Questions tagged [multilevel-analysis]
Statistical analysis of datasets comprising several levels of hierarchy (e.g., students nested in classes nested in schools or hierarchical forecasting). For questions about mixed models use [mixed-model] tag. For nested random effects, use [nested-data].
1,490
questions
0
votes
0answers
8 views
Multilevel logistic regression: is it possible to apply
We conducted a study and the results submitted to a journal and one of the reviewers suggested me to conduct a hierarchical logistic regression. Basically I know how to conduct multilevel regression ...
0
votes
0answers
19 views
Best model choice for data with patients having >1 observations? Multi-level logistic regression? Robust standard errors?
I have a dataset of admissions to emergency dept's over a 2yr period. The outcome is binary and "rare-event-ish" (10% of total). We're mainly interested if certain patient characteristics ...
0
votes
0answers
14 views
Mixed models: Why can level-2 variance increase when adding a random slope?
I have a three-level hierarchical model with students nested in classrooms and in schools. When I allow one of the level-one binary variable slopes to vary randomly across classrooms, the between-...
0
votes
0answers
21 views
Why not accounting for a factor unrelated to treatment makes p-values too conservative?
I would like to know if a treatment works, but different subjects are measured across different sites. The site is unrelated to treatment, but it is related to the response (see the figure).
If I put ...
0
votes
0answers
14 views
Means-as-outcomes Regression Model with latent variable predictors at Level 2
I plan to estimate a structural equation model with several latent variables (e.g. importance of comfort when choosing a car) as predictors of a dependent variable which is a proportion:
number of ...
0
votes
0answers
12 views
Multiple imputation when several variables of interest are missing
I'm using multilevel multiple imputation to account for missing data in a dataset that is in long format. I have variables that include some missing data including the main outcome (ordinal) and ...
0
votes
0answers
20 views
Code help - a mixed model lmer- hierachy level 1 response variable and all Level 2 explanatary variables and an additional crossedrandom effect
I am running a mixed effect model using lmer in lme4.
I was wondering if someone can tell me if this is the correct code to include Fixed effects that are recorded at a different level to the response ...
0
votes
0answers
23 views
Analyzing Group-Level Outcome Variables from Variables Measured at the Individual Level
I am trying to run a multilevel model to see if my IV's have an association with my DV as well as see if there is a moderating effect of 'task'.
My sample consists of 4 teams with 4-5 members each.
...
0
votes
1answer
16 views
Modelling strategies for analyzing an effect of a predictor through higher hierarchical level
What strategies can be considered when a predictor's direct effect can not be measured directly due to unmeasured confounding? However, data has a hierarchical structure (patients within regions) that ...
2
votes
1answer
50 views
How to calculate “by hand” between group variance and the ICC for a three-level hierarchical model?
Introduction:
This question is related to this and this questions that were answered before, but I would like a more detailed answer on how between-groups variance are calculated in a (null) three-...
0
votes
0answers
14 views
Mixed Repeated Measures ANOVA vs. multilevel random effects model
I have a dataset that contains survey responses from participants attending a training workshop. Surveys were administered prior to training, just after training, and 3 months post training. Moreover, ...
1
vote
0answers
11 views
Meta-analysis_studies with within and between study design
I am trying to run a meta analysis based on the question if physical activity leads to an increase in cognitive functioning.
I have studies that report mean and standard deviations for the ...
0
votes
0answers
10 views
Multivariate multilevel regression and post-stratification
Multilevel regression and post stratification is (among other things) a way to deal with a non-representative survey sample. All examples I see in the literature either focus on a single survey ...
1
vote
0answers
22 views
Can a grouping variable also be a predictor or vice versa
I sometimes see that a grouping variable such as study ($1,2,...15$) is used as a grouping variable to the right of the |:
...
2
votes
0answers
19 views
Multilevel modelling and cointegration, can the two methods be combined?
I am an epidemiologist, but not a statistician. I have a good enough handle on longitudinal multi-level models to push through the material and publish a paper, but my knowledge of all possible ...
0
votes
1answer
38 views
Hierarchical circular-circular regression in R
I have two circular variables and I want to see if they're correlated.
The data comes from a hierarchical and unbalanced experimental design: each participant provided multiple responses and there's ...
