15
votes
nls() singular gradient matrix at initial parameter estimates error
There are some things we can do. These are generally useful to know for any kind of optimization problem and are not limited to the nls function in ...
- 334k
9
votes
How can I calculate the required sample size for Latent Growth Curve Modelling?
This is a little bit of a guess about what you want to do.
With the exception of simple/classic statistical tests and models (e.g. 1-way ANOVA, t-test, proportion test, general linear model, etc.), ...
- 47.3k
8
votes
Accepted
How do I interpret a second-order multi-variate growth model?
The first-order factors themselves could not be correlated in a second-order growth model because they are endogenous variables (their covariances are accounted for by the second-order growth factors)....
- 4,333
6
votes
Accepted
Baseline adjustment in growth models: Random Intercept or Baseline Covariate
The random effects (here, intercepts) do not adjust for baseline; they just allow each subject to be vertically shifted by their own customized amount. You'll get more outcome variation explained (...
- 98.4k
6
votes
nls() singular gradient matrix at initial parameter estimates error
The problem seems to be in convergence of the z parameter so fix it at each of a sequence of values and optimize on the others for each and then take the result ...
- 2,030
5
votes
Structural equation modeling (latent growth models): robust estimators to handle outliers?
I personally prefer not to remove outliers unless it is 100% clear that they represent invalid scores. Have you tried a "sensitivity analysis" with different regular and robust estimators ...
- 4,333
5
votes
Is it possible to model a Second-order growth slope factor as a mediator of another second-order growth slope factor?
Technically, it is certainly possible to specify such a model. Whether it makes sense is a substantive rather than statistical question. You would make the assumption that change in one variable ...
- 4,333
4
votes
Accepted
Estimating common slope across two traits for a parallel growth curve model
Yes, you could do this, but it would be weird.
It would be sort of like having a common factor and specific factors in a confirmatory factor analysis, except the factors are growth factors.
I ...
- 19k
4
votes
Accepted
Growth curve model with structured missingness
I agree with your intuition that it would be incorrect to use any imputation scheme here.
The good news is that mixed models can handle this kind of structural missingness "out of the box". ...
- 65.8k
4
votes
Accepted
Effect of robust maximum likelihood estimator in structural equation modelling when data is normal?
are there any disadvantages of using a robust maximum likelihood estimator when the data are normally distributed?
Loss of efficiency. The normality assumption is what makes ML point estimates ...
- 2,652
4
votes
Accepted
Latent growth curve model with a continuous time-invariant covariate, multi-group or covariate model?
You should most definitely not divide your continuous covariate into categories because that would result in an unnecessary and potentially detrimental loss of information (and statistical power). ...
- 4,333
4
votes
How can I calculate the required sample size for Latent Growth Curve Modelling?
almost all power calculations are based on simulations of the proposed model
Indeed, simulation is currently necessary for anything but the ideal case. But if you simulate normally distributed, ...
- 2,652
4
votes
What possible effects to include when running a Mixed Model, time variable and or lags for DV's and IV's?
You ask important questions, which I address below in turn.
1: My main research question is whether or not there is a relation between 'Health Care' and 'Social Support' how should i decide whether i ...
- 5,880
4
votes
Accepted
Standardized or unstandardized coefficients to report? The covariances and regression of a multivariate latent growth model
The covariances between the growth factors tend to be more difficult to interpret than the correlations (standardized coefficients). Nonetheless, for the sake of completeness, reproducibility, and for ...
- 4,333
3
votes
Accepted
lme4 non-linear modelling with missing values
The linear mixed model indeed appropriately accounts for missing at random missing data, given that you have also appropriately/flexibly specified the covariance structure.
As far as I can see in ...
- 21.5k
3
votes
Modeling growth curves with different starting sizes (NLME in R)
You could have a look at the SITAR model and the associated sitar R package. This models allows for the shifts you are describing.
- 21.5k
3
votes
Growth rate vs. Absolute correlations
The growth rate of a series of values is approximately equal to the rate-of-change of the logarithm of the series. (In fact, you can define it that way if you want to measure growth as a continuous ...
- 133k
3
votes
How to run a nls for multiple dependent variables?
Good Morning! As I understand you are wanting to fit a logistic curve to your data, however, when plotting your data, I noticed that they are far away from a logistic curve.
...
- 572
3
votes
Estimating growth rate from noisy data?
It makes sense to smooth and then calculate growth rate.
I assume you are interested in the growth rate of the latent measurement (i.e. the noise free value). Smoothing is a method of estimating this ...
- 39.6k
3
votes
Accepted
Random slopes in a growth curve analysis
There are two main considerations when choosing whether to specify random slopes for a variable:
Is it biologically / clinically / theoretically possible for each subject (or whatever the grouping ...
- 65.8k
3
votes
Accepted
Analyzing the pattern in the growth of organisms using discrete data in R
Longitudinal ordinal regression using Markov models can deal with the situations you described. For example in a first-order Markov proportional odds logistic model the current count has the previous ...
- 98.4k
3
votes
Accepted
Using change in one variable (2 timepoints) to predict change in another variable (2 timepoints): latent change models?
You also need to define a latent intercept for the "b" pair. In your current code, s1 is just a dummy/phantom/single-indicator factor that puts ...
- 2,652
3
votes
Accepted
fitting growth curves with nls singular gradient error
It's basically a problem with the starting values, and the limitations of the fitting algorithm in nls().
The following works.
...
- 11.6k
3
votes
Lavaan growth model: to treat endogenous variable as ordinal or continuous
I'd treat this as continuous.
Treating data as ordinal where there are a large number of categories can lead to computation / identification problems.
- 19k
3
votes
Accepted
Latent growth curve model: The variance-covariance matrix of the estimated parameters (vcov) does not appear to be positive definite
There's nothing obvious in the output that suggests that you did something wrong.
(It's sort of interesting that your scaled chi-square is higher than your unscaled chi-square, this is pretty unusual, ...
- 19k
3
votes
How to Estimate Growth Rates Between Two Periods from Data with Varying Time Intervals Between Measurements?
Have you considered using growth curve models within the multilevel analysis framework (a.k.a. hierarchical linear modeling or random coefficient regression analysis)? See, e.g.,
Kwok, O.-M., ...
- 4,333
3
votes
Accepted
How to code for a mulitgroup analysis concerning two catagorical variables
One option could be to combine the two grouping variables (sex, country) into a single grouping variable, for example, as follows:
Category 1: US males
Category 2: US females
Category 3: Canadian ...
- 4,333
3
votes
Accepted
Invariance test for a longitudinal multi-group growth model. Is a group invariance test for all timepoints required?
Is there a need to run a group invariance test for all the time points I have?
If you plan to make comparisons of any parameter(s) across those groups, then measurement invariance is an assumption ...
- 2,652
2
votes
Accepted
2
votes
Accepted
Latent Change Models: account for change in one latent variable as function of change in another
You set up two latent growth models with either a regression or a correlation between the latent slopes.
It's hard to know what to explain, as it's not clear how far you have got, but here's a path ...
- 19k
Only top scored, non community-wiki answers of a minimum length are eligible