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
0 answers
11 views

What critical level to use in diagnostic tests for model selection in forecasting?

I have been reading Hyndman & Athanasopoulos "Forecasting: Principles and Practice" (newest edition here) recently, and I noticed something that I regard as a possible inconsistency. On ...
Richard Hardy's user avatar
1 vote
1 answer
51 views

Issues with metaprop function for computing pooled specificity in meta-analysis

I am training to learn how to perform meta-analysis using R. I conducted a meta-analysis using the metaprop function in R with the provided dataset. The goal is to ...
Reza Khayami's user avatar
5 votes
2 answers
254 views

Residuals vs fitted values plot interpretation for "striped residuals"

I tried to run a simple linear regression in R, and when I check for the linearity, my "Residuals vs Fitted" graph is like this: Are the points randomly scattered? Or this showing a pattern ...
Reimy Tan's user avatar
3 votes
2 answers
151 views

Interdependence between leverages and residuals

According to the following online quote I read online: It’s worth noting that an observation can have a high absolute value for a standardized residual, yet have a low value for leverage. My ...
Andrea Catucci's user avatar
0 votes
1 answer
87 views

Impact of outliers to QQ plot

I'm trying to build an GLM regression (10k samples and 50 dimensions). I ran an analysis of the dependent variable since the regression has a normality assumption for the dependent variable. The QQ ...
cat's user avatar
  • 53
0 votes
0 answers
12 views

What are the main differences between a traditional receiver-operating curve and a Lorenz curve?

I am analyzing a dataset of cardiac echocardiographic exams, aiming to compare the diagnostic accuracy of a novel test in comparison to a standard one. I have recognized that using Stata I can ...
Giuseppe Biondi-Zoccai's user avatar
0 votes
0 answers
37 views

Check linearity Residual vs Fitted Chart

I have a question about one of the simple linear regression test graphs. Looking at the graph it apparently appears to be linear but this curve is causing me a lot of doubt, I did another test that I ...
user avatar
2 votes
1 answer
26 views

ARIMA - Identifying an outlier in residuals

I am trying to perform an ARIMA (SARIMAX in fact) and when looking at the residuals I see a large outlier. I am using python statsmodels.tsa.statespace.sarimax. I ...
Solebay Sharp's user avatar
2 votes
1 answer
16 views

How to interpret this model diagnostics?

A model was fit as below: m1 <- lmer(log (ld50) ~ var * strain * time + (1|rep) + (1|rep:var) + (1|strain:env), dt) The response ld50 ranges from 0.15 (lower ...
Rabin KC's user avatar
2 votes
1 answer
53 views

GARCH diagnostics via standardized residuals: interpreting my findings

I have fit a GARCH(1,) model in Python, assuming the residuals are $t$ distributed. I am checking the standardized residuals. ARCH and Ljung-Box tests don't reject the null hypothesis. However, I am ...
Mattia's user avatar
  • 129
4 votes
3 answers
225 views

How to compare influence of outlier in regression model. ANOVA of two models in R

I am doing linear regression in R. I have identified an outlier in my data: ...
Mark Davies's user avatar
2 votes
1 answer
25 views

standardized residuals GARCH

I am having a hard time understanding ACF and PACF. I estimated a GARCH(1,1) model and now I am checking its standardized residuals. This is what I get: I can not really understand why the lag 0 has ...
Mattia's user avatar
  • 129
2 votes
1 answer
80 views

What aspects should I test from a fitted GARCH model?

I estimated a GARCH(1,1) assuming that the residuals follow Student-$t$ distribution. ...
Mattia's user avatar
  • 129
0 votes
0 answers
8 views

Question about residual diagnostic tests in time series

I was reading a chapter from this book on residual diagnostics for time series data. The book presents Box Pierce and Ljung Box test statistics $Q = T\sum_{k=1}^lr_k^2$ and $Q^*=T(T+2)\sum_{k=1}^l(T-k)...
Yandle's user avatar
  • 1,129
0 votes
0 answers
44 views

Gamma GLM goodness-of-fit diagnostics and remedies for double glm

I’m looking for some help in diagnosing a gamma GLM. I am not sure whether the apparently poor fit is to do with the fact that my glm models dispersion rather than the mean, whether I am ...
Fiona's user avatar
  • 1
2 votes
2 answers
212 views

Understanding slope in plot of residuals vs. fitted values

How should I interpret the negative relationship between the residual and the fitted value in the plot shown below?
CCZ's user avatar
  • 21
0 votes
1 answer
35 views

How to diagnose HMC results like r-hat for a Mixture Model?

