Run your Pipeline

Once you have built your full specification blueprint and feel comfortable with how the pipeline is executed, you can implement a full multiverse-style analysis.

Simply use run_multiverse(<your expanded grid object>):

library(tidyverse)
library(multitool)

# create some data
the_data <-
  data.frame(
    id  = 1:500,
    iv1 = rnorm(500),
    iv2 = rnorm(500),
    iv3 = rnorm(500),
    mod = rnorm(500),
    dv1 = rnorm(500),
    dv2 = rnorm(500),
    include1 = rbinom(500, size = 1, prob = .1),
    include2 = sample(1:3, size = 500, replace = TRUE),
    include3 = rnorm(500)
  )

# create a pipeline blueprint
full_pipeline <- 
  the_data |>
  add_filters(include1 == 0, include2 != 3, include3 > -2.5) |> 
  add_variables(var_group = "ivs", iv1, iv2, iv3) |> 
  add_variables(var_group = "dvs", dv1, dv2) |> 
  add_model("linear model", lm({dvs} ~ {ivs} * mod))

# expand the pipeline
expanded_pipeline <- expand_decisions(full_pipeline)

# Run the multiverse
multiverse_results <- analyze_grid(expanded_pipeline)

multiverse_results
#> # A tibble: 48 × 5
#>    decision specifications   model_fitted     pipeline_code    timing_logs     
#>       <dbl> <list>           <list>           <list>           <list>          
#>  1        1 <tibble [1 × 3]> <tibble [1 × 5]> <tibble [1 × 4]> <tibble [1 × 4]>
#>  2        2 <tibble [1 × 3]> <tibble [1 × 5]> <tibble [1 × 4]> <tibble [1 × 4]>
#>  3        3 <tibble [1 × 3]> <tibble [1 × 5]> <tibble [1 × 4]> <tibble [1 × 4]>
#>  4        4 <tibble [1 × 3]> <tibble [1 × 5]> <tibble [1 × 4]> <tibble [1 × 4]>
#>  5        5 <tibble [1 × 3]> <tibble [1 × 5]> <tibble [1 × 4]> <tibble [1 × 4]>
#>  6        6 <tibble [1 × 3]> <tibble [1 × 5]> <tibble [1 × 4]> <tibble [1 × 4]>
#>  7        7 <tibble [1 × 3]> <tibble [1 × 5]> <tibble [1 × 4]> <tibble [1 × 4]>
#>  8        8 <tibble [1 × 3]> <tibble [1 × 5]> <tibble [1 × 4]> <tibble [1 × 4]>
#>  9        9 <tibble [1 × 3]> <tibble [1 × 5]> <tibble [1 × 4]> <tibble [1 × 4]>
#> 10       10 <tibble [1 × 3]> <tibble [1 × 5]> <tibble [1 × 4]> <tibble [1 × 4]>
#> # ℹ 38 more rows

The result will be another tibble with various list columns.

It will always contain a list column named specifications containing all the information you generated in your blueprint. Next, there will a list column for your fitted model fitted, labelled model_fitted.

Unpacking a multiverse analysis

There are two main ways to unpack and examine multitool results. The first is by using tidyr::unnest().

Unnest

Inside the model_fitted column, multitool gives us 4 columns: model_parameters, model_performance, model_warnings, and model_messages.

multiverse_results |> unnest(model_fitted)
#> # A tibble: 48 × 9
#>    decision specifications   model_function model_parameters  model_performance
#>       <dbl> <list>           <chr>          <list>            <list>           
#>  1        1 <tibble [1 × 3]> lm             <tibble [4 × 13]> <tibble [1 × 7]> 
#>  2        2 <tibble [1 × 3]> lm             <tibble [4 × 13]> <tibble [1 × 7]> 
#>  3        3 <tibble [1 × 3]> lm             <tibble [4 × 13]> <tibble [1 × 7]> 
#>  4        4 <tibble [1 × 3]> lm             <tibble [4 × 13]> <tibble [1 × 7]> 
#>  5        5 <tibble [1 × 3]> lm             <tibble [4 × 13]> <tibble [1 × 7]> 
#>  6        6 <tibble [1 × 3]> lm             <tibble [4 × 13]> <tibble [1 × 7]> 
#>  7        7 <tibble [1 × 3]> lm             <tibble [4 × 13]> <tibble [1 × 7]> 
#>  8        8 <tibble [1 × 3]> lm             <tibble [4 × 13]> <tibble [1 × 7]> 
#>  9        9 <tibble [1 × 3]> lm             <tibble [4 × 13]> <tibble [1 × 7]> 
#> 10       10 <tibble [1 × 3]> lm             <tibble [4 × 13]> <tibble [1 × 7]> 
#> # ℹ 38 more rows
#> # ℹ 4 more variables: model_warnings <list>, model_messages <list>,
#> #   pipeline_code <list>, timing_logs <list>

