I'm working with a data set that has more than 500 variables, all of them numeric.
I've run the svm() function of the e1071 library and the results are great.
Now I'm struggling with the way to plot my results.
I had reviewed some the plot.svm function, and I can make it work with 4 variables.
But I'm wondering if there is a better way for plotting my results, something that summarizes the model I have created with svm.
Any suggestions?
Related
I have used Tidymodel to build a logistic regression model.
While I can extract the performance metrics, I would like to plot the agreement between predictions and observations (calibration plot)
But, have yet to find a method to do this - has anyone got experience with this?
tidymodels does not have a calibration plot function yet (I'm literally working on that now). I would suggest using the one in caret. I don't expect our work to be ready for a while.
I am currently running a simple linear regression model with 5 multiply imputed datasets in R.
E.g. model <- with(imp, lm(outcome ~ exposure))
To pool the summary estimates I could use the command summary(mitools::MIcombine(model)) from the mitools package. However, this does not give results for p-values. I could also use the command summary(pool(model)) from the mice package and this does give results for p-values.
Because of this, I am wondering if there is a specific reason why MIcombine does not produce p-values?
After looking through the documentation, it doesn't seem like there is a particular reason that the mitools library doesn't provide p-values. Although, the package's focus is on imputation, not model results.
However, you don't need either of these packages to see your results–along with the per model p-values. I started writing this as a comment but decided to include the code. If you weren't aware...you can use base R's summary. I realize that the output of mice is comparative, as is mitools. I thought it was important enough to mention this, as well.
If the output of your call is model, then this will work.
library(tidyverse)
map(1:length(model), ~summary(model[.x]))
I have 6 different multivariate cox models which run different sub groups of a dataset with the same other co-variates that I am adjusting for the in the model. I would like to plot the hazard ratios of the subgroups in one forest plot from 6 different models.
I am using R
I can't find a suitable solution for this anywhere. Please help. I have looked into the metafor package and this doesn't seem to help. ggplot package doesn't seem to be able to combine different multivariate models.
Willing to try solutions outside of R also.
Check out my forestplot package. This is exactly for what it was designed for. In particular you want the multiple confidence band section in the vignette.
I am very satisfied with the sjPlot package, with which I can make a table of results of regression analysis, such as lm(), lmer(), glm() and glmer().
However, I learned that the current version of sjt.lmer() in sjPlot does not support models without intercept so far (https://github.com/strengejacke/sjPlot/issues/78). I would like to make tables of results for the sake of my statistics learning.
I am wondering if you could let me know if there is any R package that makes regression tables like sjPlot. Thank you.
I'm looking for a way to fit a conditional logit on grouped data in R. I have multinomial choice counts with response- and individual-specific variables. Unfortunately, the expanded dataset would be too huge to work with it. Thus I can't use most of the packages I know, mlogit for example.
I discovered vglm from the VGAM package but it doesn't work if one explanatory variable is missing for a response category.
Has someone tried something similar in R ?
Thanks!
You can use clogit in the survival package by setting the strata to your group id.