I have the following distribution $$ \begin{align} \boldsymbol \pi&\sim\text{Dirichlet}([1,\cdots 1]\in R^K)\\ \boldsymbol \theta&\sim P(\boldsymbol \theta) \\ \mathbf y&\sim \sum _{i=1}^K\...
wd violet's user avatar
  • 635
0 votes
0 answers
40 views

Can linear regressions be used, given these diagnostic plots? [duplicate]

I'm using several linear regressions on a big dataset (about 1000 datapoints) with one numerical dependent variable and several independent variables (both dummy and numerical): ...
statuser's user avatar
1 vote
0 answers
29 views

Multinomial gam diagnostic help

I have created a Generalized additive model of a multinomial distribution using the mgcv package, I have used check.gam to do some diagnostic tests but they look ...
G_man932's user avatar
0 votes
0 answers
43 views

Correcting issues with binomial GLM (identified with DHARMa)

I'm working with a binomial GLM that I've fit in R using the glm() function. The percent of deviance explained is decent for my field (35%) and I don't think the residuals vs fitted plot looks too bad....
pfadenhw's user avatar
1 vote
0 answers
381 views

C-statistic vs AUC [closed]

I am analysing diagnostic accuracy. I have a dataset with a ground truth and 3 predictors. Ground truth = binary (0/1) Predictor 1-2 = binary (0/1) Predictor 3 = continuous (0-100) I have 50,000 ...
user12541161's user avatar
0 votes
0 answers
13 views

What is the best way for comparing the diagnostic performance of sequential testing? Log regression? Compare ROC?

I have two index tests, Test A and Test B, both of which have been studied in participants. Every participant also underwent the reference standard. I've found that Test A and Test B perform equally ...
Jorge's user avatar
  • 1
0 votes
1 answer
58 views

Residuals with mean 0 but with bigger standard deviation in regression

When I tried to fit a regression model to my data to predict a power variable using steam at entry and steam at exit variables in a thermal power plant, after taking care of outliers, etc... I fit the ...
Yahya SGHIOURI's user avatar
0 votes
0 answers
14 views

How to determine the best cut-off of measurement numbers for diagnostic decision?

I am currently doing a research on determining a cut-off of a ECG signal's number of 12 patients with their diseased/normal label that is produced by classifier for diagnostic decision purpose. ...
Dziban N's user avatar
0 votes
0 answers
16 views

Intercept residuals correlated with level-one residuals in MLM

I am running my ever first multi-level model. The model has three fixed effects and a random intercept by the grouping factor "participant id". The outcome variable is "bone mineral ...
Trypanosoma's user avatar
0 votes
0 answers
26 views

I need help interpreting diagnostic plots for a glm

I have used a function in the R package boot that give me diagnostic plots for a generalised linear model: glm.diag.plots(). I dont have experience with these, and ...
EcotoxicologyGirl's user avatar
0 votes
0 answers
36 views

Evaluating linear regression model [duplicate]

I understand that when performing linear regression, one common rule-of-thumb is that for a good 'fit', the residuals should be 1) independently distributed, 2) stationary and 3) not serially ...
joaocandre's user avatar
1 vote
0 answers
58 views

How to check assumptions for time series linear regression? [closed]

So, I am checking the assumptions for my time series data. I also did this test and it seems to reject the null hypotheses. Then, to check the equal variances, I made a box plot. So, I found that ...
Priscilla Raj's user avatar
10 votes
3 answers
525 views

How to get confidence interval for the population variance?

I have data that is reasonably assumed to be iid samples from some distribution. Our goal is to put a confidence interval on the population variance. Notationally, we have IID $X_i, i = 1, ..., n$ ...
travelingbones's user avatar
2 votes
1 answer
73 views

Techniques/diagnostics for gaining confidence in normality assumptions and resulting confidence intervals

I have data that is reasonably assumed to be iid samples from some distribution. Our goal is to put a confidence interval on the population mean and have something similar for the population variance. ...
travelingbones's user avatar
1 vote
1 answer
63 views

Comparing binary and continuous predictors for diagnostic test

There is a "traditional" biomarker (binary predictor) used in the diagnosis of a disease (binary outcome) that has a high cost to perform for the clinical labs. I'm studying alternatives, ...
Daniel Nunes's user avatar
1 vote
1 answer
61 views

Statsmodels VAR plot_acorr() amount of plots

I am working on a statsmodels VAR model to forecast some values and want to analyze the created model. In the examples and in some books I read about calculating the autocorrelation of the residuals ...
Krautsultan's user avatar
0 votes
0 answers
43 views

Whether my model follows the QQ plot and DHARMa residual in glmmTMB?

I ran this code and found the result. Could you please help me to figure out my model follows DHARMa residual? ...
Tanjijul Haque Tonmoy's user avatar
2 votes
1 answer
91 views

Validity of Automatic Portmanteau test for serial correlation vs Ljung-Box Test

I would like to model the Value-at-Risk of U.S. sector indices and the U.S. Broad Dollar Index using the variance-covariance method. To achieve this, I model the conditional means and variances of the ...
WebSurfer's user avatar
1 vote
0 answers
58 views

Concurvity involving categorical variables (?)

