-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathEvaluación Conjunta de Necesidades.Rmd
2449 lines (2246 loc) · 124 KB
/
Evaluación Conjunta de Necesidades.Rmd
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: "Evaluación Conjunta de Necesidades"
author: "Sebastian Garcia, IM Associate"
date: "2024-04-08"
output: html_document
---
```{r message = FALSE, warning = FALSE}
library(tidyverse)
library(readxl)
library(ggplot2)
library(writexl)
library(labelled)
library(robotoolbox)
library(Hmisc)
library(modeest)
```
# Step 1. Load data
```{r}
#setwd("****")
#kobo_setup(url = "https://kobo.unhcr.org",token = ****)
#x <- kobo_submissions("****")
#HH <- x$main
#Individual <- x$rpt_hhmnames
```
# Step 2. Reorder columns
```{r}
# rename variables that where wrongly named
Individual <- Individual |>
rename(NUT_D1_Q2 = NUT_D2_Q1,
NUT_D1_Q2_1 = NUT_D2_Q1_1,
NUT_D1_Q2_2 = NUT_D2_Q1_2,
NUT_D1_Q2_3 = NUT_D2_Q1_3,
NUT_D1_Q2_4 = NUT_D2_Q1_4,
NUT_D1_Q2_5 = NUT_D2_Q1_5,
NUT_D1_Q2_6 = NUT_D2_Q1_6,
NUT_D1_Q2_98 = NUT_D2_Q1_98,
NUT_D1_Q2_99 = NUT_D2_Q1_99)
HH <- HH |>
rename(GBV_D3_Q1 = GBV_D2_Q1)
# reorder stuff to better EDA
Individual <- Individual |>
select("hhmnames_pos", "HHH01_2_aux", "HH01_aux", "nt_rostermember", "HH03_aux", "HH01_2_aux", "HH03_2_aux", "nt_names",
"personId", "hhroster_pos_aux", "hhmnames_pos_match", "nt_endnames", "HH01", "HH03", "HH04", "HH05",
"HH06", "calcul1", "age", "AgeMonths", "ageMD","agecalculated", "age_est", "months_est",
"HH07", "HH07_months", "MH_3", "MH_3_1", "MH_3_2", "MH_3_3", "MH_3_4", "MH_3_5",
"MH_3_6", "MH_3_7", "MH_3_8", "MH_3_9", "MH_3_10", "MH_3_99", "PRO_D4_Q1", "PRO_D4_Q1_1",
"PRO_D4_Q1_2", "PRO_D4_Q1_3", "PRO_D4_Q1_4", "PRO_D4_Q1_5", "PRO_D4_Q1_6", "PRO_D4_Q1_7", "PRO_D4_Q1_10", "PRO_D4_Q1_96",
"PRO_D4_Q1_98", "PRO_D4_Q1_99", "PRO_D4_Q1_O", "NUT_D1_Q1", "NUT_D1_Q1_1", "NUT_D1_Q1_2", "NUT_D1_Q1_3", "NUT_D1_Q1_98",
"NUT_D1_Q1_99", "NUT_D1_Q2", "NUT_D1_Q2_1", "NUT_D1_Q2_2", "NUT_D1_Q2_3", "NUT_D1_Q2_4", "NUT_D1_Q2_5", "NUT_D1_Q2_6",
"NUT_D1_Q2_98", "NUT_D1_Q2_99", "NUT_D4_Q1", "NUT_D4_Q1_1", "NUT_D4_Q1_2", "NUT_D4_Q1_3", "NUT_D4_Q1_4", "NUT_D4_Q1_98",
"NUT_D4_Q1_99", "NUT_D5_Q1", "NUT_D5_Q2", "NUT_D5_Q2_1", "NUT_D5_Q2_2", "NUT_D5_Q2_3", "NUT_D5_Q2_4", "NUT_D5_Q2_5",
"NUT_D5_Q2_6", "NUT_D5_Q2_7", "NUT_D5_Q2_8", "NUT_D5_Q2_9", "NUT_D5_Q2_10", "NUT_D5_Q2_98", "NUT_D5_Q2_99", "NUT_D8_Q1",
"NUT_D8_Q1_1", "NUT_D8_Q1_2", "NUT_D8_Q1_3", "NUT_D8_Q1_4", "NUT_D8_Q1_5", "NUT_D8_Q1_6", "NUT_D8_Q1_7","NUT_D8_Q1_8",
"NUT_D8_Q1_9", "NUT_D8_Q1_98", "NUT_D8_Q1_99", "NUT_D10_Q1", "NUT_D10_Q1_1", "NUT_D10_Q1_2", "NUT_D10_Q1_3", "NUT_D10_Q1_4",
"NUT_D10_Q1_5", "NUT_D10_Q1_6", "NUT_D10_Q1_7", "NUT_D10_Q1_8", "NUT_D10_Q1_9", "NUT_D10_Q1_10", "NUT_D10_Q1_11", "NUT_D10_Q1_98",
"NUT_D10_Q1_99", "EDU_D1_Q1", "EDU_D2_Q1", "EDU_D2_Q2", "EDU_D3_Q1", "EDU_D6_Q1", "EDU_D6_Q1_1", "EDU_D6_Q1_2",
"EDU_D6_Q1_3", "EDU_D6_Q1_4", "EDU_D6_Q1_5", "EDU_D6_Q1_6", "EDU_D6_Q1_96", "EDU_D6_Q1_98", "EDU_D6_Q1_99", "EDU_D6_Q1_O",
"EDU_D7_Q1", "EDU_D7_Q1_1", "EDU_D7_Q1_2", "EDU_D7_Q1_3", "EDU_D7_Q1_4", "EDU_D7_Q1_5", "EDU_D7_Q1_6", "EDU_D7_Q1_96",
"EDU_D7_Q1_98", "EDU_D7_Q1_99", "EDU_D7_Q1_O", "HE_D1_Q1", "HE_D1_Q2", "HE_D3_Q1", "HE_D3_Q1_1", "HE_D3_Q1_2",
"HE_D3_Q1_3", "HE_D3_Q1_4", "HE_D3_Q1_5", "HE_D3_Q1_6", "HE_D3_Q1_7", "HE_D3_Q1_8", "HE_D3_Q1_9", "HE_D3_Q1_10",
"HE_D3_Q1_11", "HE_D3_Q1_96", "HE_D3_Q1_98", "HE_D3_Q1_99", "HE_D3_Q1_O", "INT_D1_Q1", "INT_D2_Q1", "INT_D2_Q2",
"INT_D2_Q3", "start_time_2_001", "position", "Relation_R", "adult18", "women_b", "father_b", "childLess2",
"childLess2name", "women", "father", "adult", "women_b_count", "hh_size", "hhhead_age_ab18", "adult_sum",
"hhhead_age", "position18", "adult01", "age18above", "below5", "below18", "child_edu_calcul", "below5_r",
"below18_r", "child_edu_calcul_r", "positionbelow5", "positionbelow18", "positionchild_edu_calcul", "below5_nc",
"below18_nc", "child_edu_calcul_nc", "adult_sum_001", "hh_size_001", "ven01", "_index", "_parent_table_name",
"_parent_index", "_validation_status")
HH <- HH |>
select("start", "end", "start_time_1", "logo", "note1", "interviewdate", "implementador", "testreal",
"name_enumerator", "Intro01", "Intro01_A", "number", "PoC_name", "call_attempt", "attempt1", "next_attempt",
"note_attempt_implementador1", "note_attempt_implementador2", "attempt2", "attempt3", "consent_form", "Intro04",
"Intro04.1", "DEMO_1", "DEMO_2", "DEMO_00.6", "attempt3.1", "DEMO_5", "DEMO_5.1", "DEMO_6",
"DEMO_7", "DEMO_7.1", "country", "country.1", "admin1", "admin2", "DEMO_18", "note_HH01",
"HHH01_aux", "MH_1", "namechild2less", "nochild2less", "women_name_b_total", "women_name_b",
"father_name_b", "women_name", "father_name", "adult_name", "sumbelow5", "sumbelow18", "sumchild_edu_calcul",
"nobelow5", "nobelow18", "nochild_edu_calcul", "ven_sum", "respondent_1", "note_integration",
"INT_D3_Q1", "INT_D3_Q1B", "INT_D3_Q1B_1", "INT_D3_Q1B_2", "INT_D3_Q1B_3", "INT_D3_Q1B_4", "INT_D3_Q1B_5",
"INT_D3_Q1B_6", "INT_D3_Q1B_7", "INT_D3_Q1B_8", "INT_D3_Q1B_9", "INT_D3_Q1B_98", "INT_D3_Q1B_99", "INT_D3_Q2",
