Questions tagged [generalized-estimating-equations]
Stands for Generalized Estimating Equations which is an approach to estimating regression coefficients. GEE can be used on clustered / longitudinal data and has the attractive property that it provides consistent estimators of regression coefficients and unbiased inference even when the association structure within a cluster is mis-specified.
355
questions
0
votes
0
answers
11
views
Coefficient covariance matrix of inverse probability weighted regression
I am interested in computing an estimate $\hat\Sigma_\hat\beta$ of the asymptotic covariance matrix of the parameter estimates $\hat\beta$ in a regression of $Y$ on $\{X, Z\}$, weighted by weighs $\...
- 31.5k
0
votes
0
answers
21
views
How to choose between mixed effect and GEE
my outcome variable is on patient discharge disposition, with three categories(1.home,2.nursing home 3. hospital)
my independent variable is based on hospital characteristics, eg bed (1. <500; 2.&...
2
votes
1
answer
38
views
How to analyse a non-inferiority trial using GEE in R?
I'm trying to analyse a non-inferiority trial in R. Since there are correlated observations and a population averaged interpretation seems fine, I want to use GEE.
To illustrate my problem, I will use ...
9
votes
3
answers
337
views
longitudinal data with unequal samples and end points
I've been asked to look at a dataset of repeated measures taken during exercise in participants under two conditions control and ...
- 113
1
vote
0
answers
8
views
Managing Daily Quotas with Complex Equation for Resource Allocation
I have a complex resource allocation problem where I need to manage specific quantities while adhering to a daily quota of 3000 tonnes. The allocation is based on various variables, and I'm looking ...
0
votes
0
answers
18
views
Having trouble with geeglm convergence
I am trying to implement propensity score weighting in a GEE model with geeglm. I am also using bootstrapping to estimate the standard errors. However, I am running into a strange convergence related ...
- 670
1
vote
0
answers
12
views
Variable Selection for GEE or other Longitudinal Methods When Dealing with Many Variables?
I see the question of model selection for GEE come up and answers seem to usually involve QIC/MLIC for non-nested models, or LRT for nested. That's all fine, but when I have 50 predictors it's a bit ...
- 11
3
votes
1
answer
105
views
Where does GEE formula come from?
I am trying to understand where GEE formula comes from.
Here is the formula:
$$Q(\beta) = \sum_{i}^{n} { \frac{d\mu}{d\beta}\boldsymbol{\Sigma}^{-1}(y_i - \mu)}$$
I am just wondering how they came up ...
0
votes
0
answers
11
views
How to calculate R-squared for the unequal number of LST and CO samples?
I want to calculate R-squared from LST and CO data in GEE. However, after considering the revisit time and cloud masking, I get very few data for Landsat-8 with respect to CO data. For example I have ...
- 1
0
votes
0
answers
16
views
How to predict the outcomes form GEE regression across period of time
The recent paper by Liu et al. 2023 (https://onlinelibrary.wiley.com/doi/epdf/10.1002/ajh.26998) describes a single-arm study on crovalimab.
In the maintenance phase (weeks 5 to 25) patients were ...
- 1
0
votes
0
answers
33
views
GEE Using a Bernolli Model and Log link
Conceptually I am interested in a pretty simple question: Do screening rates (dichotomous outcome) differ between an intervention and control group. We have a number of clinics that patients are drawn ...
- 1
0
votes
1
answer
36
views
Why do you always need to interact the covariates with the slope in mutlilevel models?
On a number of occassions, I have seen people remark that you should always interact your covariates with the with your slope when running multilevel models. That is, for example, you should not run ...
0
votes
0
answers
10
views
Logic behind the direction of coefficient in generalized estimating equation
I am not familiar with statistics and thus nor am I familiar with the methodological reasoning behind it so can someone please explain the reasoning behind the following results:
I have an outcome (...
- 1
1
vote
0
answers
17
views
What's the best model GEE or lmer?
I have access to individual data from 3 different studies. The first one has measurements of the variable of interest at baseline and 5 days after the intervention. the second one has measurements at ...
- 11
0
votes
0
answers
19
views
Using Generalized Estimating Equations (GEE) to handle uneven clusters where some subjects have more outcomes than others
If possible, I would like to use GEE to control for clusters in my data where some subjects have more measurement and outcome pairs than others. In this particular case, the outcome is binary and the ...
0
votes
0
answers
35
views
How to transform GEE coefficients to Cohen's d (standardized mean difference) for meta-analysis
I am conducting a meta analysis and am looking into how to convert coefficients (with SEs) from a GEE linear estimation into a standardized mean difference, Cohen's d. Does anyone have any hints on ...