The model_parameters column gives you the result of calling parameters::parameters() on each model in your grid, which is a data.frame of model coefficients and their associated standard errors, confidence intervals, test statistic, and p-values.

multiverse_results |> 
  unnest(model_fitted) |> 
  unnest(model_parameters)
#> # A tibble: 192 × 21
#>    decision specifications   model_function parameter   coefficient     se    ci
#>       <dbl> <list>           <chr>          <chr>             <dbl>  <dbl> <dbl>
#>  1        1 <tibble [1 × 3]> lm             (Intercept)    -0.0826  0.0517  0.95
#>  2        1 <tibble [1 × 3]> lm             iv1             0.0121  0.0520  0.95
#>  3        1 <tibble [1 × 3]> lm             mod             0.0385  0.0553  0.95
#>  4        1 <tibble [1 × 3]> lm             iv1:mod         0.00306 0.0544  0.95
#>  5        2 <tibble [1 × 3]> lm             (Intercept)     0.00699 0.0612  0.95
#>  6        2 <tibble [1 × 3]> lm             iv1            -0.0658  0.0616  0.95
#>  7        2 <tibble [1 × 3]> lm             mod             0.00262 0.0655  0.95
#>  8        2 <tibble [1 × 3]> lm             iv1:mod        -0.0205  0.0645  0.95
#>  9        3 <tibble [1 × 3]> lm             (Intercept)    -0.0839  0.0514  0.95
#> 10        3 <tibble [1 × 3]> lm             iv2            -0.0146  0.0510  0.95
#> # ℹ 182 more rows
#> # ℹ 14 more variables: ci_low <dbl>, ci_high <dbl>, t <dbl>, df_error <int>,
#> #   p <dbl>, std_coefficient <dbl>, std_ci <dbl>, std_ci_low <dbl>,
#> #   std_ci_high <dbl>, model_performance <list>, model_warnings <list>,
#> #   model_messages <list>, pipeline_code <list>, timing_logs <list>

The model_performance column gives fit statistics, such as r2 or AIC and BIC values, computed by running performance::performance() on each model in your grid.

multiverse_results |> 
  unnest(model_fitted) |>
  unnest(model_performance)
#> # A tibble: 48 × 15
#>    decision specifications   model_function model_parameters    aic  aicc   bic
#>       <dbl> <list>           <chr>          <list>            <dbl> <dbl> <dbl>
#>  1        1 <tibble [1 × 3]> lm             <tibble [4 × 13]>  750.  750.  769.
#>  2        2 <tibble [1 × 3]> lm             <tibble [4 × 13]>  849.  849.  867.
#>  3        3 <tibble [1 × 3]> lm             <tibble [4 × 13]>  750.  750.  768.
#>  4        4 <tibble [1 × 3]> lm             <tibble [4 × 13]>  849.  849.  867.
#>  5        5 <tibble [1 × 3]> lm             <tibble [4 × 13]>  749.  749.  768.
#>  6        6 <tibble [1 × 3]> lm             <tibble [4 × 13]>  849.  850.  868.
#>  7        7 <tibble [1 × 3]> lm             <tibble [4 × 13]>  752.  753.  771.
#>  8        8 <tibble [1 × 3]> lm             <tibble [4 × 13]>  851.  852.  870.
#>  9        9 <tibble [1 × 3]> lm             <tibble [4 × 13]>  752.  752.  770.
#> 10       10 <tibble [1 × 3]> lm             <tibble [4 × 13]>  851.  852.  870.
#> # ℹ 38 more rows
#> # ℹ 8 more variables: r2 <dbl>, r2_adjusted <dbl>, rmse <dbl>, sigma <dbl>,
#> #   model_warnings <list>, model_messages <list>, pipeline_code <list>,
#> #   timing_logs <list>

The model_messages and model_warnings columns contain information provided by the modeling function. If something went wrong or you need to know something about a particular model, these columns will have captured messages and warnings printed by the modeling function.