"INT_D3_Q2_1", "INT_D3_Q2_2", "INT_D3_Q2_3", "INT_D3_Q2_4", "INT_D3_Q2_5", "INT_D3_Q2_6","INT_D3_Q2_7",
"INT_D3_Q2_8", "INT_D3_Q2_9", "INT_D3_Q2_10", "INT_D3_Q2_98", "INT_D3_Q2_99", "INT_D3_Q2_O", "INT_D4_Q1",
"INT_D4_Q1_1", "INT_D4_Q1_2", "INT_D4_Q1_3", "INT_D4_Q1_4", "INT_D4_Q1_5", "INT_D4_Q1_6", "INT_D4_Q1_10",
"INT_D4_Q1_96", "INT_D4_Q1_98", "INT_D4_Q1_99", "INT_D4_Q1_O", "note_food_security", "FS_D1_label", "FS_D1_Q1",
"FS_D1_Q2", "FS_D1_Q3", "FS_D1_Q4", "FS_D1_Q5", "FS_D1_Q6", "FS_D1_Q7", "FS_D1_Q8", "note_food_security2",
"FS_D2_label", "FS_D2_Q1","FS_D2_Q2", "FS_D2_Q3", "FS_D2_Q4", "FS_D2_Q5", "note_food_security3", "FS_D3_Q1",
"FS_D3_Q2", "note_food_security4", "FS_D4_label", "FS_D4_Q1", "FS_D4_Q2", "FS_D4_Q3", "FS_D4_Q4", "FS_D4_Q5",
"FS_D4_Q6", "FS_D4_Q7", "FS_D4_Q8", "FS_D4_Q9", "FS_D4_Q10", "note_transportation", "HT_D1_Q1_label", "HT_D1_Q1_first",
"HT_D1_Q1_first_o", "HT_D1_Q1_second", "HT_D1_Q1_second_o","HT_D1_Q2", "HT_D2_Q1", "HT_D2_Q1_O", "note_shelter",
"SHE_D1_Q1", "SHE_D1_Q1_O", "SHE_D1_Q2", "SHE_D1_Q2_1", "SHE_D1_Q2_2", "SHE_D1_Q2_3", "SHE_D1_Q2_4", "SHE_D1_Q2_5",
"SHE_D1_Q2_6", "SHE_D1_Q2_98", "SHE_D1_Q2_99", "SHE_D1_Q3", "SHE_D1_Q3_1", "SHE_D1_Q3_2", "SHE_D1_Q3_3",
"SHE_D1_Q3_4", "SHE_D1_Q3_5", "SHE_D1_Q3_98", "SHE_D1_Q3_99", "SHE_D2_Q1", "SHE_D3_Q1", "SHE_D3_Q1_1", "SHE_D3_Q1_2",
"SHE_D3_Q1_3", "SHE_D3_Q1_4", "SHE_D4_Q1", "note_wash", "WA_D1_Q1", "WA_D1_Q2", "WA_D2_Q1", "WA_D2_Q2",
"WA_D4_Q1", "WA_D4_Q2", "WA_D6_Q1", "WA_D8_Q1", "WA_D11_Q1", "note_protection", "PRO_D1_Q1", "PRO_D1_Q1_1",
"PRO_D1_Q1_2", "PRO_D1_Q1_3", "PRO_D1_Q1_4", "PRO_D1_Q1_5", "PRO_D1_Q1_6", "PRO_D1_Q1_7", "PRO_D1_Q1_9",
"PRO_D1_Q1_96", "PRO_D1_Q1_98", "PRO_D1_Q1_99", "PRO_D1_Q1_O", "PRO_D2_Q1", "PRO_D2_Q1B", "PRO_D2_Q1B_1",
"PRO_D2_Q1B_2", "PRO_D2_Q1B_3", "PRO_D2_Q1B_4", "PRO_D2_Q1B_5", "PRO_D2_Q1B_6", "PRO_D2_Q1B_7", "PRO_D2_Q1B_8",
"PRO_D2_Q1B_9", "PRO_D2_Q1B_10", "PRO_D2_Q1B_96", "PRO_D2_Q1B_98", "PRO_D2_Q1B_99", "PRO_D2_Q1B_O", "PRO_D3_Q1",
"PRO_D3_Q1B", "PRO_D3_Q1B_1", "PRO_D3_Q1B_2", "PRO_D3_Q1B_3", "PRO_D3_Q1B_4", "PRO_D3_Q1B_5", "PRO_D3_Q1B_6",
"PRO_D3_Q1B_7", "PRO_D3_Q1B_96", "PRO_D3_Q1B_98", "PRO_D3_Q1B_99", "PRO_D3_Q1B_O", "PRO_D3_Q2",
"PRO_D3_Q2B", "PRO_D3_Q2B_1", "PRO_D3_Q2B_2", "PRO_D3_Q2B_3", "PRO_D3_Q2B_4", "PRO_D3_Q2B_5", "PRO_D3_Q2B_6",
"PRO_D3_Q2B_7", "PRO_D3_Q2B_8", "PRO_D3_Q2B_9", "PRO_D3_Q2B_98", "PRO_D3_Q2B_99", "PRO_D5_Q1", "PRO_D5_Q2",
"PRO_D5_Q2_1", "PRO_D5_Q2_2", "PRO_D5_Q2_3", "PRO_D5_Q2_4", "PRO_D5_Q2_5", "PRO_D5_Q2_6", "PRO_D5_Q2_7",
"PRO_D5_Q2_98", "PRO_D5_Q2_99", "note_gbv", "GBV_D1_Q1", "GBV_D1_Q1B", "GBV_D1_Q1B_1", "GBV_D1_Q1B_2",
"GBV_D1_Q1B_3", "GBV_D1_Q1B_4", "GBV_D1_Q1B_5", "GBV_D1_Q1B_6", "GBV_D1_Q1B_8", "GBV_D1_Q1B_96", "GBV_D1_Q1B_98",
"GBV_D1_Q1B_99", "GBV_D1_Q1B_O", "GBV_D3_Q1", "HTS_D1_Q1", "HTS_D1_Q2", "HTS_D2_Q1", "HTS_D2_Q1_1",
"HTS_D2_Q1_2", "HTS_D2_Q1_3", "HTS_D2_Q1_4", "HTS_D2_Q1_5", "HTS_D2_Q1_6", "CP_D1_Q1", "CP_D1_Q1_1",
"CP_D1_Q1_2", "CP_D1_Q1_3", "CP_D1_Q1_4", "CP_D1_Q1_5", "CP_D1_Q1_6", "CP_D1_Q1_7", "CP_D1_Q1_98",
"CP_D1_Q1_99", "CP_D1_Q2", "psea_org", "psea3", "end_survey", "end_result", "name_respondent", "final_notes",
"final_notes_entry", "end_time_1", "_id", "uuid", "_submission_time", "_validation_status", "_status", "_submitted_by",
"__version__", "_uuid", "_index", "rpt_hhmnames_count", "S2_respondent_count", "instanceID", "_xform_id_string")
```
# Step 3. Functions
Some functions need to be created to be used during the data-processing of the individual dataset since there where changes applied to the regional form while we had already entered the data collection process.
```{r}
# this function will be used for rounding in de CARI_FES
round_half_up <- function(x) {
floor(x + 0.5)
}
# Peru Only
# define processes to clear inconsistencies in bulk
replace_values_nut_under_6_months <- function(data, uuid_condition, aux_condition, columns) {
for (column in columns) {
data <- data %>%
mutate({{ column }} :=
ifelse(
`_parent_index` == uuid_condition &
HH01_aux == aux_condition,
NA_character_,
!!rlang::sym(column)
)
)
}
return(data)
}
replace_values_nut_over_5_years <- function(data, age_condition, columns) {
for (column in columns) {
data <- data %>%
mutate({{ column }} :=
ifelse(
age > age_condition & HH05 == "1" |
age_est > age_condition & HH05 == "0",
NA_character_,
!!rlang::sym(column)
)
)
}
return(data)
}
```
# Step 4. Household Pre-processing
The aim was to lose as less information as possible. We had two different data services providers working in this project. PULSO was hired by UNHCR and Equilibrium hired by IOM. PULSO identified 6 records where the data quality check was not passed, then they where dismissed from the dataset. Other minor adjustments had to do with phone numbers and internal coding. On the other hand, Equilibrium corrected information on food security via a second call.
Other pre-processing:
clearing some variables since there where changes in the skip logic in the regional form while we were already gathering data.
