-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathtargets.Rmd
More file actions
1590 lines (1406 loc) · 55.3 KB
/
targets.Rmd
File metadata and controls
1590 lines (1406 loc) · 55.3 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
---
title: "SCORE Targets"
output:
html_document:
toc: true
toc_float: true
toc_depth: 6
---
```{r setup, include = FALSE}
knitr::opts_chunk$set(collapse = TRUE, comment = "#>")
library(targets)
library(readr)
library(googledrive)
library(googlesheets4)
library(dplyr)
library(visNetwork)
tar_unscript()
```
# The Targets Package
Rendering this file using `rmarkdown::render("targets.Rmd")` executes a series of functions in the correct order to build target files (also known as "targets", e.g., analytic datasets, figures) from source files (e.g., raw data). It also documents the dependencies of the target file, including all files (whether source files or other targets) which are used as inputs to the commands in the functions used to generate the target file.
# Globals
We first define the global options and source functions used to generate target files.
```{targets globals, tar_globals = TRUE}
options(tidyverse.quiet = TRUE,
scipen = 999)
tar_option_set(
# Packages the targets need to run
packages = c("BayesFactor",
"BayesRep",
"BFF", # Version 4.2.1 REQUIRED
"dplyr",
"effectsize",
"ggExtra",
"glue",
"googlesheets4",
"googledrive",
"here",
"kableExtra",
"lubridate",
"metaBMA",
"metafor",
"osfr",
"purrr",
"pwr",
"readr",
"ReplicationSuccess",
"sjPlot",
"stringr",
"tibble",
"tidyr")
)
# All functions used to create targets are found in the folder named "pipeline"
tar_source(files = "pipeline")
```
# Targets
## Raw Data
Most raw data files will have three targets associated with them - one for their ID on OSF, one for the modification date of the file, and one that actually represents the data loaded into R.
The file targets are the GUID for the file on [OSF](https://osf.io/dtzx4/files/osfstorage). These files can be found in the "Raw Data" folder.
The modification date targets are set to run every time `tar_make()` is called (with the parameter `cue = tar_cue("always")`) so that the file is pulled again if, and only if, it is ever updated online.
The `get_osf_mod_date()` and `load_osf_csv()` functions can be found in `pipeline/helper_download_osf.R`.
### Journal Metadata
``` {targets raw-journal}
list(
# journal_metadata_raw.csv ----
# Metadata about journals that articles were sourced from, including names,
# ISSNs, and general publication category
tar_target(journal_metadata_file,
"tcb8q"),
tar_target(journal_metadata_moddate,
get_osf_mod_date(journal_metadata_file),
cue = tar_cue("always")),
tar_target(journal_metadata_raw,
load_osf_csv(journal_metadata_file,
journal_metadata_moddate)),
# journal_repro-policies.csv ----
# Journal policies about reproducibility and data/code sharing
tar_target(journal_repro_policies_file,
"24j8s"),
tar_target(journal_repro_policies_moddate,
get_osf_mod_date(journal_repro_policies_file),
cue = tar_cue("always")),
tar_target(journal_repro_policies,
load_osf_csv(journal_repro_policies_file,
journal_repro_policies_moddate)),
# journal_top-factor.csv ----
# TOP Factor (2015) standards for journals that articles were sourced from,
# according to the TOP factor website (https://topfactor.org/journals)
tar_target(journal_top_factor_file,
"2bhwe"),
tar_target(journal_top_factor_moddate,
get_osf_mod_date(journal_top_factor_file),
cue = tar_cue("always")),
tar_target(journal_top_factor,
load_osf_csv(journal_top_factor_file,
journal_top_factor_moddate))
)
```
### Paper Metadata
```{targets raw-paper}
list(
# paper_citations.csv ----
# Citations in APA format for papers from which claims were extracted
tar_target(paper_citations_file,
"wr8a3"),
tar_target(paper_citations_moddate,
get_osf_mod_date(paper_citations_file),
cue = tar_cue("always")),
tar_target(paper_citations,
load_osf_csv(paper_citations_file,
paper_citations_moddate)),
# paper_metadata_covid.csv ----
# Metadata for COVID preprints from which claims were extracted
tar_target(paper_metadata_covid_file,
"dc3uv"),
tar_target(paper_metadata_covid_moddate,
get_osf_mod_date(paper_metadata_covid_file),
cue = tar_cue("always")),
tar_target(paper_metadata_covid,
load_osf_csv(paper_metadata_covid_file,
paper_metadata_covid_moddate)),
# paper_metadata_raw.csv ----
# Raw metadata for papers from which research claims were extracted
# (excluding COVID preprints)
tar_target(paper_metadata_raw_file,
"j4gkp"),
tar_target(paper_metadata_raw_moddate,
get_osf_mod_date(paper_metadata_raw_file),
cue = tar_cue("always")),
tar_target(paper_metadata_raw,
load_osf_csv(paper_metadata_raw_file,
paper_metadata_raw_moddate))
)
