Questions tagged [diagnostic]

Diagnostic measures (such as residuals or some summary statistics calculated from residuals) are used to evaluate some aspect of quality of model fit to data.

Filter by
Sorted by
Tagged with
0
votes
0answers
13 views

Valid alternative to Box Tidwell method for Linear Regression [duplicate]

I am building a Logistic Regression model (in sklearn) and want to verify that the assumption regarding the linearity between X and the logit function is correct. I am using Python so am looking for ...
0
votes
0answers
17 views

How to test linearity in ordinal logistic regression analysis?

One of the assumptions for performing ordinal regression is linearity. How to test this for this specific type of regression? Do you have to use logit etc.? And how does this work in SPSS?
0
votes
1answer
18 views

OLS on autoregressive models

Suppose I have a linear model with strongly correlated residuals. Suppose further that after adding one or more lags of the dependent variable, the residuals no longer appear to be autocorrelated ...
1
vote
0answers
27 views

Help understanding residual vs covariate plots in linear regression when covariate is transformed

I'm self-studying stats and in the books I've studying there usually aren't examples specifically dealing with residual plots for polynomial and spline fits. This has be thinking about residual vs ...
0
votes
0answers
6 views

lightgbm model diagnostics

I am currently building a house price predictor. My lightgbm errors look like the one the one below (illustrative). It shows that there is a pattern in my errors. Can someone explain how to resolve ...
1
vote
1answer
37 views

Interpretation of GAM diagnostics

I am hoping to get some advice on my below gam diagnostics and whether my model needs further refining or is adequate as is? I have conducted a randomised controlled trial to test if tagging impacts ...
2
votes
0answers
42 views

Check assumptions of linear regression before having the final model

There are usually four assumptions associated with a linear regression model: (1) linear relationship, (2) normal residuals, (3) homoscedastic residuals, and (4) i.i.d residuals. I think that it is ...
0
votes
1answer
24 views

Autocorrelation in residuals, what to do next? [duplicate]

I run an OLS, after check residuals, they are normally distributed, mean is zero with some randomness. But after the autocorrelation plot shows significant correlations to 15+ lags. What should I do ...
0
votes
0answers
35 views

Mixed-effects log-linear regression for counts -

I've read other answers but couldn't find exactly what I was looking. I have generated the following contingency table from my data: ...
0
votes
0answers
12 views

Diagnosing model performance in the serving time?

I was reading a very insightful paper from booking.com published at KDD 2019 150 successful Machine Learning models: 6 lessons learned at Booking.com. The paper shares practical lessons from deploying ...
1
vote
1answer
39 views

Variability in the fitted values

For a dataset, I have fitted a model. The fitted or predicted values have less variability than the observed values. What does it imply?
0
votes
0answers
9 views

How to graphically diagnose conditional zero-inflation in count response regression?

Is there any ubiquitous (or not so much) graphical method in count response models (e.g. Poisson GLM) to diagnose conditional zero-inflation? I'm aware of statistical tests that can be used for that, ...
0
votes
0answers
18 views

Will usual tests state that data is overdispersed if response mean in poisson regression can vary greatly?

Assume I have 1000 responses from some count data, where each response follows the Poisson distribution with a mean (and variance) falling somewhere in the large range of 1 - 100. There is one ...
0
votes
0answers
36 views

P-values for sensitivity/specificity when only improvement is possible

Imagine two diagnostic tests in a single population at risk of the disease, one of which is always "more strict" than the other, meaning that if test 1 is positive, test 2 will be positive ...
1
vote
0answers
19 views

How to find out about weird patterns in gam.check of a bam

I run a bam with timeseries data and a response variable defined as cbind(positive, negative), family = quasibinomial (because of overdispersion), a number of interactions, and some random effects. ...
0
votes
1answer
27 views

MASS::glmmPQL diagnostic

I am fitting models with MASS::glmmPQL of the form ...
0
votes
0answers
31 views

(multiple) Infinite/right censored independent values in diagnostics

We are facing a problem with infinite/right censored independent values. Case-control study where decay time (mono-exponential function) and half-value time seems to be of great diagnostic accuracy. ...
0
votes
0answers
65 views

DHARMa package diagnostic plots give different results

I am fitting a poisson GLMM of the type ...
1
vote
0answers
32 views

ARIMA Model Suitability Testing

I'm attempting to forecast 24-month hydroelectric generation at various river systems in the United States. Because river flows -- which is the primary driver behind hydro generation -- are mean-...
0
votes
0answers
15 views

Why is my mixed model predicting outside of my cut-off?