Creation of SHE_D1_Q3_ALL that will be used in step 9 Household level indicators
#### AD HOC FOR PERU
```{r}
# fixing minor bugs to do not lose records
HH <- HH |>
mutate(implementador =
ifelse(`_uuid` == "c6de4918-d3af-4d56-8465-fdf15051647a", "2", implementador),
implementador =
ifelse(`_uuid` == "298b6023-4c6d-420f-8749-87bdc8710d7b", "2", implementador),
implementador =
ifelse(`_uuid` == "53d14903-76e2-4acc-8faa-3532e44660c1", "2", implementador),
implementador =
ifelse(`_uuid` == "93f82e5d-1657-4df9-8936-f97edb4b9f26", "2", implementador),
implementador =
ifelse(`_uuid` == "faab88b8-9191-4a2a-bd11-def8ef9c3421", "1", implementador),
testreal =
ifelse(`_uuid` == "aa3cd4df-9062-4af8-a9c0-141aa08c1789", "real", testreal),
Intro01_A =
if_else(Intro01_A == "ACNUR _05703", "ACNUR_05703", Intro01_A)
)
# Delete 6 invalid registries that did not pass the supervision re-call quality check
HH <- HH |>
subset(!`_uuid` %in% c('7a54aa3e-aac9-4cb9-97e1-2983138d7f3e',
'c3da093c-80f7-4e17-acd7-b808024bbeeb',
'686d4e26-573a-4282-88c5-f1452d970df5',
'4c39a23c-dd95-4c07-9664-5521503a795a',
'b702dc78-3553-4c18-9ea9-b3ab5a4b27ce',
'9d7f23c3-6c0b-4658-b6d3-99a0060200b9'))
# Data imputation
# PULSO
HH <- HH |>
mutate(
# Código Pulso
Intro01 = case_when(
`_id` == 49603065 ~ 'ACNUR_03946',
`_id` == 49391490 ~ 'ACNUR_03290',
`_id` == 49490163 ~ 'ACNUR_04655',
TRUE ~ Intro01),
# Número de celular
number = case_when(
`_id` == 49868767 ~ 51951531796,
`_id` == 49490268 ~ 51917529462,
TRUE ~ number))
# Equilibrium
HH <- HH |>
mutate(
# FS_D3_Q1
FS_D3_Q1 = case_when(
`_id` == 48952959 ~ 1000,
`_id` == 49044796 ~ 1500,
`_id` == 49294309 ~ 200,
`_id` == 49363836 ~ 800,
`_id` == 49363877 ~ 400,
`_id` == 49423606 ~ 1500,
TRUE ~ FS_D3_Q1),
# FS_D3_Q2
FS_D3_Q2 = case_when(
`_id` == 49477621 ~ 300,
`_id` == 49122384 ~ 2000,
`_id` == 49294338 ~ 1300,
TRUE ~ FS_D3_Q2))
# Clearing the values of WA_D1_Q2 since there where changes in the skip logic of the regional form
HH <- HH |>
mutate(WA_D1_Q2 =
ifelse(WA_D1_Q1 == "2", NA, WA_D1_Q2))
# creating new variables
# Zones Lima, Norte and Sur
HH <- HH |>
mutate(SECTOR = ifelse(admin1 == "PE15" | admin1 == "PE07", "LIMA METROPOLITANA",
ifelse(admin1 == "PE01" |
admin1 == "PE02" |
admin1 == "PE06" |
admin1 == "PE13" |
admin1 == "PE14" |
admin1 == "PE16" |
admin1 == "PE20" |
admin1 == "PE22" |
admin1 == "PE24", "NORTE",
"SUR")))
# All facilities inside household
HH <- HH |>
mutate(SHE_D1_Q3_ALL = if_else((SHE_D1_Q3_1 == "1" &
SHE_D1_Q3_2 == "1" &
SHE_D1_Q3_3 == "1" &
SHE_D1_Q3_4 == "1"), 1, 0))
```
# Step 5. Individual Pre-processing
In this step data is edited in the variables related with age (AgeMonths, ageMD, age, HH07 and HH07_monts). Since we used an old RMS form as the canvas for the JNA some calculations and other variables where inherited. Age was calculated substracting the Today() variable minus date of birth (HH06). Errors emerged when enumerators tried to correct the date of birth due to an approximate calculation of age (ie. phone survey was held in april, and someone said their DOB was 04-2000, the calculated age would be 24, however he/she might have been born in the final days of April so could still be a 23 y/o)
The nutrition quality checks functions created in step 3 where used to fix errors due to bad programming of the xls form. We spotted the error 3 days deep in the data collection process. Some values were imputed in the nutrition questions since 23 minors where not assessed in the NUT_D8 and NUT_D10 indicators. We used the mode since it was a categorical question
#### AD HOC FOR PERU
```{r}
Individual <- Individual |>
mutate(
AgeMonths = case_when(
`_parent_index` == "213" & `_index` == "385" ~ 180,
`_parent_index` == "2535" & `_index` == "4823" ~ 419,
TRUE ~ AgeMonths),
ageMD = case_when(
`_parent_index` == "213" & `_index` == "385" ~ 0,
`_parent_index` == "3318" & `_index` == "5660" ~ 11,
`_parent_index` == "3610" & `_index` == "5913" ~ 11,
`_parent_index` == "1738" & `_index` == "3525" ~ 1,
`_parent_index` == "1198" & `_index` == "2498" ~ 0,
`_parent_index` == "2535" & `_index` == "4823" ~ 11,
TRUE ~ as.numeric(ageMD)),
age = case_when(
`_parent_index` == "1738" & `_index` == "3525" ~ 5,
`_parent_index` == "1198" & `_index` == "2498" ~ 8,
TRUE ~ age),
HH07 = case_when(
`_parent_index` == "1738" & `_index` == "3525" ~ 5,
`_parent_index` == "1198" & `_index` == "2498" ~ 8,
TRUE ~ HH07),
HH07_months = case_when(
`_parent_index` == "213" & `_index` == "385" ~ 0,
`_parent_index` == "3318" & `_index` == "5660" ~ 11,
`_parent_index` == "3610" & `_index` == "5913" ~ 11,
`_parent_index` == "1738" & `_index` == "3525" ~ 1,
`_parent_index` == "1198" & `_index` == "2498" ~ 0,
`_parent_index` == "2535" & `_index` == "4823" ~ 11,
TRUE ~ as.numeric(HH07_months)))
Individual <- Individual |>
mutate(
HH06 = case_when(
`_parent_index` == "435" & `_index` == "813" ~ as.Date(32599, origin = "1899-12-30"),
TRUE ~ HH06),
age = case_when(
`_parent_index` == "435" & `_index` == "813" ~ 35,
TRUE ~ age),
AgeMonths = case_when(
`_parent_index` == "435" & `_index` == "813" ~ 420,
TRUE ~ AgeMonths),
ageMD = case_when(
`_parent_index` == "435" & `_index` == "813" ~ 0,
TRUE ~ ageMD),
HH07 = case_when(
`_parent_index` == "435" & `_index` == "813" ~ 35,
TRUE ~ HH07),
HH07_months = case_when(
`_parent_index` == "435" & `_index` == "813" ~ 0,
TRUE ~ HH07_months),
NUT_D1_Q1 = case_when(
`_parent_index` == "435" & `_index` == "813" ~ "3",
TRUE ~ NUT_D1_Q1),
NUT_D1_Q1_1 = case_when(
`_parent_index` == "435" & `_index` == "813" ~ 0,
TRUE ~ NUT_D1_Q1_1),
NUT_D1_Q1_2 = case_when(
`_parent_index` == "435" & `_index` == "813" ~ 0,
TRUE ~ NUT_D1_Q1_2),
NUT_D1_Q1_3 = case_when(
`_parent_index` == "435" & `_index` == "813" ~ 1,
TRUE ~ NUT_D1_Q1_3),
NUT_D1_Q1_98 = case_when(
`_parent_index` == "435" & `_index` == "813" ~ 0,
TRUE ~ NUT_D1_Q1_98),
NUT_D1_Q1_99 = case_when(
`_parent_index` == "435" & `_index` == "813" ~ 0,
TRUE ~ NUT_D1_Q1_99),
INT_D1_Q1 = case_when(
`_parent_index` == "435" & `_index` == "813" ~ "1",
TRUE ~ INT_D1_Q1),