```
### Original Studies
#### Original Study Claims
```{targets raw-claims}
list(
# orig_claims_bushel-complex.csv ----
# Indicates bushel claims where the evidence is anything other than a single
# statistically significant effect
tar_target(orig_claims_bushel_complex_file,
"qjgwb"),
tar_target(orig_claims_bushel_complex_moddate,
get_osf_mod_date(orig_claims_bushel_complex_file),
cue = tar_cue("always")),
tar_target(orig_claims_bushel_complex,
load_osf_csv(orig_claims_bushel_complex_file,
orig_claims_bushel_complex_moddate)),
# orig_claims_bushel-non-sig.csv ----
# Indicates which bushel claims use non-significant evidence.
tar_target(orig_claims_bushel_sig_gsheet,
"sgqf8"),
tar_target(orig_claims_bushel_sig_moddate,
get_osf_mod_date(orig_claims_bushel_sig_gsheet),
cue = tar_cue("always")),
tar_target(orig_claims_bushel_sig,
load_osf_csv(orig_claims_bushel_sig_gsheet,
orig_claims_bushel_sig_moddate)),
# orig_claims_covid_ta2-ids.csv ----
# Claims extracted from phase 1 COVID preprints with IDs for human assessment
# teams. Used to reconcile IDs for process reproducibility work.
tar_target(orig_claims_covid_ta2_file,
"q4kca"),
tar_target(orig_claims_covid_ta2_moddate,
get_osf_mod_date(orig_claims_covid_ta2_file),
cue = tar_cue("always")),
tar_target(orig_claims_covid_ta2,
load_osf_csv(orig_claims_covid_ta2_file,
orig_claims_covid_ta2_moddate)),
# orig_claims_p1-covid.csv ----
# Claims extracted from phase 1 COVID preprints with canonical paper IDs.
# Preprints were from PsyarXiv, SocArXiv, and medRxiv.
tar_target(orig_claims_p1_covid_file,
"94dfs"),
tar_target(orig_claims_p1_covid_moddate,
get_osf_mod_date(orig_claims_p1_covid_file),
cue = tar_cue("always")),
tar_target(orig_claims_p1_covid,
load_osf_csv(orig_claims_p1_covid_file,
orig_claims_p1_covid_moddate)),
# orig_claims_p1.csv ----
# Claims extracted from articles during phase 1 (February 2019 to December
# 2020) with canonical paper IDs
tar_target(orig_claims_p1_file,
"na35f"),
tar_target(orig_claims_p1_moddate,
get_osf_mod_date(orig_claims_p1_file),
cue = tar_cue("always")),
tar_target(orig_claims_p1,
load_osf_csv(orig_claims_p1_file,
orig_claims_p1_moddate)),
# orig_claims_p2-bushel.csv ----
# Bushel claims from phase 2 with canonical paper IDs.
# Rather than focusing on an individual claim in a paper, bushel claim
# traces may branch at any point of a paper up until the
# test description (claim 4)
tar_target(orig_claims_p2_bushel_file,
"9m57d"),
tar_target(orig_claims_p2_bushel_moddate,
get_osf_mod_date(orig_claims_p2_bushel_file),
cue = tar_cue("always")),
tar_target(orig_claims_p2_bushel,
load_osf_csv(orig_claims_p2_bushel_file,
orig_claims_p2_bushel_moddate)),
# orig_claims_p2-single.csv ----
# Single-trace claims extracted from articles during phase 2 (January 2021 to
# May 2022) with canonical paper IDs
tar_target(orig_claims_p2_single_file,
"nakxy"),
tar_target(orig_claims_p2_single_moddate,
get_osf_mod_date(orig_claims_p2_single_file),
cue = tar_cue("always")),
tar_target(orig_claims_p2_single,
load_osf_csv(orig_claims_p2_single_file,
orig_claims_p2_single_moddate))
)
```
#### Original Study Variables
```{targets raw-orig}
list(
# orig_effect-size.csv ----
# Calculated effect sizes with upper and lower bounds for original studies
tar_target(orig_effect_size_file,
