
  • 41
2 votes
1 answer
56 views

Log-linear fit and parameters in case of perfectly correlated variables

Here is an example case. Take the following ´data´: ...
Davor Josipovic's user avatar
1 vote
1 answer
151 views

Check if dropout rates are independent for an interaction of two independent variables (one with a large amount of levels)

I am trying to analyse dropout rates in an experiment, but there are multiple issues which collide, and I don't know how to deal with them as a whole. First, find a list of those issues. Below, see a ...
einGlasRotwein's user avatar
0 votes
0 answers
100 views

interpreting a log-log-linear model of two continous variables with or without interaction terms

I am regressing ecological distances between communities (as expressed as similarity) over their spatial and temporal distance on a regular grid of 360 sampling stations divided over six time points. ...
nouse's user avatar
  • 258
1 vote
1 answer
377 views

Statsmodels - 'corrected predictors' on log-linear models?

I'm currently working through an econometrics book , and in the section about log linear models it is stated that predictions made with ...
Jasper's user avatar
  • 215
0 votes
0 answers
161 views

Log-linear model for contingency table with no fixed count

I have table of counts of born children with four two-level factor variables (mother smoker/nonsmoker, child born dead/alive, ..). I would like to use log-linear model to understand interactions of ...
Avec's user avatar
  • 1
0 votes
1 answer
265 views

Help needed to Interpret ln(y) = a +b (Standardized X)

I am analysing server data and I have a scenario where I need to get the % by which Y is changed because of a unit change in X: EDIT: I am doing a Linear Regression in Python (and its other forms ...
Sherin Varghese's user avatar
2 votes
1 answer
719 views

Appropriate way to visualize significance in 2x3 contingency table using mosaic plot

I've checked multiple threads about handling or visualizing contingency tables, but can't find one that can help my current question. I have a 2x3 contingency table: "group" variable has 3 levels not ...
Pumbaa's user avatar
  • 23