0
votes
0
answers
25
views
Building an adequate statical model
My question is: What statistical model can I use to meet my objective and how can I specify it properly?
DV: MuscleMass
VIs: Age, sex, Intervention (control vs interventions (1 to 7)), and Time.
...
- 11
2
votes
0
answers
44
views
Replicate GEE from SPSS in R - differences in output
I am trying to replicate the results from a GEE I have done with SPSS in R.
The dataset I am using can be found here
SPSS Script
...
0
votes
0
answers
5
views
GEE contradicts descriptives
I'm writing my thesis on the effects of tobacco control policies on tobacco cognitions. One of the cognitions is pro-smoking health beliefs and is a dependent variable in a binary generlized ...
- 11
0
votes
0
answers
19
views
Estimating treatment effects, 2 Group Pre-Post Matched Analysis
I am trying to estimate the treatment effect for a pre/post w 2 groups design, subjects were measured on healthcare utilization 1yr before and after the intervention (non-random assignment). The ...
- 1
2
votes
1
answer
129
views
ROC-AUC in GEE models?
I am wondering if it is possible to make ROC-AUC curves for GEE models? I found few papers who did that and it wasn't clear for me. I thought it was impossible given how they are marginal models. ...
- 31
0
votes
0
answers
75
views
Clustered data: GEE VS GLM with robust S.E
I am trying to understand the difference between running a GEE with robust S.E., vs running a GLM where robust S.E could be calculated posthoc based on the model output. For example, if one considers ...
- 333
1
vote
0
answers
21
views
Longitudinal data in ML vs GEE
I'm currently working with pregnant women data. Given that the same woman could have multiple pregnancies over the years, I tend to use GEE to obtain odd ratios of my variables of interest.
Now say I ...
- 31
0
votes
0
answers
12
views
carry over effect
When testing the carry-over effect (period*treatment) for cross-validation by GEE, do I actually need to bring in the main factors period, and treatment to the GEE model?
(1) Y = intercept + (...
1
vote
0
answers
110
views
Binary logistic regression vs generalized estimating equation (GEE) for time series
I have time series with 322 observations. My dataset contains financial data. My endogenous variable, "target" is a binary variable. My exogenous variables are two continuous variables: &...
- 31
1
vote
0
answers
45
views
Subsequent analysis on estimated marginal means from GEE
I have a set of data measuring response variable (length) on the same individual over several time points in nine different treatments (pH). Due to the confounding effect of temperature and it's ...
- 11
0
votes
1
answer
33
views
How to define interaction between 2 categorical covariates and Time and Intervention in a longitudinal model? (in R)
Dears,
Let's assume, that I have a study like this:
longitudinal, 3 time points, T1, T2, T3. Let's assume T1 is post-intervention.
2 interventions, A and B
2 categorical covariates: Cov1 (2 levels: ...
0
votes
0
answers
26
views
Clusters in stepped wedge cluster randomized trial
I want to run a stepped wedge cluster randomised trial (link), over $N \sim 1000$ cities during $M = 4$ weeks. When I analyze the data of the experiment, at which level should I define clusters (for ...
- 236
2
votes
1
answer
400
views
GEE interaction interpretation
I’m trying to understand the interpretation of interaction terms, specifically in the context of GEE models. I’m familiar with them in conditional models, and am comfortable with marginal effects in ...
- 23
6
votes
1
answer
335
views
Wildly different answers replicating a GEE model from SPSS
Describe the bug
I'm attempting to replicate a GEE model in statsmodels from a published paper that used SPSS (https://pubmed.ncbi.nlm.nih.gov/33279717/). I am getting very different answers for what ...
- 63
0
votes
0
answers
139
views
geeglm correlation matrix interpretation
I chose an exchangeable var-cov mmatrix for my geeglm
...
0
votes
0
answers
59
views
exchangable variance covariance matrix
I was trying to learn how to estimate exchangable correlation matrix. I asked ChatGPT to give me an example so that I can learn the steps and ChatGPT gave me this example
...
0
votes
1
answer
38
views
Cox analysis with a variable exposition with two measures at different times
I measured blood glucose for a sample of 500 participants at baseline and one year after. My issue is death.
I already did a Cox survival analysis for the first blood glucose with my 500 ...
- 23
2
votes
1
answer
88
views
As a researcher dealing with randomized trial, should I use GEE or a GLMM? [closed]
I'm sorry, I searched all topics on StackExchange and cannot still get the difference between marginal and conditional model. All answers tell me the same by showing averaged non-linear curves, which ...