"4s3de"),
tar_target(orig_effect_size_moddate,
get_osf_mod_date(orig_effect_size_file),
cue = tar_cue("always")),
tar_target(orig_effect_size,
load_osf_csv(orig_effect_size_file,
orig_effect_size_moddate)),
# orig_n_ser.csv ----
# Set of sample sizes calculated via the SER method for power calculations
tar_target(orig_n_ser_file,
"nhw8q"),
tar_target(orig_n_ser_moddate,
get_osf_mod_date(orig_n_ser_file),
cue = tar_cue("always")),
tar_target(orig_n_ser,
load_osf_csv(orig_n_ser_file,
orig_n_ser_moddate)),
# orig_n_traditional.csv ----
# Set of sample sizes calculated via traditional methods for
# power calculations
tar_target(orig_n_traditional_file,
"pbftz"),
tar_target(orig_n_traditional_moddate,
get_osf_mod_date(orig_n_traditional_file),
cue = tar_cue("always")),
tar_target(orig_n_traditional,
load_osf_csv(orig_n_traditional_file,
orig_n_traditional_moddate)),
# orig_stats_effective.csv ----
# Adjusted sample sizes and degrees of freedom for the purpose of
# effect size estimation.
tar_target(orig_stats_effect_file,
"k5chq"),
tar_target(orig_stats_effect_moddate,
get_osf_mod_date(orig_stats_effect_file),
cue = tar_cue("always")),
tar_target(orig_stats_effect,
load_osf_csv(orig_stats_effect_file,
orig_stats_effect_moddate)),
# orig_stats_extended.csv ----
# Additional statistics for original studies calculated by collaborators at
# Tilburg University.
tar_target(orig_stats_extended_file,
"9fbm8"),
tar_target(orig_stats_extended_moddate,
get_osf_mod_date(orig_stats_extended_file),
cue = tar_cue("always")),
tar_target(orig_stats_extended,
# Delivered data has everything encased in quotes
# These are removed before merging into analytic datasets
load_osf_csv(orig_stats_extended_file,
orig_stats_extended_moddate)),
# orig_stats_p1.csv ----
# Statistics from original articles that underwent replication/reproduction
# in phase 1. Each record is a paper that documents the single claim and
# inferential test selected for that paper. In Phase 1, the (unique)
# inferential test from the (unique) focal claim is coded and stored across
# several different workflows, then aggregated into a ground truth version
# post QA and merging. Original variables may have been coded in either/both
# of main or repro type pipelines, so there are sometimes multiple rows
# per paper.
tar_target(orig_stats_p1_file,
"fa6ub"),
tar_target(orig_stats_p1_moddate,
get_osf_mod_date(orig_stats_p1_file),
cue = tar_cue("always")),
tar_target(orig_stats_p1,
load_osf_csv(orig_stats_p1_file,
orig_stats_p1_moddate)),
# orig_stats_p2_additional.csv ----
# Statistics from original articles that underwent replications/reproductions
# in phase 2 that were entered manually later in the process
tar_target(orig_stats_p2_additional_file,
"y84gf"),
tar_target(orig_stats_p2_additional_moddate,
get_osf_mod_date(orig_stats_p2_additional_file),
cue = tar_cue("always")),
tar_target(
orig_stats_p2_additional,
load_osf_csv(
orig_stats_p2_additional_file,
orig_stats_p2_additional_moddate,
col_types = list(
# All entries "F", which should load as char, not logical
original_statistic_type_reported = col_character(),
original_statistic_analysis_type_statsteam = col_character()
)
)