Unpack

I wrote wrappers around the tidyr::unnest() workflow. The main function is unpack_results(). Pass a multiverse results object to unpack_results() and tell it which columns to grab by indicating the column name in the .what argument:

multiverse_results |> 
  unpack_results(.what = model_fitted)
#> # A tibble: 48 × 14
#>    decision ivs   dvs   include1     include2 include3 model_meta model_function
#>       <dbl> <chr> <chr> <chr>        <chr>    <chr>    <chr>      <chr>         
#>  1        1 iv1   dv1   include1 ==… include… include… linear mo… lm            
#>  2        2 iv1   dv2   include1 ==… include… include… linear mo… lm            
#>  3        3 iv2   dv1   include1 ==… include… include… linear mo… lm            
#>  4        4 iv2   dv2   include1 ==… include… include… linear mo… lm            
#>  5        5 iv3   dv1   include1 ==… include… include… linear mo… lm            
#>  6        6 iv3   dv2   include1 ==… include… include… linear mo… lm            
#>  7        7 iv1   dv1   include1 ==… include… include… linear mo… lm            
#>  8        8 iv1   dv2   include1 ==… include… include… linear mo… lm            
#>  9        9 iv2   dv1   include1 ==… include… include… linear mo… lm            
#> 10       10 iv2   dv2   include1 ==… include… include… linear mo… lm            
#> # ℹ 38 more rows
#> # ℹ 6 more variables: model_parameters <list>, model_performance <list>,
#> #   model_warnings <list>, model_messages <list>, pipeline_code <list>,
#> #   timing_logs <list>

If you want to get straight to a specific result you can specify a sub-list with the .which argument:

multiverse_results |> 
  unpack_results(.what = model_fitted, .which = model_parameters)
#> # A tibble: 192 × 26
#>    decision ivs   dvs   include1     include2 include3 model_meta model_function
#>       <dbl> <chr> <chr> <chr>        <chr>    <chr>    <chr>      <chr>         
#>  1        1 iv1   dv1   include1 ==… include… include… linear mo… lm            
#>  2        1 iv1   dv1   include1 ==… include… include… linear mo… lm            
#>  3        1 iv1   dv1   include1 ==… include… include… linear mo… lm            
#>  4        1 iv1   dv1   include1 ==… include… include… linear mo… lm            
#>  5        2 iv1   dv2   include1 ==… include… include… linear mo… lm            
#>  6        2 iv1   dv2   include1 ==… include… include… linear mo… lm            
#>  7        2 iv1   dv2   include1 ==… include… include… linear mo… lm            
#>  8        2 iv1   dv2   include1 ==… include… include… linear mo… lm            
#>  9        3 iv2   dv1   include1 ==… include… include… linear mo… lm            
#> 10        3 iv2   dv1   include1 ==… include… include… linear mo… lm            
#> # ℹ 182 more rows
#> # ℹ 18 more variables: parameter <chr>, coefficient <dbl>, se <dbl>, ci <dbl>,
#> #   ci_low <dbl>, ci_high <dbl>, t <dbl>, df_error <int>, p <dbl>,
#> #   std_coefficient <dbl>, std_ci <dbl>, std_ci_low <dbl>, std_ci_high <dbl>,
#> #   model_performance <list>, model_warnings <list>, model_messages <list>,
#> #   pipeline_code <list>, timing_logs <list>

unpack_model_*

multitool will run and save anything you put in your pipeline but most often, you will want to look at model parameters and/or performance. To that end, there are a set of convenience functions for getting at the most common multiverse results: unpack_model_parameters, unpack_model_performance, unpack_model_messages, and unpack_model_warnings.

unpack_model_parameters unpacks the model parameters in your multiverse:

multiverse_results |>
  unpack_model_parameters()
#> # A tibble: 192 × 21
#>    decision ivs   dvs   include1     include2 include3 model_meta model_function
#>       <dbl> <chr> <chr> <chr>        <chr>    <chr>    <chr>      <chr>         
#>  1        1 iv1   dv1   include1 ==… include… include… linear mo… lm            
#>  2        1 iv1   dv1   include1 ==… include… include… linear mo… lm            
#>  3        1 iv1   dv1   include1 ==… include… include… linear mo… lm            
#>  4        1 iv1   dv1   include1 ==… include… include… linear mo… lm            
#>  5        2 iv1   dv2   include1 ==… include… include… linear mo… lm            
#>  6        2 iv1   dv2   include1 ==… include… include… linear mo… lm            
#>  7        2 iv1   dv2   include1 ==… include… include… linear mo… lm            
#>  8        2 iv1   dv2   include1 ==… include… include… linear mo… lm            
#>  9        3 iv2   dv1   include1 ==… include… include… linear mo… lm            
#> 10        3 iv2   dv1   include1 ==… include… include… linear mo… lm            
#> # ℹ 182 more rows
#> # ℹ 13 more variables: parameter <chr>, coefficient <dbl>, se <dbl>, ci <dbl>,
#> #   ci_low <dbl>, ci_high <dbl>, t <dbl>, df_error <int>, p <dbl>,
#> #   std_coefficient <dbl>, std_ci <dbl>, std_ci_low <dbl>, std_ci_high <dbl>

