Questions tagged [logistic]

Refers generally to statistical procedures that utilize the logistic function, most commonly various forms of logistic regression

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

How to use gsem when the independent variables are binary?

According to this website, "Binary—probit, logit, complementary log-log". But does the "binary" here mean independent variable or the latent variable (that is determined by the ...
0
votes
0answers
11 views

How to interpret the marginal effects (MEM) of binary variables in R?

My model is binary logit regression and the dependent variable is default (whether a loan would be defaulted, if it was, it is given a value of 1). I ran logitmfx (...
0
votes
0answers
9 views

Constrained regression parameter and reparametrization in conditional logit model

I'm trying to replicate this paper which contains a specific function for a conditional logit model that contains a parameter $\beta$ that should (theoretically) lie between 0 and 1. I have simplified ...
0
votes
1answer
18 views

What are the preliminary analysis before running a logistic regression?

I have a dichotomous variable which represents if a student is accepted or not in a University. In order to do this I have about 60 variables (information of the students: gender, age, etc; their ...
0
votes
1answer
28 views

Understanding the connection between binomial (logit link) and emmeans output

I ran a binomial model with a logit link in R. I am trying to understand the coefficient relation to the logit scale output provided by the emmeans package in R. Idled is the reference level for "...
1
vote
0answers
7 views

How would you transform a percentage dependent variable to fit a logistic regression? [duplicate]

I have a outcome variable that is a percentage (proportion). According to this, I should probably use a logistic regression: What are the issues with using percentage outcome in linear regression? My ...
0
votes
0answers
9 views

Using Logistic regression in record linkage

I am curious as to how logistic regression handles string variables in a training matched data set I am aware many use Logistic regression to categorize data that includes the process of matching ...
1
vote
0answers
28 views

duplicate feature with same data in logistic regression

this is not a duplicated question What happens if I train a model on a data set that includes a duplicated feature? we have some feature such as x(1) and the label is y(1). we add a new feature that ...
0
votes
0answers
14 views

In binary logistic regression, how do you interpret a categorical-by-categorical interaction term?

I am working with multiply imputed data and I have run a logistic regression model with 6 predictors (3 dichotomous and 3 categorical) and their interaction terms, controlling for a number relevant ...
2
votes
1answer
27 views

GLM weights vs. identical observations

I was recently working on a homework assignment on binary GLMs and the following question came up when comparing solutions with a classmate. The data for the problem was given as a contingency table, ...
0
votes
1answer
10 views

Testing reliability of regression coefficients

If I run a logit/linear regression for the purpose of measuring marginal effects and estimating the causal impact of a specific independent variable on the dependent variable, is there a reliable way ...
0
votes
1answer
15 views

How to prepare a 2x2 Confusion matrix for binary classifier [duplicate]

Problem statement: Evaluate a binary classifier. There are 50 positive outcomes in the test data, and 100 observations. Using a 50% threshold, the classifier predicts 40 positive outcomes, of which 10 ...
0
votes
0answers
11 views

Logit Laplace Loss Function

In a recent OpenAi paper, the authors propose a novel loss function for the reconstruction term of a VAE coined Logit-Laplace loss. They detail the math on page 13 of the paper but I am having trouble ...
0
votes
0answers
18 views

Event-based markov chain with observed covariates at non-constant time intervals

I am working on a project where I need to identify the traffic state at intersections. More specifically, I want to classify the situation in 5 states: undersaturation (where the traffic needs to stop ...
0
votes
0answers
21 views

Comparing disease variants prevalences in R

I have minimal data on disease variants prevalence in two periods of time. An example of the data I have might be represented with the following code: ...
0
votes
0answers
19 views

Marginal effect of discrete R.V. in multinomial or binary logit

I am trying to prove a formula for the marginal effect of a discrete random variable in the context of multinomial logit. Strictly speaking, I believe this could be solved in a logit framework as well,...
0
votes
1answer
21 views

Am I coding dummy variables for disease groups correctly in logistic regression?