),
# orig_stats_p2_form-outputs.csv ----
# Statistics from original articles that underwent replications/reproductions
# in phase 2 that were entered via google form.
tar_target(orig_stats_p2_form_file,
"6qg4a"),
tar_target(orig_stats_p2_form_moddate,
get_osf_mod_date(orig_stats_p2_form_file),
cue = tar_cue("always")),
tar_target(orig_stats_p2_form,
load_osf_csv(orig_stats_p2_form_file,
orig_stats_p2_form_moddate)),
# orig_stats_p2_manual-entry.csv ----
# Statistics from original articles that underwent replications in phase 2
# that were entered manually rather than through the other workflows.
tar_target(orig_stats_p2_manual_file,
"dusqm"),
tar_target(orig_stats_p2_manual_moddate,
get_osf_mod_date(orig_stats_p2_manual_file),
cue = tar_cue("always")),
tar_target(
orig_stats_p2_manual,
load_osf_csv(
orig_stats_p2_manual_file,
orig_stats_p2_manual_moddate,
col_types = list(
# Empty columns that should load as char, not logical
original_statistic_type_reported = col_character(),
original_statistic_type_reference = col_character()
)
)
),
# orig_stats_p2_power-outputs.csv ----
# Statistics from original articles that underwent replications in phase 2
# that were gathered from power analysis outputs
tar_target(orig_stats_p2_pwr_file,
"6cweg"),
tar_target(orig_stats_p2_pwr_moddate,
get_osf_mod_date(orig_stats_p2_pwr_file),
cue = tar_cue("always")),
tar_target(orig_stats_p2_pwr,
load_osf_csv(orig_stats_p2_pwr_file,
orig_stats_p2_pwr_moddate)),
# orig_prereg-indicated.csv ----
# Indicates whether the original study paper mentions preregistration
tar_target(orig_prereg_indicated_file,
"2k34q"),
tar_target(orig_prereg_indicated_moddate,
get_osf_mod_date(orig_prereg_indicated_file),
cue = tar_cue("always")),
tar_target(orig_prereg_indicated,
load_osf_csv(orig_prereg_indicated_file,
orig_prereg_indicated_moddate,
col_types = c("clcd")))
)