unpack_model_performance unpacks the model performance:

multiverse_results |>
  unpack_model_performance()
#> # A tibble: 48 × 15
#>    decision ivs   dvs   include1     include2 include3 model_meta model_function
#>       <dbl> <chr> <chr> <chr>        <chr>    <chr>    <chr>      <chr>         
#>  1        1 iv1   dv1   include1 ==… include… include… linear mo… lm            
#>  2        2 iv1   dv2   include1 ==… include… include… linear mo… lm            
#>  3        3 iv2   dv1   include1 ==… include… include… linear mo… lm            
#>  4        4 iv2   dv2   include1 ==… include… include… linear mo… lm            
#>  5        5 iv3   dv1   include1 ==… include… include… linear mo… lm            
#>  6        6 iv3   dv2   include1 ==… include… include… linear mo… lm            
#>  7        7 iv1   dv1   include1 ==… include… include… linear mo… lm            
#>  8        8 iv1   dv2   include1 ==… include… include… linear mo… lm            
#>  9        9 iv2   dv1   include1 ==… include… include… linear mo… lm            
#> 10       10 iv2   dv2   include1 ==… include… include… linear mo… lm            
#> # ℹ 38 more rows
#> # ℹ 7 more variables: aic <dbl>, aicc <dbl>, bic <dbl>, r2 <dbl>,
#> #   r2_adjusted <dbl>, rmse <dbl>, sigma <dbl>

Unpacking Specifications

You can also choose to expand your decision grid with .unpack_specs to see which decisions produced what result. You have two options for unpacking your decisions - wide or long. If you set .unpack_specs = 'wide', you get one column per decision variable. This is exactly the same as how your decisions appeared in your grid.

multiverse_results |>
  unpack_model_parameters(.unpack_specs = "wide")
#> # A tibble: 192 × 21
#>    decision ivs   dvs   include1     include2 include3 model_meta model_function
#>       <dbl> <chr> <chr> <chr>        <chr>    <chr>    <chr>      <chr>         
#>  1        1 iv1   dv1   include1 ==… include… include… linear mo… lm            
#>  2        1 iv1   dv1   include1 ==… include… include… linear mo… lm            
#>  3        1 iv1   dv1   include1 ==… include… include… linear mo… lm            
#>  4        1 iv1   dv1   include1 ==… include… include… linear mo… lm            
#>  5        2 iv1   dv2   include1 ==… include… include… linear mo… lm            
#>  6        2 iv1   dv2   include1 ==… include… include… linear mo… lm            
#>  7        2 iv1   dv2   include1 ==… include… include… linear mo… lm            
#>  8        2 iv1   dv2   include1 ==… include… include… linear mo… lm            
#>  9        3 iv2   dv1   include1 ==… include… include… linear mo… lm            
#> 10        3 iv2   dv1   include1 ==… include… include… linear mo… lm            
#> # ℹ 182 more rows
#> # ℹ 13 more variables: parameter <chr>, coefficient <dbl>, se <dbl>, ci <dbl>,
#> #   ci_low <dbl>, ci_high <dbl>, t <dbl>, df_error <int>, p <dbl>,
#> #   std_coefficient <dbl>, std_ci <dbl>, std_ci_low <dbl>, std_ci_high <dbl>

If you set .unpack_specs = 'long', your decisions get stacked into two columns: decision_set and alternatives. This format is nice for plotting a particular result from a multiverse analyses per different decision alternatives.

multiverse_results |>
  unpack_model_performance(.unpack_specs = "long")
#> # A tibble: 432 × 12
#>    decision decision_type decision_set      decision_choice model_function   aic
#>       <dbl> <chr>         <chr>             <chr>           <chr>          <dbl>
#>  1        1 variables     ivs               iv1             lm              750.
#>  2        1 variables     dvs               dv1             lm              750.
#>  3        1 filters       include1          include1 == 0   lm              750.
#>  4        1 filters       include2          include2 != 3   lm              750.
#>  5        1 filters       include3          include3 > -2.5 lm              750.
#>  6        1 models        model_meta        linear model    lm              750.
#>  7        1 models        model_coefs_fn    parameters::pa… lm              750.
#>  8        1 models        model_fit_fn      performance::p… lm              750.
#>  9        1 models        model_standardiz… parameters::st… lm              750.
#> 10        2 variables     ivs               iv1             lm              849.
#> # ℹ 422 more rows
#> # ℹ 6 more variables: aicc <dbl>, bic <dbl>, r2 <dbl>, r2_adjusted <dbl>,
#> #   rmse <dbl>, sigma <dbl>

Condense

Unpacking specifications alongside specific results allows us to examine the effects of our pipeline decisions.