Normally I would code my dummy variables as follows: Original variable levels Dummy_disease1 Dummy_disease2 Dummy_disease3 Disease 1 1 0 0 Disease 2 0 1 0 Disease 3 0 0 1 However, I dont want to ...
1
vote
1answer
26 views

Propensity score matching - different sample size

I have a dataset with death outcome and around 25 independent variables. I am planning to use logistic regression with PSM to understand the effect of treatment (a specific drug) which is one of the ...
0
votes
0answers
44 views
+100

Show that classification tables do not always correlate with goodness of fit for logistic regression

Background I am reading the textbook Applied Logistic Regression by David Hosmer, specifically chapter 4, which discusses logistic regression model assesment of fit. Hosmer gives an interesting ...
2
votes
1answer
76 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 ...
0
votes
0answers
27 views

How to report odds ratio with confidence interval when it looks like this [closed]

OR 2.5 % 97.5 % p (Intercept) 0.036616 0.030116 0.0509 <2e-16 *** weight 1.000231 NA 1.0043 0.9458 Above is the ...
0
votes
0answers
9 views

Are there models of choice that allow for dependence between choices

For example, say you were modelling the winner of a running race, with a binary outcome of win/not win. You had a vector of information for each runner (X). This includes things like recent form, ...
0
votes
0answers
13 views

Linear Models vs XGBoost

I am exploring the utility of logistic regression versus boosted tree methods (ie. XGBoost) in real world datasets. I am struggling to find situations (medical datasets) in which 1 model outperforms ...
0
votes
1answer
38 views

Separate Bonferroni corrections for multiple categories

I have a study in which we are looking at healthcare costs and utilization by patients with a disease vs. healthy controls (HC), as well as by different stratifications of disease (severity, ...
0
votes
2answers
21 views

Urn Probability Questions [closed]

An urn has 5 black balls and 4 white balls in it. We randomly sample a ball, and return it to the urn (sampling with replacement), until we get 2 balls with the same color. What is the probability ...
0
votes
0answers
18 views

Regression with binary dependent and independent variables [closed]

I have an inspection dataset that consists of 5000 inspections for a given year with 20 requirements/check-point for the inspection. Both my dependent (inspection outcome) and independent (...
1
vote
1answer
36 views

Applying a Hessian matrix to a logistic function in R

I'm using the following code to implement the logistic regression function so I may get the result for that of a Hessian matrix. I start with the function defined as $\frac{1}{(1+e^{-x})}$ called &...
1
vote
1answer
28 views

How to analyse data using Likert scales? [closed]

have a dependent variable scored from 2 to 10 (this is calculated from two questions with a 5-point Likert scale, strongly disagree to strongly agree, one of which is reversed) I have 5 independent ...
0
votes
1answer
17 views

Dependent Variable between 0 and 1 that can only take on a few possible values

I've looked into other questions that dealt with what regression models to use when the dependent variable is continuous between 0 and 1 (some people have mentioned fractional logit, GLM, and even OLS)...
0
votes
1answer
27 views

Logistic regression using a predictor that's part of the outcome

Say I have 2 continuous variables measuring the same thing (e.g., at-home blood pressure monitor and in-office blood pressure cuff with in-office measurements being the gold standard). At a cut-off of ...
0
votes
0answers
15 views
+50

Can diagnostic accuracy measures be used in case-control studies?

I want to assess the predictive ability of biomarkers in a nested case-control study. The primary analysis with use conditional regression. I’d some questions: 1)Can I determine the AUC, sensitivity ...
2
votes
2answers
60 views

Which statistical test to compare same model with different parameters?

I have two datasets on people buying apples based on weight and price. One dataset in 2019 the other in 2020. I estimate a logit model with Utility = betaWeight * weight + betaPrice * price. Training ...
0
votes
1answer
17 views

When you dummy encode for logistic regression, how do you determine the feature importance for the reference group?

Say you have an IV that can be k different categorical values, and you are trying to do logistic regression. To avoid multicollinearity, you dummy encode the IV into k-1 variables, with one of the ...
0
votes
0answers
9 views

In multiclass classification, why do we have K but not (K-1) output units for softmax layer?