```
### Replication Studies
```{targets raw-repli}
list(
# repli_effective.csv ----
# Adjusted sample sizes and degrees of freedom for the purpose of
# effect size estimation.
tar_target(repli_effective_file,
"mhf8d"),
tar_target(repli_effective_moddate,
get_osf_mod_date(repli_effective_file),
cue = tar_cue("always")),
tar_target(repli_effective,
load_osf_csv(repli_effective_file,
repli_effective_moddate)),
# repli_effect-size.csv ----
# Calculated effect sizes with upper and lower bounds for replication studies
tar_target(repli_effect_size_file,
"yxw5t"),
tar_target(repli_effect_size_moddate,
get_osf_mod_date(repli_effect_size_file),
cue = tar_cue("always")),
tar_target(repli_effect_size,
load_osf_csv(repli_effect_size_file,
repli_effect_size_moddate)),
# repli_extended.csv ----
# Additional statistics for replication studies calculated by collaborators
# at Tilburg University.
tar_target(repli_extended_file,
"e9v5x"),
tar_target(repli_extended_moddate,
get_osf_mod_date(repli_extended_file),
cue = tar_cue("always")),
tar_target(repli_extended,
load_osf_csv(repli_extended_file,
repli_extended_moddate)),
# repli_stats_p1.csv ----
# Statistics from replication studies in phase 1.
tar_target(repli_stats_p1_file,
"cyr63"),
tar_target(repli_stats_p1_moddate,
get_osf_mod_date(repli_stats_p1_file),
cue = tar_cue("always")),
tar_target(repli_stats_p1,
load_osf_csv(repli_stats_p1_file,
repli_stats_p1_moddate)),
# repli_stats_p2_additional.csv ----
# Statistics from replication studies in phase 2 that were entered
# manually later in the process
tar_target(repli_stats_p2_additional_file,
"6jhy7"),
tar_target(repli_stats_p2_additional_moddate,
get_osf_mod_date(repli_stats_p2_additional_file),
cue = tar_cue("always")),
tar_target(repli_stats_p2_additional,
load_osf_csv(repli_stats_p2_additional_file,
repli_stats_p2_additional_moddate)),
# repli_stats_p2.csv ----
# Statistics from replication studies in phase 2 that were entered via
# google form.
tar_target(repli_stats_p2_file,
"7xfpq"),
tar_target(repli_stats_p2_moddate,
get_osf_mod_date(repli_stats_p2_file),
cue = tar_cue("always")),
tar_target(repli_stats_p2,
load_osf_csv(repli_stats_p2_file,
repli_stats_p2_moddate))
)
```
### Reproduction Studies
```{targets raw-repro}
list(
# repro_prereg-check.csv ----
# Researcher check-in information for reproduction registrations
tar_target(repro_prereg_check_file,
"7kydz"),
tar_target(repro_prereg_check_moddate,
get_osf_mod_date(repro_prereg_check_file),
cue = tar_cue("always")),
tar_target(repro_prereg_check,
load_osf_csv(repro_prereg_check_file,
repro_prereg_check_moddate)),
# repro_stats_additional.csv ----
# Statistics from reproduction studies that were entered later in the
# process rather than through the google form
tar_target(repro_stats_additional_file,
"sw49d"),
tar_target(repro_stats_additional_moddate,
get_osf_mod_date(repro_stats_additional_file),
cue = tar_cue("always")),
tar_target(repro_stats_additional,
load_osf_csv(repro_stats_additional_file,
repro_stats_additional_moddate)),
# repro_stats.csv ----
# Statistics from reproduction studies that were entered via google form.
tar_target(repro_stats_file,
"h82yc"),
tar_target(repro_stats_moddate,
get_osf_mod_date(repro_stats_file),
cue = tar_cue("always")),
tar_target(repro_stats,
load_osf_csv(repro_stats_file,
repro_stats_moddate)),
# repro_vor.csv ----
# Source of the reproduction version of record in cases with multiple
# reproductions for the same claim
tar_target(repro_vor_file,
"k8e7w"),
tar_target(repro_vor_moddate,
get_osf_mod_date(repro_vor_file),
cue = tar_cue("always")),
tar_target(repro_vor,
load_osf_csv(repro_vor_file,
repro_vor_moddate))
)
```
### Process Reproducibility
```{targets raw-pr}
list(
# orig-material_author-outreach.csv ----
# Original study data and code availability based on author outreach efforts
tar_target(materials_author_outreach_file,
"uxj48"),
tar_target(materials_author_outreach_moddate,
get_osf_mod_date(materials_author_outreach_file),
cue = tar_cue("always")),
tar_target(materials_author_outreach,
load_osf_csv(materials_author_outreach_file,
materials_author_outreach_moddate)),
# orig-material_availability.csv ----
# Original study data and code availability determinations from a
# variety of sources
tar_target(materials_availability_file,
"dz5cs"),
tar_target(materials_availability_moddate,
get_osf_mod_date(materials_availability_file),
cue = tar_cue("always")),
tar_target(materials_availability,
load_osf_csv(materials_availability_file,
materials_availability_moddate))
)
```
### Project Management
Some information comes from datasets used in project management.