INT_D2_Q1 = case_when(
`_parent_index` == "435" & `_index` == "813" ~ "2",
TRUE ~ INT_D2_Q1),
INT_D2_Q2 = case_when(
`_parent_index` == "435" & `_index` == "813" ~ "1",
TRUE ~ INT_D2_Q2),
INT_D2_Q3 = case_when(
`_parent_index` == "435" & `_index` == "813" ~ "1",
TRUE ~ INT_D2_Q3),
HH06 = case_when(
`_parent_index` == "800" & `_index` == "1631" ~ as.Date(24624, origin = "1899-12-30"),
TRUE ~ HH06),
age = case_when(
`_parent_index` == "800" & `_index` == "1631" ~ 56,
TRUE ~ age),
AgeMonths = case_when(
`_parent_index` == "800" & `_index` == "1631" ~ 682,
TRUE ~ AgeMonths),
ageMD = case_when(
`_parent_index` == "800" & `_index` == "1631" ~ 10,
TRUE ~ ageMD),
HH07 = case_when(
`_parent_index` == "800" & `_index` == "1631" ~ 56,
TRUE ~ HH07),
HH07_months = case_when(
`_parent_index` == "800" & `_index` == "1631" ~ 10,
TRUE ~ HH07_months),
INT_D1_Q1 = case_when(
`_parent_index` == "800" & `_index` == "1631" ~ "4",
TRUE ~ INT_D1_Q1),
AgeMonths = case_when(
`_parent_index` == "2485" & `_index` == "4737" ~ 419,
TRUE ~ AgeMonths),
ageMD = case_when(
`_parent_index` == "2485" & `_index` == "4737" ~ 11,
TRUE ~ ageMD),
HH07_months = case_when(
`_parent_index` == "2485" & `_index` == "4737" ~ 11,
TRUE ~ HH07_months),
AgeMonths = case_when(
`_parent_index` == "86" & `_index` == "142" ~ 180,
TRUE ~ AgeMonths),
ageMD = case_when(
`_parent_index` == "86" & `_index` == "142" ~ 0,
TRUE ~ ageMD),
HH07_months = case_when(
`_parent_index` == "86" & `_index` == "142" ~ 0,
TRUE ~ HH07_months),
ageMD = case_when(
`_parent_index` == "3305" & `_index` == "5638" ~ 11,
TRUE ~ ageMD),
HH07_months = case_when(
`_parent_index` == "3305" & `_index` == "5638" ~ 11,
TRUE ~ HH07_months),
age = case_when(
`_parent_index` == "3602" & `_index` == "5905" ~ 51,
TRUE ~ age),
ageMD = case_when(
`_parent_index` == "3602" & `_index` == "5905" ~ 11,
TRUE ~ ageMD),
HH07 = case_when(
`_parent_index` == "3602" & `_index` == "5905" ~ 51,
TRUE ~ HH07),
HH07_months = case_when(
`_parent_index` == "3602" & `_index` == "5905" ~ 11,
TRUE ~ HH07_months),
HH05 = case_when(
`_parent_index` == "3121" & `_index` == "5407" ~ "0",
TRUE ~ HH05),
HH07 = case_when(
`_parent_index` == "3121" & `_index` == "5407" ~ 8,
TRUE ~ HH07),
EDU_D1_Q1 = case_when(
`_parent_index` == "3121" & `_index` == "5407" ~ "1",
TRUE ~ EDU_D1_Q1),
EDU_D3_Q1 = case_when(
`_parent_index` == "3121" & `_index` == "5407" ~ "5",
TRUE ~ EDU_D3_Q1))
# fixing nutrition errors due to bad skip logic
nut_under_6_months <- c("NUT_D4_Q1",
"NUT_D4_Q1_1",
"NUT_D4_Q1_2",
"NUT_D4_Q1_3",
"NUT_D4_Q1_4",
"NUT_D4_Q1_98",
"NUT_D4_Q1_99",
"NUT_D5_Q1",
"NUT_D5_Q2",
"NUT_D5_Q2_1",
"NUT_D5_Q2_2",
"NUT_D5_Q2_3",
"NUT_D5_Q2_4",
"NUT_D5_Q2_5",
"NUT_D5_Q2_6",
"NUT_D5_Q2_7",
"NUT_D5_Q2_8",
"NUT_D5_Q2_9",
"NUT_D5_Q2_10",
"NUT_D5_Q2_98",
"NUT_D5_Q2_99")
nut_over_5_years <- c("NUT_D8_Q1",
"NUT_D8_Q1_1",
"NUT_D8_Q1_2",
"NUT_D8_Q1_3",
"NUT_D8_Q1_4",
"NUT_D8_Q1_5",
"NUT_D8_Q1_6",
"NUT_D8_Q1_7",
"NUT_D8_Q1_8",
"NUT_D8_Q1_9",
"NUT_D8_Q1_98",
"NUT_D8_Q1_99",
"NUT_D10_Q1",
"NUT_D10_Q1_1",
"NUT_D10_Q1_2",
"NUT_D10_Q1_3",
"NUT_D10_Q1_4",
"NUT_D10_Q1_5",
"NUT_D10_Q1_6",
"NUT_D10_Q1_7",
"NUT_D10_Q1_8",
"NUT_D10_Q1_9",
"NUT_D10_Q1_10",
"NUT_D10_Q1_11",
"NUT_D10_Q1_98",
"NUT_D10_Q1_99")
## clearing the columns that should have not been applied due to age group using the adhoc functions created
Individual <- replace_values_nut_under_6_months(Individual, "493", "ATALI VICTORIA TALLIDO GOITIA", nut_under_6_months)
Individual <- replace_values_nut_under_6_months(Individual, "732", "THIAGO", nut_under_6_months)
Individual <- replace_values_nut_under_6_months(Individual, "781", "MÍA ISABELLA MONTIER", nut_under_6_months)
## clearing the columns that should have not been applied due to age group
Individual <- replace_values_nut_over_5_years(Individual, 4, nut_over_5_years)
# creating new variables and recoding them to fix changes in nutrition sector from the regional form for question NUT_D8
Individual <- Individual |>
mutate(NUT_D8_Q1_2_rev = case_when(
NUT_D8_Q1_2 %in% c("1") | NUT_D8_Q1_3 %in% c("1") ~ "1",
NUT_D8_Q1_2 %in% c("0") & NUT_D8_Q1_3 %in% c("0") ~ "0")) |>
select(-NUT_D8_Q1_2, -NUT_D8_Q1_3)
Individual <- Individual |>
mutate(
NUT_D8_Q1_1 = as.character(NUT_D8_Q1_1),
NUT_D8_Q1_2 = as.character(NUT_D8_Q1_2_rev),
NUT_D8_Q1_3 = as.character(NUT_D8_Q1_4),
NUT_D8_Q1_4 = as.character(NUT_D8_Q1_5),
NUT_D8_Q1_5 = as.character(NUT_D8_Q1_6),
NUT_D8_Q1_6 = as.character(NUT_D8_Q1_7),
NUT_D8_Q1_7 = as.character(NUT_D8_Q1_8),
NUT_D8_Q1_8 = as.character(NUT_D8_Q1_9),
NUT_D8_Q1_98 = as.character(NUT_D8_Q1_98),
NUT_D8_Q1_99 = as.character(NUT_D8_Q1_99)) |>
select(-NUT_D8_Q1_9, -NUT_D8_Q1_2_rev)
# creating new variables and recoding them to fix changes in nutrition sector from the regional form for question NUT_D10
Individual <- Individual |>
mutate(NUT_D10_Q1_3_rev = case_when(
NUT_D10_Q1_3 %in% c("1") | NUT_D10_Q1_4 %in% c("1") ~ "1",
NUT_D10_Q1_3 %in% c("0") & NUT_D10_Q1_4 %in% c("0") ~ "0"),
NUT_D10_Q1_7_rev = case_when(
NUT_D10_Q1_8 %in% c("1") | NUT_D10_Q1_9 %in% c("1") ~ "1",
NUT_D10_Q1_8 %in% c("0") & NUT_D10_Q1_9 %in% c("0") ~ "0"),
NUT_D10_Q1_8_rev = case_when(
NUT_D10_Q1_10 %in% c("1") | NUT_D10_Q1_11 %in% c("1") ~ "1",
NUT_D10_Q1_10 %in% c("0") & NUT_D10_Q1_11 %in% c("0") ~ "0")) |>
select(-NUT_D10_Q1_3, -NUT_D10_Q1_4, -NUT_D10_Q1_8, -NUT_D10_Q1_9, -NUT_D10_Q1_10, -NUT_D10_Q1_11)
Individual <- Individual |>
mutate(
NUT_D10_Q1_1 = as.character(NUT_D10_Q1_1),
NUT_D10_Q1_2 = as.character(NUT_D10_Q1_2),
NUT_D10_Q1_3 = as.character(NUT_D10_Q1_3_rev),
NUT_D10_Q1_4 = as.character(NUT_D10_Q1_5),
NUT_D10_Q1_5 = as.character(NUT_D10_Q1_6),
NUT_D10_Q1_6 = as.character(NUT_D10_Q1_7),
NUT_D10_Q1_7 = as.character(NUT_D10_Q1_7_rev),
NUT_D10_Q1_8 = as.character(NUT_D10_Q1_8_rev),
NUT_D10_Q1_98 = as.character(NUT_D10_Q1_98),
NUT_D10_Q1_99 = as.character(NUT_D10_Q1_99)) |>
select(-NUT_D10_Q1_3_rev, -NUT_D10_Q1_7_rev, -NUT_D10_Q1_8_rev)
# Imputation based in the mode
mode_NUT_D8_Q1_1 <-mlv(Individual$NUT_D8_Q1_1, na.rm = TRUE)
mode_NUT_D8_Q1_2 <-mlv(Individual$NUT_D8_Q1_2, na.rm = TRUE)
