This function will obtain the coefficients (and associated statistics) for each model in the mable.

# S3 method for mdl_df
tidy(x, ...)

# S3 method for mdl_df
coef(object, ...)

# S3 method for mdl_ts
tidy(x, ...)

# S3 method for mdl_ts
coef(object, ...)

Arguments

x, object

A mable.

...

Arguments for model methods.

Examples

if (requireNamespace("fable", quietly = TRUE)) { library(fable) library(tsibbledata) olympic_running %>% model(lm = TSLM(log(Time) ~ trend())) %>% tidy() }
#> New names: #> * tidied1 -> tidied1...1 #> * tidied2 -> tidied2...2 #> * tidied1 -> tidied1...3 #> * tidied2 -> tidied2...4 #> * tidied1 -> tidied1...5 #> * ...
#> # A tibble: 28 x 8 #> Length Sex .model term estimate std.error statistic p.value #> * <int> <chr> <chr> <chr> <dbl> <dbl> <dbl> <dbl> #> 1 100 men lm (Intercept) 2.41 0.00813 297. 2.01e-47 #> 2 100 men lm trend() -0.00482 0.000429 -11.2 1.78e-11 #> 3 100 women lm (Intercept) 2.52 0.0143 176. 5.28e-32 #> 4 100 women lm trend() -0.00501 0.000657 -7.62 3.41e- 7 #> 5 200 men lm (Intercept) 3.11 0.00664 468. 8.18e-51 #> 6 200 men lm trend() -0.00479 0.000344 -14.0 2.66e-13 #> 7 200 women lm (Intercept) 3.24 0.0229 142. 3.21e-26 #> 8 200 women lm trend() -0.00590 0.000992 -5.94 2.07e- 5 #> 9 400 men lm (Intercept) 3.92 0.00885 443. 5.98e-52 #> 10 400 men lm trend() -0.00551 0.000467 -11.8 6.04e-12 #> # … with 18 more rows