Function reference • ManyEcoEvo

Unprocessed data cleaning and checking

Functions for cleaning and QA checking unprocessed analyst data

Miscellaneous cleaning functions

rm_inf_na(): Removes infinite and NA values from a dataframe of standardised effects

anonymise_teams(): Anonymise ManyEcoEvo Data

clean_response_transformation(): Clean response transformation variable

assign_transformation_type(): Assign back-transformation type to be applied to analysts' point-estimates

Tidying analyst out-of-sample predictions

augment_prediction_data(): Augment analyst out-of-sample prediction data according to the outcome of pointblank interrogation

preprocess_prediction_files(): Preprocess Prediction Files

preprocess_updated_prediction_files(): Performs QA on re-submitted out-of-sample prediction files

read_submission_data(): Read out-of-sample-prediction analyst submission data

validate_predictions_df_blue_tit() validate_predictions_df_euc() validate_predictions(): Validating analyst-submitted predictions

Data Processing for Meta-analysis and Modelling

Calculating and standardising variables for meta-analysis and modelling

Back-transforming / standardising analyst estimates

log_back() logit_back() probit_back() inverse_back() square_back() cube_back() identity_back() power_back() divide_back() square_root_back(): Back-transform effect-sizes to response scale.

back_transform_response_vars_yi(): Back Transform Response Variables - yi

conversion(): Apply back-transformation to beta estimates

conversion_2(): Conditionally apply back-transformation

convert_predictions(): Convert Predictions

est_to_zr(): Convert estimate to Zr

Z_VZ_preds(): Standardize out-of-sample predictions

pred_to_Z(): Z-standardise a dataframe of back-transformed Out-Of-Sample Predictions

pmap_wrap() standardise_response() process_response() log_transform_response(): Wrapper function to standardise response variables

Excluding Data from Meta-analysis

apply_VZ_exclusions(): Apply VZ exclusion to a data-frame containing list-columns of yi subsets

exclude_extreme_VZ(): Exclude extreme values of VZ from a dataframe of standardised predictions

exclude_extreme_estimates(): Exclude extreme estimates above a threshold parameter sd

subset_fns_Zr(): Subsetting Functions for effect-size meta-analysis

subset_fns_yi(): Subsetting Functions for out-of-sample predictions meta-analysis

Transforming and standardising meta-analysis variables

Functions for computing and standardising response and predictor variables for meta-analysis.

box_cox_transform(): Box-cox transform absolute deviation from the meta-analytic mean scores

variance_box_cox(): Calculate the variance of the Box-Cox transformed absolute deviation scores

folded_params(): Calculate the folded parameters for the Box-Cox transformation

log_transform(): log transform response-scale yi estimates

log_transform_yi(): Log-transform a data-frame of back-transformed out-of-sample estimates

calculate_deviation_score(): Calculate deviation from meta-analytic mean

calculate_sorensen_diversity_index(): Calculate mean Sorensen pair-wise dissimilarity values for a ManyAnalyst dataset

apply_sorensen_calc(): Applies the sorensen diversity index calculation to variable diversity dataset

Process and create datasets for analysis

Functions for creating datasets ready for meta-analysis and modelling

make_param_table(): Make parameter table

compute_MA_inputs(): Compute meta-analysis inputs for a nested-dataframe containing different datasets/subsets of analyst data

compute_metaanalysis_inputs(): Compute all metaanalysis inputs for different types of estimates

get_diversity_data(): Get Diversity Data

prepare_ManyEcoEvo(): Prepare ManyEcoEvo raw dataset

prepare_ManyEcoEvo_yi(): Prepare ManyEcoEvo raw dataset for out-of-sample predictions

prepare_analyst_summary_data(): Prepare data for summarising analyst summary statistics

prepare_df_for_summarising(): Prepare data for summarising descriptive statistics

prepare_diversity_raw(): Prepare diversity index data

prepare_diversity_summary_data(): Prepare data for summarising variable diversity

prepare_response_variables(): Prepare response variable data for nested ManyEcoEvo dataset

prepare_response_variables_yi(): Prepare response variable data for nested ManyEcoEvo dataset - out of sample predictions only

prepare_review_data(): Prepare peer-review data from Qualtrics

prepare_sorenson_summary_data(): Prepare data for summarising Sorensen diversity indices

split_yi_subsets(): Split a dataset of out-of-sample predictions by estimate_type

rename_prediction_cols(): Rename Prediction Columns

Model Fitting & Meta-analysis

Functions for fitting meta-analysis and other models described in Gould et al. (2023)

fit_MA_mv(): Fit Meta-regression with random-effects

fit_boxcox_ratings_cat(): Fit model of boxcox deviation scores as function of continuous ratings