mode_NUT_D8_Q1_3 <-mlv(Individual$NUT_D8_Q1_3, na.rm = TRUE)
mode_NUT_D8_Q1_4 <-mlv(Individual$NUT_D8_Q1_4, na.rm = TRUE)
mode_NUT_D8_Q1_5 <-mlv(Individual$NUT_D8_Q1_5, na.rm = TRUE)
mode_NUT_D8_Q1_6 <-mlv(Individual$NUT_D8_Q1_6, na.rm = TRUE)
mode_NUT_D8_Q1_7 <-mlv(Individual$NUT_D8_Q1_7, na.rm = TRUE)
mode_NUT_D8_Q1_8 <-mlv(Individual$NUT_D8_Q1_8, na.rm = TRUE)
mode_NUT_D8_Q1_98 <-mlv(Individual$NUT_D8_Q1_98, na.rm = TRUE)
mode_NUT_D8_Q1_99 <-mlv(Individual$NUT_D8_Q1_99, na.rm = TRUE)
mode_NUT_D10_Q1_1 <-mlv(Individual$NUT_D10_Q1_1, na.rm = TRUE)
mode_NUT_D10_Q1_2 <-mlv(Individual$NUT_D10_Q1_2, na.rm = TRUE)
mode_NUT_D10_Q1_3 <-mlv(Individual$NUT_D10_Q1_3, na.rm = TRUE)
mode_NUT_D10_Q1_4 <-mlv(Individual$NUT_D10_Q1_4, na.rm = TRUE)
mode_NUT_D10_Q1_5 <-mlv(Individual$NUT_D10_Q1_5, na.rm = TRUE)
mode_NUT_D10_Q1_6 <-mlv(Individual$NUT_D10_Q1_6, na.rm = TRUE)
mode_NUT_D10_Q1_7 <-mlv(Individual$NUT_D10_Q1_7, na.rm = TRUE)
mode_NUT_D10_Q1_8 <-mlv(Individual$NUT_D10_Q1_8, na.rm = TRUE)
mode_NUT_D10_Q1_98 <-mlv(Individual$NUT_D10_Q1_98, na.rm = TRUE)
mode_NUT_D10_Q1_99 <-mlv(Individual$NUT_D10_Q1_99, na.rm = TRUE)
# Data imputation for multiple option question NUT_D8_Q1
Individual <- Individual |>
mutate(
NUT_D8_Q1_1 = case_when(
is.na(NUT_D8_Q1_1) &
(HH07 %in% c("1", "2", "3", "4") |
(HH07 == "0" & HH07_months %in% c("6", "7", "8", "9", "10", "11"))) ~ mode_NUT_D8_Q1_1,
TRUE ~ NUT_D8_Q1_1),
NUT_D8_Q1_2 = case_when(
is.na(NUT_D8_Q1_2) &
(HH07 %in% c("1", "2", "3", "4") |
(HH07 == "0" & HH07_months %in% c("6", "7", "8", "9", "10", "11"))) ~ mode_NUT_D8_Q1_2,
TRUE ~ NUT_D8_Q1_2),
NUT_D8_Q1_3 = case_when(
is.na(NUT_D8_Q1_3) &
(HH07 %in% c("1", "2", "3", "4") |
(HH07 == "0" & HH07_months %in% c("6", "7", "8", "9", "10", "11"))) ~ mode_NUT_D8_Q1_3,
TRUE ~ NUT_D8_Q1_3),
NUT_D8_Q1_4 = case_when(
is.na(NUT_D8_Q1_4) &
(HH07 %in% c("1", "2", "3", "4") |
(HH07 == "0" & HH07_months %in% c("6", "7", "8", "9", "10", "11"))) ~ mode_NUT_D8_Q1_4,
TRUE ~ NUT_D8_Q1_4),
NUT_D8_Q1_5 = case_when(
is.na(NUT_D8_Q1_5) &
(HH07 %in% c("1", "2", "3", "4") |
(HH07 == "0" & HH07_months %in% c("6", "7", "8", "9", "10", "11"))) ~ mode_NUT_D8_Q1_5,
TRUE ~ NUT_D8_Q1_5),
NUT_D8_Q1_6 = case_when(
is.na(NUT_D8_Q1_6) &
(HH07 %in% c("1", "2", "3", "4") |
(HH07 == "0" & HH07_months %in% c("6", "7", "8", "9", "10", "11"))) ~ mode_NUT_D8_Q1_6,
TRUE ~ NUT_D8_Q1_6),
NUT_D8_Q1_7 = case_when(
is.na(NUT_D8_Q1_7) &
(HH07 %in% c("1", "2", "3", "4") |
(HH07 == "0" & HH07_months %in% c("6", "7", "8", "9", "10", "11"))) ~ mode_NUT_D8_Q1_7,
TRUE ~ NUT_D8_Q1_7),
NUT_D8_Q1_8 = case_when(
is.na(NUT_D8_Q1_8) &
(HH07 %in% c("1", "2", "3", "4") |
(HH07 == "0" & HH07_months %in% c("6", "7", "8", "9", "10", "11"))) ~ mode_NUT_D8_Q1_8,
TRUE ~ NUT_D8_Q1_8),
NUT_D8_Q1_98 = case_when(
is.na(NUT_D8_Q1_98) &
(HH07 %in% c("1", "2", "3", "4") |
(HH07 == "0" & HH07_months %in% c("6", "7", "8", "9", "10", "11"))) ~ mode_NUT_D8_Q1_98,
TRUE ~ NUT_D8_Q1_98),
NUT_D8_Q1_99 = case_when(
is.na(NUT_D8_Q1_99) &
(HH07 %in% c("1", "2", "3", "4") |
(HH07 == "0" & HH07_months %in% c("6", "7", "8", "9", "10", "11"))) ~ mode_NUT_D8_Q1_99,
TRUE ~ NUT_D8_Q1_99),
NUT_D8_Q1 = case_when(
is.na(NUT_D8_Q1) &
(HH07 %in% c("1", "2", "3", "4") |
(HH07 == "0" & HH07_months %in% c("6", "7", "8", "9", "10", "11"))) ~ mode_NUT_D8_Q1_1,
TRUE ~ NUT_D8_Q1)
)
# Data imputation for multiple option question NUT_D10_Q1
Individual <- Individual |>
mutate(
NUT_D10_Q1_1 = case_when(
is.na(NUT_D10_Q1_1) &
(HH07 %in% c("1", "2", "3", "4") |
(HH07 == "0" & HH07_months %in% c("6", "7", "8", "9", "10", "11"))) ~ mode_NUT_D10_Q1_1,
TRUE ~ NUT_D10_Q1_1),
NUT_D10_Q1_2 = case_when(
is.na(NUT_D10_Q1_2) &
(HH07 %in% c("1", "2", "3", "4") |
(HH07 == "0" & HH07_months %in% c("6", "7", "8", "9", "10", "11"))) ~ mode_NUT_D10_Q1_2,
TRUE ~ NUT_D10_Q1_2),
NUT_D10_Q1_3 = case_when(
is.na(NUT_D10_Q1_3) &
(HH07 %in% c("1", "2", "3", "4") |
(HH07 == "0" & HH07_months %in% c("6", "7", "8", "9", "10", "11"))) ~ mode_NUT_D10_Q1_3,
TRUE ~ NUT_D10_Q1_3),
NUT_D10_Q1_4 = case_when(
is.na(NUT_D10_Q1_4) &
(HH07 %in% c("1", "2", "3", "4") |
(HH07 == "0" & HH07_months %in% c("6", "7", "8", "9", "10", "11"))) ~ mode_NUT_D10_Q1_4,
TRUE ~ NUT_D10_Q1_4),
NUT_D10_Q1_5 = case_when(
is.na(NUT_D10_Q1_5) &
(HH07 %in% c("1", "2", "3", "4") |
(HH07 == "0" & HH07_months %in% c("6", "7", "8", "9", "10", "11"))) ~ mode_NUT_D10_Q1_5,
TRUE ~ NUT_D10_Q1_5),
NUT_D10_Q1_6 = case_when(
is.na(NUT_D10_Q1_6) &
(HH07 %in% c("1", "2", "3", "4") |
(HH07 == "0" & HH07_months %in% c("6", "7", "8", "9", "10", "11"))) ~ mode_NUT_D10_Q1_6,
TRUE ~ NUT_D10_Q1_6),
NUT_D10_Q1_7 = case_when(
is.na(NUT_D10_Q1_7) &
(HH07 %in% c("1", "2", "3", "4") |
(HH07 == "0" & HH07_months %in% c("6", "7", "8", "9", "10", "11"))) ~ mode_NUT_D10_Q1_7,
TRUE ~ NUT_D10_Q1_7),
NUT_D10_Q1_8 = case_when(
is.na(NUT_D10_Q1_8) &
(HH07 %in% c("1", "2", "3", "4") |
(HH07 == "0" & HH07_months %in% c("6", "7", "8", "9", "10", "11"))) ~ mode_NUT_D10_Q1_8,
TRUE ~ NUT_D10_Q1_8),
NUT_D10_Q1_98 = case_when(
is.na(NUT_D10_Q1_98) &
(HH07 %in% c("1", "2", "3", "4") |
(HH07 == "0" & HH07_months %in% c("6", "7", "8", "9", "10", "11"))) ~ mode_NUT_D10_Q1_98,
TRUE ~ NUT_D10_Q1_98),
NUT_D10_Q1_99 = case_when(
is.na(NUT_D10_Q1_99) &
(HH07 %in% c("1", "2", "3", "4") |
(HH07 == "0" & HH07_months %in% c("6", "7", "8", "9", "10", "11"))) ~ mode_NUT_D10_Q1_99,
TRUE ~ NUT_D10_Q1_99),
NUT_D10_Q1 = case_when(
is.na(NUT_D10_Q1) &
(HH07 %in% c("1", "2", "3", "4") |
(HH07 == "0" & HH07_months %in% c("6", "7", "8", "9", "10", "11"))) ~ "2 4 5",
TRUE ~ NUT_D10_Q1)
)
# fixing changes in integration sector from the regional form for question INT_D2_Q2 and INT_D2_Q3
Individual <- Individual |>
mutate(
INT_D2_Q2 = case_when(
INT_D2_Q1 %in% c("0", "98") & is.na(INT_D2_Q2) ~ "0",
TRUE ~ INT_D2_Q2),
INT_D2_Q3 = case_when(
INT_D2_Q1 %in% c("0", "98") & is.na(INT_D2_Q3) ~ "0",
TRUE ~ INT_D2_Q3)
)
# creating a variable that will help build the indicator as a sum of different food groups for children among 6 and 59 months of age.