In my study, I'm looking at the effect of transitioning across wealth levels (either from Low to High, or stable (High to High)) and the legitimacy of wealth (Luck vs Merit) on distributive ...
1
vote
1answer
284 views

Interpretation of Ljung-Box tests for GARCH models from the 'rugarch' package in R

I have used the 'rugarch' R package to fit a GARCH model, as: ...
1
vote
1answer
25 views

Diagnostic Meta-Regression with mada in R

I am trying to figure out how to perform a meta-analysis of diagnostic test accuracy studies and I have a doubt that is driving me crazy. I am using the package mada written in R and following the ...
0
votes
0answers
24 views

What pitfalls should we avoid with Heidelberger-Welch convergence

I'm working through validating a Bayesian mixture model for multi-species occupancy with a collaborator. Initially, we relied on coda::heidel.diag to alert us to ...
0
votes
0answers
10 views

Cross sectional dependence

I am working with a panel data set of neighbouring EU countries (n=9,t=24). The variables are CO2 emissions (dependent), GDP, Population and fossil fuel usage. I ran a ridge regression model on the ...
1
vote
2answers
84 views

Ridge regression and autocorrelation

Im currently working with a strongley balanced data set. I have 15 countries over the period 1990-2017. My dependent variable is CO2 emissions. My independent variables are as follows, GDP per capita, ...
1
vote
0answers
28 views

Emergency Use Auth (EUA) for SARS-CoV-2 Tests

Problem: After the EUA for SARS-CoV-2 tests, we have a diagnostic test that passes both of the following criteria: All first five true-negative samples each produce a negative test result. All ...
0
votes
1answer
25 views

Which assumptions do I need to test?

I am currently doing an OLS regression where my dependent variable is a Likert scale going from 0 to 10 and my independent variables are factor variables such as gender, ethnicity etc. Now, I know ...
0
votes
0answers
51 views

How to Test the Dynamic Stability of an ARDL Model

1) I have an ARDL model(1,2,3). How can I test whether it is dynamically stable and the inverse roots are inside the unit circle? Prof. David Giles suggested a trick to do so in Eviews a simple AR ...
1
vote
1answer
118 views

Transformation of residual plot of linear regression model

I have a linear model which is represented by the following plot, with a fitted line: And the residual plot is as following: The distribution of the residuals is show in the following graph: I see ...
1
vote
1answer
60 views

Problematic residual plot

I have created a linear model in R, and then plotted the residuals. If my residual plot looks like this, then which model assumptions are not appropriate?
0
votes
1answer
19 views

How to interpret these conflicting results on normality of the residuals?

I ran a VAR(1) model and got some results. I then moved to "diagnostic tests". The problem is that these tests seem to be conflicting (at least from the way I read them). The ARCH test shows no sign ...
2
votes
0answers
31 views

Multiple linear regression and model build in light of regression diagnostics

I have a dataset of approx. 200 observations, consisting of Profit which is my dependent variable and is continuous, and the independent variables are Turnover (also continuous), and 3 additional ...
4
votes
1answer
183 views

Using splines to address non-linearity in logistic regression

I was wondering if the following is a reasonable way to proceed: I have a number of logistic models, fitted using glm, that I want to use to make predictions. The ...
1
vote
1answer
184 views

Diagnostic plot (residual vs. predicted) of a glmm using DHARMa

I used glmmTMB to fit a model with beta distributed errors, zero inflation, several nested random effects and temporal correlation. I then used the diagnostic plots available in DHARMa. My residual vs ...
2
votes
0answers
104 views

Which method should be used for evaluating the linearity assumption of logistic models?