```{targets raw-project}
list(
# score_paper_id-key.csv ----
# Links canonical paper ID to the IDs used by other teams.
# Does not include COVID papers
tar_target(score_paper_id_key_file,
"qgdwh"),
tar_target(score_paper_id_key_moddate,
get_osf_mod_date(score_paper_id_key_file),
cue = tar_cue("always")),
tar_target(score_paper_id_key,
load_osf_csv(score_paper_id_key_file,
score_paper_id_key_moddate)),
# score_paper_status.csv ----
# Status of articles at each stage in SCORE.
# Does not contain COVID preprints.
tar_target(score_paper_status_file,
"smpd6"),
tar_target(score_paper_status_moddate,
get_osf_mod_date(score_paper_status_file),
cue = tar_cue("always")),
tar_target(score_paper_status,
load_osf_csv(score_paper_status_file,
score_paper_status_moddate)),
# score_rr-projects_dates.csv ----
# Start and end dates of replication/reproduction projects
tar_target(score_rr_dates_file,
"6tpf7"),
tar_target(score_rr_dates_moddate,
get_osf_mod_date(score_rr_dates_file),
cue = tar_cue("always")),
tar_target(score_rr_dates,
load_osf_csv(score_rr_dates_file,
score_rr_dates_moddate,
col_types = c("cccDDD"))),
# score_rr-projects_not-sourced.csv ----
# Reasons why non-matched papers were not plausible for replication
tar_target(score_rr_not_sourced_file,
"3hxzj"),
tar_target(score_rr_not_sourced_moddate,
get_osf_mod_date(score_rr_not_sourced_file),
cue = tar_cue("always")),
tar_target(score_rr_not_sourced,
load_osf_csv(score_rr_not_sourced_file,
score_rr_not_sourced_moddate)),
# score_rr-projects_osf-ids_add.csv ----
# Links to replication and reproduction OSF projects and components for
# additional projects not in the original tracking file.
tar_target(score_rr_osf_ids_add_file,
"et6ng"),
tar_target(score_rr_osf_ids_add_moddate,
get_osf_mod_date(score_rr_osf_ids_add_file),
cue = tar_cue("always")),
tar_target(score_rr_osf_ids_add,
load_osf_csv(score_rr_osf_ids_add_file,
score_rr_osf_ids_add_moddate)),
# score_rr-projects_osf-ids_raw.csv ----
# Links to replication and reproduction OSF projects and components.
tar_target(score_rr_osf_ids_raw_file,
"7nmgy"),
tar_target(score_rr_osf_ids_raw_moddate,
get_osf_mod_date(score_rr_osf_ids_raw_file),
cue = tar_cue("always")),
tar_target(score_rr_osf_ids_raw,
load_osf_csv(score_rr_osf_ids_raw_file,
score_rr_osf_ids_raw_moddate)),
# score_rr-projects_sourced.csv ----
# All replication and reproduction projects that were matched with a team.
tar_target(score_rr_sourced_file,
"x2cbe"),
tar_target(score_rr_sourced_moddate,
get_osf_mod_date(score_rr_sourced_file),
cue = tar_cue("always")),
tar_target(score_rr_sourced,
load_osf_csv(score_rr_sourced_file,
score_rr_sourced_moddate)),
# score_rr-project_status.csv ----
# Status tracking and other internal documentation for replication and
# reproduction studies
tar_target(score_rr_status_file,
"khpbu"),
tar_target(score_rr_status_moddate,
get_osf_mod_date(score_rr_status_file),
cue = tar_cue("always")),
tar_target(score_rr_status,
load_osf_csv(score_rr_status_file,
score_rr_status_moddate)),
# score_rr-project_types.csv ----
# Internal project types for replication and reproduction studies.
tar_target(score_rr_types_file,
"dx759"),
tar_target(score_rr_types_moddate,
get_osf_mod_date(score_rr_types_file),
cue = tar_cue("always")),
tar_target(score_rr_types_raw,
load_osf_csv(score_rr_types_file,
score_rr_types_moddate))
)
```
### Correlations
```{targets raw-corr}
list(
# corr_orig-significance_p1.csv ----
# Original study claims significance for phase 1 claims
tar_target(stat_sig_p1_file,
"ftxyn"),
tar_target(stat_sig_p1_moddate,
get_osf_mod_date(stat_sig_p1_file),
cue = tar_cue("always")),
tar_target(stat_sig_p1,
load_osf_csv(stat_sig_p1_file,
stat_sig_p1_moddate)),
# corr_orig-significance_p2.csv ----
# Original study claims significance for phase 2 claims
tar_target(stat_sig_p2_file,
"kqp2w"),
tar_target(stat_sig_p2_moddate,
get_osf_mod_date(stat_sig_p2_file),
cue = tar_cue("always")),
tar_target(stat_sig_p2,
load_osf_csv(stat_sig_p2_file,
stat_sig_p2_moddate))
)
```
## Change Logs
If changes ever needed to be made to any dataset for any reason, these changes were recorded in a change log. Change logs record who requested the change, when the change was implemented, the key ID of the record to change, the column the change was in, what the change was to, what data was recorded there previously, and the reasoning behind the change.