Individual <- Individual |>
mutate(NUT_D10_Q1_ALL =
as.numeric(NUT_D10_Q1_1) +
as.numeric(NUT_D10_Q1_2) +
as.numeric(NUT_D10_Q1_3) +
as.numeric(NUT_D10_Q1_4) +
as.numeric(NUT_D10_Q1_5) +
as.numeric(NUT_D10_Q1_6) +
as.numeric(NUT_D10_Q1_7) +
as.numeric(NUT_D10_Q1_8))
Individual <- Individual |>
mutate(
Age_Group = case_when(
HH07>=0 & HH07 <=4 ~ "0-4",
HH07>4 & HH07 <=11 ~ "5-11",
HH07>11 & HH07 <=17 ~ "12-17",
HH07>17 & HH07 <=29 ~ "18-29",
HH07>29 & HH07 <=39 ~ "30-39",
HH07>39 & HH07 <=49 ~ "40-49",
HH07>49 & HH07 <=59 ~ "50-59",
HH07>59 ~ "60+"))
Individual <- Individual |>
mutate(
HH04 = case_when(
`_parent_index` == "2340" & `_index` == "4524" ~ "1",
TRUE ~ HH04),
HH04 = case_when(
`_parent_index` == "1212" & `_index` == "2533" ~ "1",
TRUE ~ HH04))
```
# Step 6. Filtering
Filter and subset the Individual dataset according to the Parent ID's of the Households that where selected with the filtering
```{r}
HH <- HH |>
filter(testreal == "real") |>
filter(attempt1 == "1") |>
filter(attempt2 == "1") |>
filter(Intro04 == "1") |>
filter(DEMO_1 >= 18) |>
filter(DEMO_00.6 == "1") |>
filter(DEMO_5 == "1") |>
filter(DEMO_7 %in% c(1, 4, 5, 6)) |>
filter(country == "Peru")
HH_final_uuid <-HH$`_index`
Individual <- Individual |>
filter(`_parent_index` %in% HH_final_uuid)
```
# Step 7. Qualitative pre-processing
Creation of new categories in the "Other (specify)" options. Some answers needed to be edited since it already existed an option and there was not need to use the "Other" text-option
#### AD HOC FOR PERU
```{r}
# Re categorization of "other" in Individual dataset
# PRO_D4_Q1_O --> 9 records
Individual <- Individual |>
mutate(
PRO_D4_Q1_96 = case_when(
PRO_D4_Q1_O == "Licencia para conducir" ~ 0,
PRO_D4_Q1_O == "Licencia de conducir" ~ 0,
PRO_D4_Q1_O == "PARTIDA DE NACIMIENTO" ~ 0,
PRO_D4_Q1_O == "Carnet de refugiada" ~ 0,
PRO_D4_Q1_O == "Carnet de refugio" ~ 0,
TRUE ~ PRO_D4_Q1_96),
PRO_D4_Q1_5 = case_when(
PRO_D4_Q1_O == "Carnet de refugiada" ~ 1,
PRO_D4_Q1_O == "Carnet de refugio" ~ 1,
TRUE ~ PRO_D4_Q1_5),
PRO_D4_Q1_6 = case_when(
PRO_D4_Q1_O == "PARTIDA DE NACIMIENTO" ~ 1,
TRUE ~ PRO_D4_Q1_6))
# EDU_D6_Q1_O --> 112 records
Individual <- Individual |>
mutate(
EDU_D1_Q1 = case_when(
EDU_D6_Q1_O == "YA VA PARA LA UNIVERSIDAD NO CONSIGUE CUPO Y NO CUENTA CON RECURSOS PARA UNIVERSIDADES PRIVADAS" ~ NA,
EDU_D6_Q1_O == "YA ACABO EL COLEGIO" ~ NA,
EDU_D6_Q1_O == "ya acabo el colegio" ~ NA,
EDU_D6_Q1_O == "Ya culmino la secundaria" ~ NA,
EDU_D6_Q1_O == "YA SE GRADUO" ~ NA,
EDU_D6_Q1_O == "EL AÑO PASADO ACABO LA SECUNDARIA" ~ NA,
EDU_D6_Q1_O == "YA TERMINÓ EL COLEGIO" ~ NA,
EDU_D6_Q1_O == "en espera para ingresar a la universidad" ~ NA,
EDU_D6_Q1_O == "YA CULMINÓ SUS ESTUDIOS" ~ NA,
EDU_D6_Q1_O == "YA CULMINO SECUNDARIA" ~ NA,
EDU_D6_Q1_O == "POSTULO A LA UNIVERSIDAD NACIONAL Y NO QUEDÓ SELECCIONADA Y NO CUENTA CON LOS RECURSOS PARA INGRESAR A UNA UNIVERSIDAD PRIVADA" ~ NA,
EDU_D6_Q1_O == "TERMINO LA SECUNDARIA" ~ NA,
EDU_D6_Q1_O == "YA CULMINÓ LA SECUNDARIA Y NO TIENE RECURSOS PARA CURSAR LA UNIVERSIDAD" ~ NA,
TRUE ~ EDU_D1_Q1),
EDU_D6_Q1 = case_when(
EDU_D6_Q1_O == "YA VA PARA LA UNIVERSIDAD NO CONSIGUE CUPO Y NO CUENTA CON RECURSOS PARA UNIVERSIDADES PRIVADAS" ~ NA,
EDU_D6_Q1_O == "YA ACABO EL COLEGIO" ~ NA,
EDU_D6_Q1_O == "ya acabo el colegio" ~ NA,
EDU_D6_Q1_O == "Ya culmino la secundaria" ~ NA,
EDU_D6_Q1_O == "YA SE GRADUO" ~ NA,
EDU_D6_Q1_O == "EL AÑO PASADO ACABO LA SECUNDARIA" ~ NA,
EDU_D6_Q1_O == "YA TERMINÓ EL COLEGIO" ~ NA,
EDU_D6_Q1_O == "en espera para ingresar a la universidad" ~ NA,
EDU_D6_Q1_O == "YA CULMINÓ SUS ESTUDIOS" ~ NA,
EDU_D6_Q1_O == "YA CULMINO SECUNDARIA" ~ NA,
EDU_D6_Q1_O == "POSTULO A LA UNIVERSIDAD NACIONAL Y NO QUEDÓ SELECCIONADA Y NO CUENTA CON LOS RECURSOS PARA INGRESAR A UNA UNIVERSIDAD PRIVADA" ~ NA,
EDU_D6_Q1_O == "TERMINO LA SECUNDARIA" ~ NA,
EDU_D6_Q1_O == "YA CULMINÓ LA SECUNDARIA Y NO TIENE RECURSOS PARA CURSAR LA UNIVERSIDAD" ~ NA,
TRUE ~ EDU_D6_Q1),
EDU_D6_Q1_1 = case_when(
EDU_D6_Q1_O == "YA VA PARA LA UNIVERSIDAD NO CONSIGUE CUPO Y NO CUENTA CON RECURSOS PARA UNIVERSIDADES PRIVADAS" ~ NA,
EDU_D6_Q1_O == "YA ACABO EL COLEGIO" ~ NA,
EDU_D6_Q1_O == "ya acabo el colegio" ~ NA,
EDU_D6_Q1_O == "Ya culmino la secundaria" ~ NA,
EDU_D6_Q1_O == "YA SE GRADUO" ~ NA,
EDU_D6_Q1_O == "EL AÑO PASADO ACABO LA SECUNDARIA" ~ NA,
EDU_D6_Q1_O == "YA TERMINÓ EL COLEGIO" ~ NA,
EDU_D6_Q1_O == "en espera para ingresar a la universidad" ~ NA,
EDU_D6_Q1_O == "YA CULMINÓ SUS ESTUDIOS" ~ NA,