1
vote
0answers
7 views
multilevel regression model for nested data?
Hypothesis 1
Independent variable = Thermal inertia (TI)
Dependent variable = Depth diameter ratio (d/D), Radii variation (RV) and Rim irregularity (RI).
Hypothesis 2
Independent variable = Thermal ...
1
vote
0answers
14 views
hierarchical models and m:m/matrix relationships
I have a still rudimentary understanding of hierarchical models so please bare with me. The standard text book example uses a tree/hierarchical structures like this:
...
0
votes
0answers
23 views
MLM Center Level 1 Variable with little variance
I'm conducting a multilevel logistic regression in R using glmer. I have 1 IV and 1 DV - both at level 1.
I planned to cluster-mean center my level 1 IV; however, it has no variance in the majority of ...
2
votes
1answer
79 views
Meta analysis- multivariate or multi-level model?
I am conducting a meta-analysis to understand the impact of an intervention X on people’s responses as measured by three categories of measures. I have a couple of questions regarding the methodology:
...
1
vote
0answers
23 views
two levels spatial regression in r
I need help to find the proper approach in R for an analysis of data. I have measures of a variable Y for various individuals, distributed in various geographical ...
1
vote
0answers
11 views
Predicting changes in values across two time series
I have data from an experiment in which participants provided time series data tracking their emotion (on a scale from -10 to 10) after experiencing two discrete stimuli. Data were collected at a rate ...
1
vote
0answers
18 views
Rules for deriving correlations of alternate contrast coding schemes?
Imagine a hierarchical data scenario where each of multiple people are observed many times for each of combination of a two two-level (lo-vs-hi) predictor variables. If sum contrasts are used to ...
4
votes
1answer
17 views
Asses significance in parameter differences in a multilevel model
lets say I have a model hierarchical model. 15 Observation per Individual which are allocated in one of three Condition.
Observation| Individual | Condition
I have a single independent variable (IV) ...
1
vote
0answers
9 views
Problems with 0s when centering a dummy variable within cluster
Supposing that I have a set of data that is structured like this:
customerID
orderID
couponUse
purchaseQuantity
1
1a
1
3
1
1b
0
1
1
1c
0
1
2
2a
1
5
2
2b
1
2
3
3a
1
6
3
3b
1
3
3
3c
1
7
3
3d
1
...
1
vote
0answers
56 views
Bayesian estimate of treatment effect for within-subjects and between-subjects design
Let's say I'm running an experiment with an experimental condition and a control condition, where four subjects in total provide two reaction times each. I'm interested in estimating the treatment ...
1
vote
0answers
21 views
Between Subject Covariates and Within Subject Variables in Longitudinal - Long format data
I have a longitudinal nested and crossed design dataset with both between-subject covariates and within-subject variables. My study design is below in figure 1.
As shown, the between-subject variable ...
0
votes
0answers
35 views
How to handle exces zero's in a continuous (multilevel) outcome: two-part model or Tweedie distribution?
I am trying to fit a hierarchical model on a continuous outcome that has excess zero's. This is what my data looks like:
The formula for both the main part as well a possible zero-part of the model ...
0
votes
0answers
20 views
Multilevel 3-step latent class analysis: Accounting for group at multiple phases of the 3-step method?
I conducted a multilevel latent class analysis with a large dataset gathered from five different sites, with site specified as the grouping variable. The best fitting model included 2 classes and only ...
3
votes
1answer
41 views
Manually dummy-coded variable works but its factor version fails in a mixed model
In my dataset, I have created two variables from a binary factor called name. Specifically ...
0
votes
1answer
16 views
Correlation between daily average and individual observations
I just want to calculate the correlation between two variables. One of them ($Y$) is measured daily while the other ($X$) is measured multiple times per day. The two obvious options are:
Calculate ...
1
vote
0answers
116 views
Different underlying parameter estimates for GAM fits
I'm puzzling over why I get dramatically different results fitting multilevel GAM models in two distinct, but closely related, ways. As a bit of background, I have a sample of 300 ...
1
vote
1answer
22 views
How to analyze Level 2 outcome variable when Level 1 parameters of the same person are drastically different
I have a dataset with eye measurements (retinal thicknesses) of 250 participants (500 eyes). This data is cross sectional.
I am trying to build a model where the eye measurements can predict the brain ...