```{targets change-logs}
list(
# changes_journal_metadata.csv ----
# Change log for journal metadata
tar_target(changes_journal_metadata_file,
"c2vdn"),
tar_target(changes_journal_metadata_moddate,
get_osf_mod_date(changes_journal_metadata_file),
cue = tar_cue("always")),
tar_target(changes_journal_metadata,
load_osf_csv(changes_journal_metadata_file,
changes_journal_metadata_moddate)),
# changes_orig_merged.csv ----
# Change log for merged original study variables
tar_target(changes_orig_merged_file,
"4azsd"),
tar_target(changes_orig_merged_moddate,
get_osf_mod_date(changes_orig_merged_file),
cue = tar_cue("always")),
tar_target(changes_orig_merged,
load_osf_csv(changes_orig_merged_file,
changes_orig_merged_moddate)),
# changes_orig_stats-extended.csv ----
# Change log for additional statistics for original studies
tar_target(changes_orig_stats_extended_file,
"vz2ck"),
tar_target(changes_orig_stats_extended_moddate,
get_osf_mod_date(changes_orig_stats_extended_file),
cue = tar_cue("always")),
tar_target(changes_orig_stats_extended,
load_osf_csv(changes_orig_stats_extended_file,
changes_orig_stats_extended_moddate)),
# changes_pr_data-form.csv ----
# Change log for process reproducibility variables
tar_target(changes_pr_data_form_file,
"pcyjg"),
tar_target(changes_pr_data_form_moddate,
get_osf_mod_date(changes_pr_data_form_file),
cue = tar_cue("always")),
tar_target(changes_pr_data_form,
load_osf_csv(changes_pr_data_form_file,
changes_pr_data_form_moddate)),
# changes_pr_outreach.csv ----
# Change log for original study author outreach variables
tar_target(changes_author_outreach_file,
"bhpuv"),
tar_target(changes_author_outreach_moddate,
get_osf_mod_date(changes_author_outreach_file),
cue = tar_cue("always")),
tar_target(changes_author_outreach,
load_osf_csv(changes_author_outreach_file,
changes_author_outreach_moddate)),
# changes_repli_merged.csv ----
# Change log for merged replication study variables
tar_target(changes_repli_merged_file,
"uq7pd"),
tar_target(changes_repli_merged_moddate,
get_osf_mod_date(changes_repli_merged_file),
cue = tar_cue("always")),
tar_target(changes_repli_merged,
load_osf_csv(changes_repli_merged_file,
changes_repli_merged_moddate)),
# changes_repro_merged.csv ----
# Change log for merged reproduction study variables
tar_target(changes_repro_merged_file,
"hs4v7"),
tar_target(changes_repro_merged_moddate,
get_osf_mod_date(changes_repro_merged_file),
cue = tar_cue("always")),
tar_target(changes_repro_merged,
load_osf_csv(changes_repro_merged_file,
changes_repro_merged_moddate)),
# changes_repro_summary.csv ----
# Change log for reproduction summary variables
tar_target(changes_repro_summary_file,
"e498m"),
tar_target(changes_repro_summary_moddate,
get_osf_mod_date(changes_repro_summary_file),
cue = tar_cue("always")),
tar_target(changes_repro_summary,
load_osf_csv(changes_repro_summary_file,
changes_repro_summary_moddate)),
# changes_score_rr_status.csv ----
# Change log for score replication/reproduction project status
tar_target(changes_score_rr_status_file,
"9wfc6"),
tar_target(changes_score_rr_status_moddate,
get_osf_mod_date(changes_score_rr_status_file),
cue = tar_cue("always")),
tar_target(changes_score_rr_status,
load_osf_csv(changes_score_rr_status_file,
changes_score_rr_status_moddate)),
# changes_score_rr_types.csv ----
# Change log for score internal project types
tar_target(changes_score_rr_types_file,
"xdny8"),
tar_target(changes_score_rr_types_moddate,
get_osf_mod_date(changes_score_rr_types_file),
cue = tar_cue("always")),
tar_target(changes_score_rr_types,
load_osf_csv(changes_score_rr_types_file,
changes_score_rr_types_moddate))
)
```
## Intermediate Data
These are data at various stages of processing between the raw data and analysis-ready data.