I’ve come across two methods for evaluating the linearity assumption for logistic regression (i.e., whether there is a linear relationship between continuous predictor variables and the logit of the ...
1
vote
0answers
29 views

How to run a Sargan-Hansen test?

I'm estimating a model with a lagged dependent variable and fixed effects for panel units. I understand that this can result in Nickell Bias but I didn't think it would be a big problem because there ...
2
votes
0answers
151 views

OLRE's vs. Beta Binomial Model for Overdispersed Mixed Effect logistic regression with proportion data?

this is a long post, as I wanted to be sure to provide all relevant information regarding my data, model, the methods that I have tried so far, and my diagnostic plots. If there are ways I should ...
0
votes
0answers
5 views

Two diagnostics tests over time

I have the following problem. I want to compare a self-diagnostics tool (questionnaire based) with a gold standard diagnostic tool. However, I have the following issues: 1- The gold standard is not ...
0
votes
0answers
14 views

combine Accuracy of two diagnostic test

How can one calculate combine accuracy of two independent diagnostic test on the Same population to increase the diagnostic accuracy
0
votes
0answers
17 views

Diagnostic plots GLM [duplicate]

I done a binary regression,it's possible that the the plot of residual vs Predict has two different line? I never see before one like this
0
votes
0answers
24 views

problem with diagnostic plots for binary regression

I make a binary regression to study Italy's poverty/non poverty on R. mod1<-glm(status~CLETA5+cit+AREA3+Q+studio+ACOM5+godabit,data=total,family=binomial) I don't know if the diagnostic plots are ...
0
votes
0answers
71 views

rstandard vs stdres have different behaviour (the hat matrix)

To obtain the standardized residuals in R, the the residuals minus their mean are divided by their standard deviation (calculated with the model degrees of freedom). It is also calculated using the ...
1
vote
1answer
85 views

Why we do acf on residuals?

In the book "Time series analysis" by Shumway. He is doing fit = lm(chicken~time(chicken), na.action=NULL) acf(resid(fit), 48, main="detrended") What is the ...
0
votes
0answers
53 views

t-value of regression intercept

Consider a regression model $y = \beta_0 + \beta_1 x + \epsilon$, where $\epsilon$ is a standard normal random variable. The estimate of the intercept is $\hat{\beta}_0 = \bar{y} - \hat{\beta}_1\bar{x}...
0
votes
1answer
134 views

Using the DHARMa package to test for temporal autocorrelation when time values are not unique?

I have fit a glmm using the glmer function from the lme4 package. I have found the DHARMa package very helpful for evaluating the fit of my model but am stuck as to what to do to evaluate temporal ...
2
votes
1answer
344 views

Diagnostics in DHARMa for glmmTMB model

I am fitting models to a data set with 370 observations. It is ecological data with overdispersed counts as a response variable. I have used the DHARMa package to show this overdispersion from a ...
0
votes
1answer
41 views

Finding the Case with the Highest Influence

I'm new to regression and diagnostics so if this seems a bit basic/unnecessarily long-winded that's why. I perform a multiple regression of a response variable on four predictor variables. There are ...
1
vote
0answers
42 views

Unusual DV Odds Ratio for multiple Binary Logistic Regression

I am attempting to diagnose issues with the DV odds ratio and resulting 95% CI for the final step of my logistic regression. As you can see in the below image, when the "Continuous F" variable is ...
2
votes
1answer
434 views

Regression diagnostics for ordered logistic regression

I am doing a regression with an ordinal dependent variable (answers ranging from very good to very bad) for the first time. The model itself seems to be working fine. I have no idea however which ...
0
votes
1answer
106 views

I tested serial correlation and got a p-value of 0.13, can I accept that there is no serial correlation?

My data are 6 variables × 68 data. Null hypothesis is there is no serial correlation. Is p=0.13 too small? it is very close to 0.1. The significance level I choose is 0.05 though.

1
2 3 4 5 6