0
votes
2answers
27 views
Fitting a Poisson GLM with level 1 and level 2 predictors
I'm trying to fit a GLMER poisson model with level 1 and level 2 predictors. There's plenty of information in this website about fitting a Poisson GLM with level 1 predictors. My question is whether ...
0
votes
0answers
11 views
Multilevel and Longitudinal Logistic Regression
Thank you in advance.
I have a dataset measuring individual gun carrying behavior (binary) and other time-stable (e.g., race/ethnicity, gender) and time-varying (e.g., substance use) covariates for 10 ...
1
vote
0answers
11 views
Interpretation of predicted probabilities of multi-level logit model when “integrating over the random effects”
Let's say I run a single-level logit model of "being depressed", as a function of age (in years) and opiate use (binary). The model looks like this
$Pr(Y_i=1)=\frac{exp(\beta_0+\beta_1Age_i+\...
2
votes
1answer
85 views
Defining the model syntax of an lme() model based on an nlme() model
I'm trying to replicate the output of mg4.math.nlme model fit via nlme() function, using the ...
0
votes
0answers
113 views
“Random” slopes in GAM(M)s
I could use help thinking through how to specify a set of random effects in a GAMM.
My data are repeated measures of neighborhoods (tracts) across time (...
0
votes
0answers
11 views
Modeling and comparing repeated measures regressions
We have the following data: Subjects rated emotionality of three events that differ in terms of expressions (i.e., repeated measures DV with three levels). Then, for each of these emotionality rates ...
0
votes
0answers
7 views
Multilevel Model Specification with duplicated rows
I have a dataset that has 360 households from 60 villages (cluster variable). I have a single water quality data point for each household (HHWAT) and a range of water quality samples from 1-5 samples ...
0
votes
0answers
13 views
Is Beta-Geometric a continuous mixture or a multi-level Bayesian model?
Bruce Hardie, an authority on statistical marketing wrote this reference, which covers various probabilistic methods for various marketing use cases. Specifically, on slide 23 he details a Beta-...
1
vote
1answer
58 views
Multilevel model with crossed random effects?
I'm trying to figure out to "best" specify a model in lmer. Any insight is appreciated!
For background information, my data are repeated measures of some ...
0
votes
0answers
11 views
Multi-level model with crossed random effects, robust standard erorrs yield different results
I'm having trouble setting up a multi-level model with crossed random effects (I just started
getting into the topic).
My data:
Observations (n = 122) are an appearance of a speaker (n = 81) at an ...
0
votes
0answers
36 views
Negative % variance explained for Cross-validated Hierarchical Generalized Additive Model
So I have a dataset I've split into training & test with an 80/20 ratio. It's a hieararchically structured dataset, individual human participants each with many observations, so when splitting I ...
0
votes
0answers
5 views
Definition of a link function (brms or multilevel model -associated)
I have one question related to a link function defined in BRM.
According to the reference (Bürkner, Paul-Christian. "brms: An R package for Bayesian multilevel models using Stan." Journal of ...
0
votes
0answers
9 views
Independent variable groups in multilevel clusters
I have a question regarding multilevel analysis:
Suppose I have data on 1,000 students from 10 universities, and let's say I have an independent variable called "Major", which states if the ...
0
votes
1answer
15 views
How do the -me- commands in Stata deal with missing data?
I am running several melogit commands whereby I am accounting for clustering of individuals (it is a repeated measures design). So, I have melogit commands that look like this (increasing complexity).
...
0
votes
0answers
11 views
Issues when using independent variables from two levels for prediction on single level
This is my first question here and I want to make sure I am giving as much relevant background as possible, so please bear with me!
I am analysing the factors influencing commute mode choice in ...
0
votes
0answers
14 views
Specifying the linear predictor for logistic multilevel model in longitudinal dataset
I am running a random intercept model on a longitudinal dataset where I am interested in examining the association between certain protective/risk factors and suicide ideation among a group of ...
0
votes
1answer
42 views
What are the assumptions that need to be checked for multilevel logistic regression and for multilevel ordinal logistic regression
I am running multilevel models for panel data on a binary outcome (mixed logistics regression) and on a ordinal outcome (mixed ordinal logistic regression).
I am aware that for example with a mixed ...