EDU_D6_Q1_O == "YA CULMINO SECUNDARIA" ~ NA,
EDU_D6_Q1_O == "POSTULO A LA UNIVERSIDAD NACIONAL Y NO QUEDÓ SELECCIONADA Y NO CUENTA CON LOS RECURSOS PARA INGRESAR A UNA UNIVERSIDAD PRIVADA" ~ NA,
EDU_D6_Q1_O == "TERMINO LA SECUNDARIA" ~ NA,
EDU_D6_Q1_O == "YA CULMINÓ LA SECUNDARIA Y NO TIENE RECURSOS PARA CURSAR LA UNIVERSIDAD" ~ NA,
TRUE ~ EDU_D6_Q1_1),
EDU_D6_Q1_2 = case_when(
EDU_D6_Q1_O == "YA VA PARA LA UNIVERSIDAD NO CONSIGUE CUPO Y NO CUENTA CON RECURSOS PARA UNIVERSIDADES PRIVADAS" ~ NA,
EDU_D6_Q1_O == "YA ACABO EL COLEGIO" ~ NA,
EDU_D6_Q1_O == "ya acabo el colegio" ~ NA,
EDU_D6_Q1_O == "Ya culmino la secundaria" ~ NA,
EDU_D6_Q1_O == "YA SE GRADUO" ~ NA,
EDU_D6_Q1_O == "EL AÑO PASADO ACABO LA SECUNDARIA" ~ NA,
EDU_D6_Q1_O == "YA TERMINÓ EL COLEGIO" ~ NA,
EDU_D6_Q1_O == "en espera para ingresar a la universidad" ~ NA,
EDU_D6_Q1_O == "YA CULMINÓ SUS ESTUDIOS" ~ NA,
EDU_D6_Q1_O == "YA CULMINO SECUNDARIA" ~ NA,
EDU_D6_Q1_O == "POSTULO A LA UNIVERSIDAD NACIONAL Y NO QUEDÓ SELECCIONADA Y NO CUENTA CON LOS RECURSOS PARA INGRESAR A UNA UNIVERSIDAD PRIVADA" ~ NA,
EDU_D6_Q1_O == "TERMINO LA SECUNDARIA" ~ NA,
EDU_D6_Q1_O == "YA CULMINÓ LA SECUNDARIA Y NO TIENE RECURSOS PARA CURSAR LA UNIVERSIDAD" ~ NA,
TRUE ~ EDU_D6_Q1_2),
EDU_D6_Q1_3 = case_when(
EDU_D6_Q1_O == "YA VA PARA LA UNIVERSIDAD NO CONSIGUE CUPO Y NO CUENTA CON RECURSOS PARA UNIVERSIDADES PRIVADAS" ~ NA,
EDU_D6_Q1_O == "YA ACABO EL COLEGIO" ~ NA,
EDU_D6_Q1_O == "ya acabo el colegio" ~ NA,
EDU_D6_Q1_O == "Ya culmino la secundaria" ~ NA,
EDU_D6_Q1_O == "YA SE GRADUO" ~ NA,
EDU_D6_Q1_O == "EL AÑO PASADO ACABO LA SECUNDARIA" ~ NA,
EDU_D6_Q1_O == "YA TERMINÓ EL COLEGIO" ~ NA,
EDU_D6_Q1_O == "en espera para ingresar a la universidad" ~ NA,
EDU_D6_Q1_O == "YA CULMINÓ SUS ESTUDIOS" ~ NA,
EDU_D6_Q1_O == "YA CULMINO SECUNDARIA" ~ NA,
EDU_D6_Q1_O == "POSTULO A LA UNIVERSIDAD NACIONAL Y NO QUEDÓ SELECCIONADA Y NO CUENTA CON LOS RECURSOS PARA INGRESAR A UNA UNIVERSIDAD PRIVADA" ~ NA,
EDU_D6_Q1_O == "TERMINO LA SECUNDARIA" ~ NA,
EDU_D6_Q1_O == "YA CULMINÓ LA SECUNDARIA Y NO TIENE RECURSOS PARA CURSAR LA UNIVERSIDAD" ~ NA,
TRUE ~ EDU_D6_Q1_3),
EDU_D6_Q1_4 = case_when(
EDU_D6_Q1_O == "YA VA PARA LA UNIVERSIDAD NO CONSIGUE CUPO Y NO CUENTA CON RECURSOS PARA UNIVERSIDADES PRIVADAS" ~ NA,
EDU_D6_Q1_O == "YA ACABO EL COLEGIO" ~ NA,
EDU_D6_Q1_O == "ya acabo el colegio" ~ NA,
EDU_D6_Q1_O == "Ya culmino la secundaria" ~ NA,
EDU_D6_Q1_O == "YA SE GRADUO" ~ NA,
EDU_D6_Q1_O == "EL AÑO PASADO ACABO LA SECUNDARIA" ~ NA,
EDU_D6_Q1_O == "YA TERMINÓ EL COLEGIO" ~ NA,
EDU_D6_Q1_O == "en espera para ingresar a la universidad" ~ NA,
EDU_D6_Q1_O == "YA CULMINÓ SUS ESTUDIOS" ~ NA,
EDU_D6_Q1_O == "YA CULMINO SECUNDARIA" ~ NA,
EDU_D6_Q1_O == "POSTULO A LA UNIVERSIDAD NACIONAL Y NO QUEDÓ SELECCIONADA Y NO CUENTA CON LOS RECURSOS PARA INGRESAR A UNA UNIVERSIDAD PRIVADA" ~ NA,
EDU_D6_Q1_O == "TERMINO LA SECUNDARIA" ~ NA,
EDU_D6_Q1_O == "YA CULMINÓ LA SECUNDARIA Y NO TIENE RECURSOS PARA CURSAR LA UNIVERSIDAD" ~ NA,
TRUE ~ EDU_D6_Q1_4),
EDU_D6_Q1_5 = case_when(
EDU_D6_Q1_O == "YA VA PARA LA UNIVERSIDAD NO CONSIGUE CUPO Y NO CUENTA CON RECURSOS PARA UNIVERSIDADES PRIVADAS" ~ NA,
EDU_D6_Q1_O == "YA ACABO EL COLEGIO" ~ NA,
EDU_D6_Q1_O == "ya acabo el colegio" ~ NA,
EDU_D6_Q1_O == "Ya culmino la secundaria" ~ NA,
EDU_D6_Q1_O == "YA SE GRADUO" ~ NA,
EDU_D6_Q1_O == "EL AÑO PASADO ACABO LA SECUNDARIA" ~ NA,
EDU_D6_Q1_O == "YA TERMINÓ EL COLEGIO" ~ NA,
EDU_D6_Q1_O == "en espera para ingresar a la universidad" ~ NA,
EDU_D6_Q1_O == "YA CULMINÓ SUS ESTUDIOS" ~ NA,
EDU_D6_Q1_O == "YA CULMINO SECUNDARIA" ~ NA,
EDU_D6_Q1_O == "POSTULO A LA UNIVERSIDAD NACIONAL Y NO QUEDÓ SELECCIONADA Y NO CUENTA CON LOS RECURSOS PARA INGRESAR A UNA UNIVERSIDAD PRIVADA" ~ NA,
EDU_D6_Q1_O == "TERMINO LA SECUNDARIA" ~ NA,
EDU_D6_Q1_O == "YA CULMINÓ LA SECUNDARIA Y NO TIENE RECURSOS PARA CURSAR LA UNIVERSIDAD" ~ NA,
TRUE ~ EDU_D6_Q1_5),
EDU_D6_Q1_6 = case_when(
EDU_D6_Q1_O == "YA VA PARA LA UNIVERSIDAD NO CONSIGUE CUPO Y NO CUENTA CON RECURSOS PARA UNIVERSIDADES PRIVADAS" ~ NA,
EDU_D6_Q1_O == "YA ACABO EL COLEGIO" ~ NA,
EDU_D6_Q1_O == "ya acabo el colegio" ~ NA,
EDU_D6_Q1_O == "Ya culmino la secundaria" ~ NA,
EDU_D6_Q1_O == "YA SE GRADUO" ~ NA,
EDU_D6_Q1_O == "EL AÑO PASADO ACABO LA SECUNDARIA" ~ NA,
EDU_D6_Q1_O == "YA TERMINÓ EL COLEGIO" ~ NA,
EDU_D6_Q1_O == "en espera para ingresar a la universidad" ~ NA,
EDU_D6_Q1_O == "YA CULMINÓ SUS ESTUDIOS" ~ NA,
EDU_D6_Q1_O == "YA CULMINO SECUNDARIA" ~ NA,