A powerful way to organize these results is to summarize a specific results column, say the r2 values of our model over the entire multiverse. condense() takes a result column and summarizes it with the .how argument, which takes a list in the form of list(<a name you pick> = <summary function>).

.how will create a column named like so <column being condsensed>_<summary function name provided>. For this case, we have r2_mean and r2_median.

# model performance r2 summaries
multiverse_results |>
  unpack_model_performance() |>
  condense(r2, list(mean = mean, median = median))
#> # A tibble: 1 × 3
#>   r2_mean r2_median r2_list   
#>     <dbl>     <dbl> <list>    
#> 1 0.00340   0.00318 <dbl [48]>

# model parameters for our predictor of interest
multiverse_results |>
  unpack_model_parameters() |>
  filter(str_detect(parameter, "iv")) |>
  condense(coefficient, list(mean = mean, median = median))
#> # A tibble: 1 × 3
#>   coefficient_mean coefficient_median coefficient_list
#>              <dbl>              <dbl> <list>          
#> 1         -0.00707            -0.0128 <dbl [96]>

In the last example, we have filtered our multiverse results to look at our predictors iv* to see what the mean and median effect was (over all combinations of decisions) on our outcomes.

However, we had three versions of our predictor and two outcomes, so combining dplyr::group_by() with condense() might be more informative:

multiverse_results |>
  unpack_model_parameters(.unpack_specs = "wide") |>
  filter(str_detect(parameter, "iv")) |>
  group_by(ivs, dvs) |>
  condense(coefficient, list(mean = mean, median = median))
#> # A tibble: 6 × 5
#> # Groups:   ivs [3]
#>   ivs   dvs   coefficient_mean coefficient_median coefficient_list
#>   <chr> <chr>            <dbl>              <dbl> <list>          
#> 1 iv1   dv1            0.00117            0.00717 <dbl [16]>      
#> 2 iv1   dv2           -0.0386            -0.0350  <dbl [16]>      
#> 3 iv2   dv1           -0.0115            -0.0124  <dbl [16]>      
#> 4 iv2   dv2            0.0173             0.0254  <dbl [16]>      
#> 5 iv3   dv1           -0.0461            -0.0449  <dbl [16]>      
#> 6 iv3   dv2            0.0353             0.0347  <dbl [16]>

If we were interested in all the terms of the model, we can leverage group_by further:

multiverse_results |>
  unpack_model_parameters(.unpack_specs = "wide") |>
  group_by(parameter, dvs) |>
  condense(coefficient, list(mean = mean, median = median))
#> # A tibble: 16 × 5
#> # Groups:   parameter [8]
#>    parameter   dvs   coefficient_mean coefficient_median coefficient_list
#>    <chr>       <chr>            <dbl>              <dbl> <list>          
#>  1 (Intercept) dv1            -0.0695           -0.0698  <dbl [24]>      
#>  2 (Intercept) dv2            -0.0144           -0.0174  <dbl [24]>      
#>  3 iv1         dv1             0.0147            0.0103  <dbl [8]>       
#>  4 iv1         dv2            -0.0580           -0.0546  <dbl [8]>       
#>  5 iv1:mod     dv1            -0.0123           -0.00995 <dbl [8]>       
#>  6 iv1:mod     dv2            -0.0191           -0.0185  <dbl [8]>       
#>  7 iv2         dv1            -0.0117           -0.0124  <dbl [8]>       
#>  8 iv2         dv2            -0.0240           -0.0285  <dbl [8]>       
#>  9 iv2:mod     dv1            -0.0114           -0.0108  <dbl [8]>       
#> 10 iv2:mod     dv2             0.0586            0.0592  <dbl [8]>       
#> 11 iv3         dv1            -0.0423           -0.0430  <dbl [8]>       
#> 12 iv3         dv2             0.0338            0.0347  <dbl [8]>       
#> 13 iv3:mod     dv1            -0.0499           -0.0481  <dbl [8]>       
#> 14 iv3:mod     dv2             0.0369            0.0349  <dbl [8]>       
#> 15 mod         dv1             0.0197            0.0184  <dbl [24]>      
#> 16 mod         dv2            -0.0114           -0.0123  <dbl [24]>