I recently learned how to test for concurvity on a GAMM I constructed, but I'm confused about how to test if 2 factors (2 categorical parametric terms), or 1 factor and a smooth term, are too closely ...
Nate's user avatar
  • 1,459
2 votes
1 answer
219 views

Understanding residual vs fit plot for mixed effect model with AR1 structure

I am running a linear mixed effects model for time series data using R-INLA. My response variable is normally distributed. The model has a random intercept, and temporal autocorrelation between data ...
user21085294's user avatar
0 votes
0 answers
39 views

Bayesian statistics: Inferring a true value for test sensitivity and specificity

Based on a data set I found a sensitivity (.82) and specificity (.88) for a diagnostic test bases on a n=257 sample. However, I wonder whether I can generalize these numbers. I thought this was very ...
Weflex's user avatar
  • 1
0 votes
0 answers
125 views

DHARMa plots diagnostic

I have performed a linear regression analysis using R and generated some diagnostic plots by using package DHARMa (in R). However, I am having trouble interpreting these plots and would appreciate any ...
sulevon's user avatar
0 votes
0 answers
75 views

Checking assumptions of ANCOVA

I'm trying to run one-way ANCOVA on my data set in R. My dependent variable is continuous, my independent variable is categorical with 4 levels, and my covariates are categorical: One with 2 levels, ...
user avatar
1 vote
0 answers
88 views

How to validate a Bayesian model using posterior predictive check

Prediction ability of a model is usually being used for model validation/evaluation. But in a high noise to signal ratio setting, and when you are not caring about prediction but inference, then ...
Amin Shn's user avatar
  • 755
0 votes
0 answers
60 views

Diagnostic plot of gamma log link model in DHARMa package

I used this formula in Rstudio: model<-glm (NRQ1~Sample, family= gamma (link= 'log'), data =df) and to check the model, I used ...
Elvis Bai's user avatar
1 vote
0 answers
62 views

Singularity in Poisson GLMM - when is it better to switch to GLM?

I am analysing count data (count of observations per day of certain mammal species) at 12 different sites. My dataset consists of ~120 days of observations at each of the different sites. For each ...
hannahdv35's user avatar
1 vote
0 answers
112 views

How to deal with non normality of residuals in VECM?

Does anyone know how to handle non normality of residuals in VECM? I have tried transforming the data into log, exp, and Box-cox but nothing has changed. Any suggestion will do. Thank you.
Anne's user avatar
  • 21
3 votes
1 answer
135 views

Diagnostics in Spline Regression

In linear models, we do statistical tests (e.g. normality of residuals, homoskedasticity, autocorrelation, etc.). In spline regression, using the following method, we are running linear regression ...
ragas's user avatar
  • 215
2 votes
1 answer
84 views

GAMM is producing irregular predicted probability

Predicted Probability of GAMM I've probably beaten this topic to death here, but I continue to have issues with model fitting. Thanks to the excellent advice here, I was able to at least square away ...
Shawn Hemelstrand's user avatar
0 votes
0 answers
88 views

Model diagnostic plots for anova test

Could you please help me in interpreting the model diagnostic plots? I feel there is a problem with the scale-location plot?
Marwah Al-kaabi's user avatar
2 votes
1 answer
440 views

Levene's Test and residuals vs. fitted plot lead to different interpretations about heteroscedasticity

I am performing a one-way ANOVA in R with the following data: Cu Day CC Cu1 49 30934500 Cu1 49 26860125 Cu1 49 46524750 Cu10 49 15272561 Cu10 49 31601659 Cu10 49 17627634 Cu100 49 3718127 ...
Sergio M.'s user avatar
2 votes
1 answer
166 views

Intuition behind martingale residuals and their properties in survival modeling

I am reading Tutz & Schmid "Modeling Discrete Time-to-Event Data" (2016) chapter 4 Evaluation and Model Choice section 4.2 Residuals and Goodness-of-Fit. A martingale residual is defined ...
Richard Hardy's user avatar
2 votes
1 answer
60 views

Intuition behind the null distribution of the deviance statistic in survival models

I am reading Tutz & Schmid "Modeling Discrete Time-to-Event Data" (2016) chapter 4 Evaluation and Model Choice section 4.2 Residuals and Goodness-of-Fit. A goodness-of-fit statistic ...
Richard Hardy's user avatar
3 votes
1 answer
316 views

What is the hat matrix and why is it inappropriate for GLMM standardized residuals?

When I run this code to plot standardized residuals for a standard logistic regression: ...
Shawn Hemelstrand's user avatar

1
2 3 4 5
8