search

NightingaleHealth / ggforestplot

An R package to create forestplots of measures of effects with their confidence intervals.
MIT License
57 stars 12 forks source link

From CI to error for Logistic model #8

Open lorenzoFabbri opened 3 years ago

lorenzoFabbri commented 3 years ago

Hello. I have the results of some Logistic regression models and I want to obtain some Forest Plots. In one column I have the exponentiated estimate (OR) and then I have two columns containing the lower and upper values of a 95% CI. Before using your function to create a FP, I log-transformed the estimate and I compute the error from the CI (the Standard Error). If the upper and lower values of the CI are obtained using confint in R, should I log-transform them too? Because applying various transformations does not seem to affect the width of the error bars in the plot. Thank you.

sum732 commented 2 years ago

Hi @lorenzoFabbri, I also have same information; LogOdds ratios, CI_5 (lower) and CI_95(upper), however, I am not clear how to use them in the package. I know I can use estimate=LogOdds, logodds = FALSE but then how to use CI_5 abd CI_95 data so that they are not transformed in any ways. Thanks, S