fit_boxcox_ratings_cont(): Fit model of boxcox deviation scores as function of continuous ratings

fit_boxcox_ratings_ord(): Fit model of boxcox deviation scores as function of continuous ratings

fit_metafor_mv(): Fit Multivariate Metaregression using metafoR

fit_metafor_mv_reduced(): Fit reduced metaregression model

fit_metafor_uni(): Fit univariate meta-analysis with metafor

fit_multivar_MA(): Fit a multivariate meta-regression model

fit_sorensen_glm(): Fit univariate glm of deviation scores on sorensen diversity index

fit_uni_mixed_effects(): Fit model of Box-Cox transformed deviation scores as a function random-effects inclusion in analyses

Extracting Analysis Outputs & Visualisation

Functions for extracting model outputs, and visualising analysis results

Extracting meta-analysis outputs

i2_ml(): i2_ml

calc_I2_ml(): Calculate I2 for a multilevel meta-analytic model

apportion_heterogeneity_ml(): Apportion heterogeneity of a multi-level meta-analytic model

Plotting

gg_forest(): Forestplot with ggplot2

get_forest_plot_data(): Get Forest Plot Data from a Metafor Model

plot_cont_rating_effects(): Plot Marginal Effects for Numeric Rating Model

plot_effects_diversity(): Marginal Effects Plot of Diversity Index Model

plot_forest(): Plot a Forest Plot

plot_model_means_box_cox_cat(): plot_model_means_box_cox_cat

plot_model_means_orchard(): Plot orchard-plot style model means

Model Checking and Comparison

compare_ml_MA(): Compare two fitted multi-level models

get_MA_fit_stats(): Extract meta-analytic statistics like \(I^2\), etc.

run_model_checks(): Perform model checking on series of fitted models for different datasets, exclusion sets and estimate types

Summarising Analysis Features

Functions for summarising qualitative and quantitative features of analyses, including model specification and variable selection, analyst conclusions and modelling approaches.

summarise_analyses_by_reviewer(): Summarise analyses reviewed by reviewer

summarise_analysis_types(): Summarise Analysis Types

summarise_conclusions(): Summarise counts of qualitative conclusions across all datasets

summarise_conclusions_data(): Count qualitative conclusions across all analyses for each dataset

summarise_model_composition(): Summarise Model Composition

summarise_model_composition_data(): Summarise model composition for a single dataframe of out of sample predictions or out or effect sizes

summarise_reviews(): Summarise Peer-Reviews

summarise_reviews_per_analysis(): Summarise reviews per each analysis

summarise_sorensen_index(): Summarise Mean Sorensen's Index Estimates

summarise_sorensen_index_data(): Summarise Sorensen's Mean Index Estimates for a dataframe

summarise_study(): Summarise ManyAnalyst study data

summarise_variable_counts(): Summarise variable usage across analyses

count_analyses_variables_used(): Count number of analyses each variable is used

count_binary_coded_features(): Summarise binary coded features of analyses

count_conclusions(): Count the number of different conclusions made by analysts across each dataset.

count_teams_analyses(): Summarise number of analyst teams and total analyses per dataset

calc_analyses_per_team(): Calculate total number of analyses per team for a given subset

calc_summary_stats_binary(): Calculate summary statistics for binary summary variables

calc_summary_stats_numeric(): Calculate summary statistics for numeric summary variables

calc_teams_per_dataset(): Calculate the number of teams per dataset for a given subset

calculate_variable_counts(): Count the number of times variables are used across analyses

Scaling Up: Working with data subsets or multiple datasets

Functions for working with multiple datasets or data subsets within a tidyverse list-column framework.

Wrapper Functions

compute_metaanalysis_inputs(): Compute all metaanalysis inputs for different types of estimates

meta_analyse_datasets(): Meta-analyses multiple datasets or subsets of datasets of analyst data

make_viz(): Make visualisations wrapper function

Generate data subsets of full ManyEcoEvo or ManyAnalyst dataset

generate_collinearity_subset(): Generate Collinearity Data Subset

generate_exclusion_subsets(): Generate subsets of analyst data based on different exclusion criteria

generate_expertise_subsets(): Generate Expertise Data Subsets

generate_outlier_subsets(): Generate Outlier Subsets for ManyEcoEvo datasets

generate_rating_subsets(): Generate subsets of ManyEcoEvo Data based on Peer Review Ratings

generate_yi_subsets(): Generate subsets of out-of-sample predictions data by estimate_type for multiple analysis datasets.

Utility Functions

Miscelaneous utility functions

capwords(): Capitalise Words

named_group_split(): Split data frame by groups and name elements

`%in%`: Negative Value Matching