Access results of intervals.lme as a dataframe + r + lme

Question

I am using a linear mixed effects model to determine the relationship between 2 variables over time, model -

data(mtcars)

# linear mixed effects model
mlme <- lme(mpg ~ wt, random = ~ 1|cyl, data = mtcars)

I then access the confidence intervals using -

conf <- intervals(mlme, level = 0.95, which = 'fixed')
conf

Returning the results -

Approximate 95% confidence intervals

 Fixed effects:
               lower      est.    upper
(Intercept) 7.431921 18.416639 29.40136
DairyTotal  2.001397  6.716849 11.43230

I want to access the values of the lower and upper limits so I can use them as variables but can't find a method to do so. If you want to access the coefficients for example you can use coef(summary(mlme)) and convert it to a dataframe.

I tried converting the result to a dataframe using data.frame(coef) but get the error:

> data.frame(conf)
Error in as.data.frame.default(x[[i]], optional = TRUE, stringsAsFactors = stringsAsFactors) : 
  cannot coerce class ‘"intervals.lme"’ to a data.frame

Can anyone recommend a method to access variables that are returned in this format?

It's easier to help you if you include a simple [reproducible example](https://stackoverflow.com/questions/5963269/how-to-make-a-great-r-reproducible-example) with sample input that can be used to test and verify possible solutions. — MrFlick, Apr 04 '23 at 20:23
That fair, I was hoping it was just something procedural as R returns a lot of variables are returned in this format... I will make it reproducible. — John Conor, Apr 04 '23 at 20:25

score 2 · Accepted Answer · answered Apr 04 '23 at 20:27

Here is an example with the mtcars dataset how we could access the lower and upper ci as variables:

library(nlme)

data(mtcars)

# linear mixed effects model
mlme <- lme(mpg ~ wt, random = ~ 1|cyl, data = mtcars)

# Confidence intervals
conf <- intervals(mlme, level = 0.95, which = 'fixed')

# Lower and upper confidence intervals as variables
lower <- conf$fixed["(Intercept)", "lower"]
upper <- conf$fixed["(Intercept)", "upper"]

[1] 25.7204
[1] 37.32919

Perfect, thank you! I'll use sample datasets to create my example in future. — John Conor, Apr 04 '23 at 20:37

score 2 · Answer 2 · answered Apr 04 '23 at 22:20

Another possibility would be to use broom.mixed::tidy(). Using @TarJae's example:

broom.mixed::tidy(mlme, conf.int = TRUE, effects = "fixed") |> 
     dplyr::select(term, estimate, conf.low, conf.high)

# A tibble: 2 × 4
  term        estimate conf.low conf.high
  <chr>          <dbl>    <dbl>     <dbl>
1 (Intercept)    31.5     25.7      37.3 
2 wt             -3.52    -4.99     -2.04

Access results of intervals.lme as a dataframe + r + lme

2 Answers2