Create Tibble from List of Anovas
anova_tbl.RdCreate a tibble from a list of anovas that compare a model to the null model or that compare two nested models.
Arguments
- anova_ls
a
listofanovaobjects.
Value
An object of classes "anova_tbl", "announce", inheriting from tibble, showing the
table entries for each anova, one per line.
Details
The anovas to be compared must all be of the same type i.e., all must be analyses of a single model object or all must be comparisons of two models. If any of the models has more than one independent variable, the results may be difficult to interpret and a warning will be given.
anova_tbl() can be used to be easily and conveniently compare a list of anovas obtained with
summanov and list_transpose, see examples.
See also
anova.glm() list_transpose(), and
tibble.
Other comp_glm:
comp_glm(),
summanov(),
univ_anova()
Examples
## Following on from summanov() examples…
## Simulate Bernoulli data
(d <- list(
iv2 = list(g = c("a", "c", "e"), h = c("b", "d", "f")),
iv3 = list(i = c("a", "b", "c"), j = c("d", "e", "f")),
iv4 = list(k = c("a", "b"), l = c("c", "d"), m = c("e", "f"))
) |> add_grps(binom_data(levels = 6), iv, .key = _))
#> __________________________
#> Simulated Binomial Data: -
#>
#> # A tibble: 6 × 6
#> iv iv2 iv3 iv4 pn qn
#> <fct> <fct> <fct> <fct> <int> <int>
#> 1 a g i k 35 31
#> 2 b h i k 38 28
#> 3 c g i l 24 42
#> 4 d h j l 10 56
#> 5 e g j m 9 57
#> 6 f h j m 8 58
## Create list of GLM anovas using summanov()
(alist <- d |> summanov(cbind(pn, qn), starts_with("iv")) |>
list_transpose() |> _$anova)
#> $iv
#> ____________
#> GLM Anova: -
#>
#> Analysis of Deviance Table
#>
#> Model: binomial, link: logit
#>
#> Response: cbind(pn, qn)
#>
#> Terms added sequentially (first to last)
#>
#>
#> Df Deviance Resid. Df Resid. Dev Pr(>Chi)
#> NULL 5 67.071
#> iv 5 67.071 0 0.000 4.165e-13 ***
#> ---
#> Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
#>
#> $iv2
#> ____________
#> GLM Anova: -
#>
#> Analysis of Deviance Table
#>
#> Model: binomial, link: logit
#>
#> Response: cbind(pn, qn)
#>
#> Terms added sequentially (first to last)
#>
#>
#> Df Deviance Resid. Df Resid. Dev Pr(>Chi)
#> NULL 5 67.071
#> iv2 1 1.6927 4 65.378 0.1932
#>
#> $iv3
#> ____________
#> GLM Anova: -
#>
#> Analysis of Deviance Table
#>
#> Model: binomial, link: logit
#>
#> Response: cbind(pn, qn)
#>
#> Terms added sequentially (first to last)
#>
#>
#> Df Deviance Resid. Df Resid. Dev Pr(>Chi)
#> NULL 5 67.071
#> iv3 1 60.159 4 6.912 8.75e-15 ***
#> ---
#> Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
#>
#> $iv4
#> ____________
#> GLM Anova: -
#>
#> Analysis of Deviance Table
#>
#> Model: binomial, link: logit
#>
#> Response: cbind(pn, qn)
#>
#> Terms added sequentially (first to last)
#>
#>
#> Df Deviance Resid. Df Resid. Dev Pr(>Chi)
#> NULL 5 67.071
#> iv4 2 58.781 3 8.290 1.721e-13 ***
#> ---
#> Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
#>
## Tibble from list of GLM anovas
alist |> anova_tbl()
#> _________________________________________________
#> Analysis of Deviance (Comparing to null model): -
#>
#> # A tibble: 4 × 9
#> Name `Null Df` `Null Dev` Df Deviance `Resid. Df` `Resid. Dev` `Pr(>Chi)`
#> * <chr> <int> <dbl> <int> <dbl> <int> <dbl> <dbl>
#> 1 iv 5 67.1 5 67.1 0 1.55e-15 4.16e-13
#> 2 iv2 5 67.1 1 1.69 4 6.54e+ 1 1.93e- 1
#> 3 iv3 5 67.1 1 60.2 4 6.91e+ 0 8.75e-15
#> 4 iv4 5 67.1 2 58.8 3 8.29e+ 0 1.72e-13
#> # ℹ 1 more variable: sig <fct>
## Add GLM anova with two independent variables
alist$iv3_iv4 <- glm(cbind(pn, qn) ~ iv3 + iv4, family = binomial, data = d) |>
anova()
## Tibble from list with multivariable anova invokes warning
try(alist |> anova_tbl())
#> Warning: iv3_iv4 has > 1 independent variable, interpret with caution
#> _________________________________________________
#> Analysis of Deviance (Comparing to null model): -
#>
#> # A tibble: 5 × 9
#> Name `Null Df` `Null Dev` Df Deviance `Resid. Df` `Resid. Dev` `Pr(>Chi)`
#> * <chr> <int> <dbl> <int> <dbl> <int> <dbl> <dbl>
#> 1 iv 5 67.1 5 67.1 0 1.55e-15 4.16e-13
#> 2 iv2 5 67.1 1 1.69 4 6.54e+ 1 1.93e- 1
#> 3 iv3 5 67.1 1 60.2 4 6.91e+ 0 8.75e-15
#> 4 iv4 5 67.1 2 58.8 3 8.29e+ 0 1.72e-13
#> 5 iv3_i… 5 67.1 1 60.2 4 6.91e+ 0 8.75e-15
#> # ℹ 1 more variable: sig <fct>
rm(d, alist)