In binary classification, if we can transform the softmax function (needs 2 outputs) to sigmoid function (needs 1 output): $$\begin{align*}\mathrm{Pr}(Y=0|X)&=\frac{e^{b_0\cdot X}}{e^{b_0 \cdot X}+...
0
votes
0answers
15 views

How to add a correction to the parameters in logistic regression s.t. the decision boundary is corrected?

Sometimes we would like to correct the decision boundary of a pretrained logistic regression model $p(y_{temp}=1|x)$, for example by multiplying by a prior in pursuit of adapting better to the ...
0
votes
0answers
23 views

does mlogit and mnlogit in R require choices to be chosen at least once?

I am fitting a logit model with many choices (17665) and individuals (767). Its a recreation demand model where people are choosing to go to coastline segments with attributes and travel costs to get ...
0
votes
0answers
20 views

Logistic regression with latent classes

For my thesis I have to model a binary outcome variable (1, 0) on a set of independent variables. The data covers multiple months and tracks different users of an app. Each week the users have to ...
0
votes
0answers
9 views

Are the statsmodels and sklearn implementation of multinomial logistic regression equivalent?

I'm trying to wrap my head around multinomial logistic regression for k classes. It looks like one formulation of the problem is to do k-1 binary logistic regressions with one class as a "pivot ...
0
votes
0answers
12 views

Interpreting a binomial regression model in R [duplicate]

I have built a binomial regression model using the equation: ...
0
votes
0answers
11 views

Predict probability of association using Bayesian logistic model in R

I am developing a ordered logistic regression model from a survey conducted where y variable takes on 5 ordinate values: ‘very good’, ‘good’, ‘neutral’, ‘bad’ and ‘very bad’. I have one x predictor ...
0
votes
0answers
11 views

Why is ROC a ranking metric and how do we understand it as a c-statistic?

I have been stuck on this topic for quite a long time. I still do not understand why AUROC is a ranking metric. In particular, what does "ranking" mean in AUROC? When I tried to code ROC out ...
1
vote
0answers
11 views

Regression coefficients in multinomial logistic regression model

I'd like to determine whether the outcome (recovered / dead / transfered to another department) is influenced by a person belonging to an age group. I have data of approx. 235 subjects. There are 5 ...
1
vote
0answers
19 views

Using multiple probability cutoffs for a logistic regression model?

Have data with "valid" and "invalid" classes, lots of predictors, over 15. Only 5% of data set is valid (success class 1), 95% is invalid class 0. The number of invalids is skewing ...
0
votes
2answers
31 views

How to recover fitting values from logit transformation

I have dependent variable y belongs to (0,1).I want to use logit transformation of this variable ln [y/(1-y)]). My question is ...
0
votes
0answers
21 views

How to prove that fitting local logistic regression model amounts to smoothing binary indicator?

I'm working on Exercise 6.5 in the book "The Elements of Statistical Learning"(not as assignment). I'm not even sure if my understanding of the problem is correct. In the simplest case where ...
0
votes
0answers
11 views

Should I handle outliers before running a logistic regression classifier?

I am doing binary imbalanced classification on large high-dimensional data (~260,000 observations with 50+ features). First I want to run logistic regression to set it as benchmark when comparing ...
0
votes
0answers
25 views

WOE logistic regression model with 61 variables, will it cause overfitting?

I've been working a WOE logistic regression model and the data I have is 2878 observations with 814 variables. I used the elastic net to create a penalized regression model so the overall variables ...
1
vote
1answer
76 views

How can I cure non-normality of residuals in logistic regression?

I am running a logistic regression against the "Default" dataset of ISLR. I am using the performance package in R (available on CRAN) to test the goodness of my model. MWE: ...
2
votes
0answers
19 views

Is it correct to combine any feature selection (backward/forward/stepwise) with regularization in logistic regression?

I use stepwise regression for exclude "worst" features (based on p-value) and after try to build model with L2 regularization on selected features. Emperically, this model is better that ...
0
votes
0answers
12 views

Obtaining odds ratios from probit (or multinomial probit)

I have an option to run a multinomial logit or probit model on two outcomes (response and remission) to assess treatment effect (T=1 or T=0 is placebo). Any patient with remission also has response, ...

1
2 3 4 5
141