### Project Management
```{targets int-project}
list(
# Updated replication/reproduction project types
tar_target(score_rr_types,
update_score_rr_types(score_rr_types_raw,
changes_score_rr_types))
)
```
### Journal Metadata
```{targets int-journal}
list(
# Update and transform journal metadata
tar_target(journal_updated,
transform_update_journal(journal_metadata_raw,
changes_journal_metadata)),
# Join journal metadata and policy information
tar_target(journal_metadata,
left_join(journal_updated,
journal_top_factor,
by = join_by(publication_standard == Journal)))
)
```
### Paper Metadata
```{targets int-paper}
list(
# Metadata for covid papers was collected separately from other papers
# Reconcile differences for merging
tar_target(papers_covid_transformed,
transform_covid_metadata(paper_metadata_covid)),
tar_target(papers_transformed,
transform_paper_metadata(paper_metadata_raw,
score_paper_status))
)
```
### Original Studies
```{targets int-orig}
list(
# Transformed and merged raw original statistics data
tar_target(orig_merged,
merge_orig_stats(orig_stats_p1,
orig_claims_p1_covid,
orig_stats_p2_pwr,
orig_stats_p2_manual,
orig_stats_p2_form,
orig_stats_p2_additional)),
# Merged original statistics updated with changes
tar_target(orig_updated,
update_orig_stats(orig_merged,
changes_orig_merged)),
# Extended original study statistics updated with changes
tar_target(orig_extended_updated,
update_orig_extended(orig_stats_extended,
changes_orig_stats_extended)),
# Original study statistics, merged and transformed into a semi-final form
tar_target(orig_dataset,
transform_orig_updated(orig_updated,
orig_extended_updated))
)
```
### Replication Studies
```{targets int-repli}
list(
# Transformed replication form data
tar_target(repli_stats_p2_transformed,
transform_repli_stats_p2(repli_stats_p2,
score_rr_types)),
# Merged replication study variables
tar_target(repli_merged,
merge_repli_input(repli_stats_p1,
repli_stats_p2_transformed,
repli_stats_p2_additional,
repli_effective)),
# Replication study statistics, updated and transformed
# into a semi-final form
tar_target(repli_dataset,
update_transform_repli(repli_merged,
changes_repli_merged))
)
```
### Reproduction Studies
```{targets int-repro}
list(
# Transformed data from forms
tar_target(repro_data_entry,
transform_repro_input(repro_stats)),
# Transformed reproduction preregistration check-ins
tar_target(rr_confrontations_repro_claim,
transform_repro_prereg(repro_prereg_check)),
# Merged reproduction study statistics
tar_target(repro_merged,
merge_repro(repro_data_entry,
repro_stats_additional,
repro_vor)),
# Updated and transformed reproduction study statistics
tar_target(repro_dataset,
update_repro(repro_merged,
changes_repro_merged)),
# Reproduction study summary variables
tar_target(repro_summary_raw,
create_repro_summary(repro_dataset,
orig_dataset,
rr_confrontations_repro_claim)),
# Reproduction study summary variables updated with new categories
tar_target(repro_summary,
update_repro_summary(repro_summary_raw,
changes_repro_summary))
)
```
### Process Reproducibility
```{targets int-pr}
list(
# Updated original author outreach
tar_target(oa_outreach,
update_oa(materials_author_outreach,
changes_author_outreach)),
# Transformed process reproducibility
tar_target(pr_transformed,
transform_pr(materials_availability,
orig_claims_covid_ta2,
orig_claims_p1_covid)),
# Updated process reproducibility
tar_target(pr_updated,
update_pr(pr_transformed,
changes_pr_data_form))
)
```
## Analysis-ready Data
Datasets that were used in papers produced during the SCORE project.
### Replication and Reproduction Papers
```{targets analytic-repli-repro}
list(
# claims_bushel_ids.csv ----
# Key IDs for bushel claims, where multiple inferential tests were evaluated
# within a single study