- 41
0
votes
1
answer
32
views
GEE results showing opposite of true marginal relationship with EXCH working correlation
I am working on a modelling issue with two main effect variables: time period and Setting, related to an outcome, with all 3 being binary. My PI wants to test for moderating effects, so we have an ...
- 21
0
votes
0
answers
46
views
If we use the GLS estimation to handle paired data, why can't we use the Welch unpaired t-test as well?
Let's assume I have a paired data to analyse, for example from a longitudinal study.
A typical approach in biosciences is to use marginal (rather than conditional mixed) model, namely the linear model ...
1
vote
0
answers
46
views
When to use GEE vs. GLMM
I'm trying to decide whether I should use GLMM or GEE for my analysis.
My study is repeat cross-sectional using longitudinal data (with 3 timepoints). I have a binary outcome and both continuous and ...
2
votes
1
answer
41
views
How to analyse longitudinal data with 2 to 4 observations per person and varying time between observations
I have clinical data from about 300 patients with repeated measures/observations of psychological distress over time. Psychological distress is measured as a continuous variable, but could be ...
0
votes
0
answers
17
views
GEE how use two different working matrices?
With longitudinal repeated measures of the same person, is it possible to have two different working matrices depending on a the value of a within-person binary predictor variable?
Suppose there are ...
- 143
0
votes
1
answer
137
views
Should be the baseline included in MMRM? MMRM vs. cLDA
In the cLDA (constrained longitudinal analysis) analysis the baseline value is already taken as a response, so it doesn't have to be included on the right side of the model.
But in MMRM ANCOVA (mixed-...
1
vote
1
answer
155
views
Solving estimating equation using R
I am working with different types of data and comparing a variety of estimating equation approaches which share a multi-dimensional parameter $\beta$. Given a set of data $\boldsymbol{X}$, is there an ...
- 36
2
votes
0
answers
93
views
separate models vs joint model
My goal is to estimate the association between children BMI and distance to the nearest fast food restaurants. The hypothesis is that children BMI increases with increasing proximity of fast food ...
1
vote
0
answers
41
views
Testing association in repeated measures with zero in contingency table
I have a small dataset of repeated measures data (each participant (id) has up to two samples taken) and would like to determine if there is an association between ...
- 307
1
vote
1
answer
123
views
Sample size calculation for a difference between two groups with clustered data
I want to compare proportions or means in two groups in a clustered sample. Suppose the sampled clusters are schools or hospitals or Census areas, and we sample from each of these an equal number in ...
- 256
-1
votes
1
answer
57
views
Why does $E\left(y_{i t}\right)=a^{\prime}\left(\theta_{i t}\right)$? in the context of assuming some GEE marginal density?
In generalized estimating equations we have a glm-response variable.
To establish notation, we let $Y_{i}=\left(y_{i 1}, \ldots, y_{i n_{i}}\right)^{\text {T }}$ be the $n_{i} \times 1$ vector of ...
user318514
0
votes
1
answer
82
views
Why is "design matrix of correlation parameters" a proxy for the "actual covariance matrix/working correlation matrix?
The example shows that knowing the design matrix of correlation parameters is sufficient to specify the working correlation.
...
user318514
0
votes
1
answer
352
views
Are the model residuals from GEE interpretable as residuals from simple linear regression?
Are the model residuals from GEE interpretable as residuals from simple linear regression, so that I may plot a residual versus fitted plot to determine whether there's heteroskedasticity?
It is known ...
user318514
0
votes
0
answers
215
views
How to obtain "normalized" model residuals for Generalized Estimating Equations?
How does one compute the "normalized" model residuals based via geepack's geeglm/gee in R?
The nlme package in R allows one to compute the
normalized model residuals:
(standardized ...
user318514
2
votes
0
answers
87
views
Does the sandwich-estimate eliminate heteroskedasticity in a model residuals versus fitted plot, or simply make the estimation robust to heteroskedas? [closed]
Does the sandwich-estimator/Huber-White/GEE eliminate heteroskedasticity in a residuals versus fitted plot, or simply make the model robust to it?
user318514
1
vote
0
answers
49
views
Why are fisher-scoring estimates of the fixed-effects not used to calculate empirical bayes estimates of random-effects? Are they in-admissible?
Why is it not practiced using estimates of fixed-effects from fisher scoring used to calculate GEE coefficients to estimate random-effects via empirical bayes? We have another estimate of $\theta$ in ...
user318514