EDU_D6_Q1_O == "POSTULO A LA UNIVERSIDAD NACIONAL Y NO QUEDÓ SELECCIONADA Y NO CUENTA CON LOS RECURSOS PARA INGRESAR A UNA UNIVERSIDAD PRIVADA" ~ NA,
EDU_D6_Q1_O == "TERMINO LA SECUNDARIA" ~ NA,
EDU_D6_Q1_O == "YA CULMINÓ LA SECUNDARIA Y NO TIENE RECURSOS PARA CURSAR LA UNIVERSIDAD" ~ NA,
TRUE ~ EDU_D6_Q1_6),
EDU_D6_Q1_96 = case_when(
EDU_D6_Q1_O == "YA VA PARA LA UNIVERSIDAD NO CONSIGUE CUPO Y NO CUENTA CON RECURSOS PARA UNIVERSIDADES PRIVADAS" ~ NA,
EDU_D6_Q1_O == "YA ACABO EL COLEGIO" ~ NA,
EDU_D6_Q1_O == "ya acabo el colegio" ~ NA,
EDU_D6_Q1_O == "Ya culmino la secundaria" ~ NA,
EDU_D6_Q1_O == "YA SE GRADUO" ~ NA,
EDU_D6_Q1_O == "EL AÑO PASADO ACABO LA SECUNDARIA" ~ NA,
EDU_D6_Q1_O == "YA TERMINÓ EL COLEGIO" ~ NA,
EDU_D6_Q1_O == "en espera para ingresar a la universidad" ~ NA,
EDU_D6_Q1_O == "YA CULMINÓ SUS ESTUDIOS" ~ NA,
EDU_D6_Q1_O == "YA CULMINO SECUNDARIA" ~ NA,
EDU_D6_Q1_O == "POSTULO A LA UNIVERSIDAD NACIONAL Y NO QUEDÓ SELECCIONADA Y NO CUENTA CON LOS RECURSOS PARA INGRESAR A UNA UNIVERSIDAD PRIVADA" ~ NA,
EDU_D6_Q1_O == "TERMINO LA SECUNDARIA" ~ NA,
EDU_D6_Q1_O == "YA CULMINÓ LA SECUNDARIA Y NO TIENE RECURSOS PARA CURSAR LA UNIVERSIDAD" ~ NA,
TRUE ~ EDU_D6_Q1_96),
EDU_D6_Q1_98 = case_when(
EDU_D6_Q1_O == "YA VA PARA LA UNIVERSIDAD NO CONSIGUE CUPO Y NO CUENTA CON RECURSOS PARA UNIVERSIDADES PRIVADAS" ~ NA,
EDU_D6_Q1_O == "YA ACABO EL COLEGIO" ~ NA,
EDU_D6_Q1_O == "ya acabo el colegio" ~ NA,
EDU_D6_Q1_O == "Ya culmino la secundaria" ~ NA,
EDU_D6_Q1_O == "YA SE GRADUO" ~ NA,
EDU_D6_Q1_O == "EL AÑO PASADO ACABO LA SECUNDARIA" ~ NA,
EDU_D6_Q1_O == "YA TERMINÓ EL COLEGIO" ~ NA,
EDU_D6_Q1_O == "en espera para ingresar a la universidad" ~ NA,
EDU_D6_Q1_O == "YA CULMINÓ SUS ESTUDIOS" ~ NA,
EDU_D6_Q1_O == "YA CULMINO SECUNDARIA" ~ NA,
EDU_D6_Q1_O == "POSTULO A LA UNIVERSIDAD NACIONAL Y NO QUEDÓ SELECCIONADA Y NO CUENTA CON LOS RECURSOS PARA INGRESAR A UNA UNIVERSIDAD PRIVADA" ~ NA,
EDU_D6_Q1_O == "TERMINO LA SECUNDARIA" ~ NA,
EDU_D6_Q1_O == "YA CULMINÓ LA SECUNDARIA Y NO TIENE RECURSOS PARA CURSAR LA UNIVERSIDAD" ~ NA,
TRUE ~ EDU_D6_Q1_98),
EDU_D6_Q1_99 = case_when(
EDU_D6_Q1_O == "YA VA PARA LA UNIVERSIDAD NO CONSIGUE CUPO Y NO CUENTA CON RECURSOS PARA UNIVERSIDADES PRIVADAS" ~ NA,
EDU_D6_Q1_O == "YA ACABO EL COLEGIO" ~ NA,
EDU_D6_Q1_O == "ya acabo el colegio" ~ NA,
EDU_D6_Q1_O == "Ya culmino la secundaria" ~ NA,
EDU_D6_Q1_O == "YA SE GRADUO" ~ NA,
EDU_D6_Q1_O == "EL AÑO PASADO ACABO LA SECUNDARIA" ~ NA,
EDU_D6_Q1_O == "YA TERMINÓ EL COLEGIO" ~ NA,
EDU_D6_Q1_O == "en espera para ingresar a la universidad" ~ NA,
EDU_D6_Q1_O == "YA CULMINÓ SUS ESTUDIOS" ~ NA,
EDU_D6_Q1_O == "YA CULMINO SECUNDARIA" ~ NA,
EDU_D6_Q1_O == "POSTULO A LA UNIVERSIDAD NACIONAL Y NO QUEDÓ SELECCIONADA Y NO CUENTA CON LOS RECURSOS PARA INGRESAR A UNA UNIVERSIDAD PRIVADA" ~ NA,
EDU_D6_Q1_O == "TERMINO LA SECUNDARIA" ~ NA,
EDU_D6_Q1_O == "YA CULMINÓ LA SECUNDARIA Y NO TIENE RECURSOS PARA CURSAR LA UNIVERSIDAD" ~ NA,
TRUE ~ EDU_D6_Q1_99),
EDU_D6_Q1_2 = case_when(
EDU_D6_Q1_O == "NO CONSIGUIÓ CUPO EN UN ESTADAL Y ESTÁ EMBARAZADA Y AL SER MADRE SOLTERA SE LE COMPLICA INGRESAR A UN PRIVADO" ~ 1,
EDU_D6_Q1_O == "POR CAMBIO DE DOMICILIO QUE NO CONSIGUIÓ EN ESTADAL" ~ 1,
TRUE ~ EDU_D6_Q1_2),
EDU_D6_Q1_7 = case_when(
EDU_D6_Q1_O == "LA NIÑA TIENE AUTISMO" ~ 1,
EDU_D6_Q1_O == "INCAPACIDAD" ~ 1,
EDU_D6_Q1_O == "Dificultad en el desarrollo del lenguaje" ~ 1,
EDU_D6_Q1_O == "DISCAPACIDAD, TIENE DIFICULTADES PARA COMER" ~ 1,
EDU_D6_Q1_O == "Presenta discapacidad visual de nacimiento" ~ 1,
EDU_D6_Q1_O == "TIENE UNA CONDICION ESPECIAL POR SALUD POR ESO NO ASISTE A LA ESCUELA" ~ 1,
EDU_D6_Q1_O == "TIENE UNA DISCAPACIDAD AUTISMO." ~ 1,
EDU_D6_Q1_O == "TIENE PROBLEMA DE APRENDIZAJE NO ENTIENDE MUCHO" ~ 1,
EDU_D6_Q1_O == "ES AUTISTA, NO HA ENCONTRADO UN CENTRO EDUCATIVO QUE PUEDA PAGAR, Y NO TINE SIS" ~ 1,
EDU_D6_Q1_O == "NIÑO CON DISCAPACIDAD" ~ 1,
EDU_D6_Q1_O == "TIENE RETRASO PSICOMOTRIZ. NO HABLA NI CAMINA." ~ 1,
EDU_D6_Q1_O == "CONDICION DE AUTISMO, ATENCION EN CASA" ~ 1,
EDU_D6_Q1_O == "TIENE AUTISMO Y NO HA CONSEGUIDO UNA ESCUELA DONDE PUEDAN ATENDER A NIÑOS CON SU CONDICION" ~ 1,
EDU_D6_Q1_O == "SUFRE DE DISCAPACIDAD INTELECTUAL" ~ 1,
EDU_D6_Q1_O == "TERAPIA DE LENGUAJE EN HOGAR, NO VA POR FALTA DE PASAJES" ~ 1,
EDU_D6_Q1_O == "salud" ~ 1,
EDU_D6_Q1_O == "SALUD" ~ 1,
EDU_D6_Q1_O == "TIENE MICROCEFALIA" ~ 1,
EDU_D6_Q1_O == "EL NIÑO TIENE UNA CONDICION D SALUD Y SU MADRE TEME MANDARLO AL COLEGIO" ~ 1,
EDU_D6_Q1_O == "EL NIÑO TIENE HEMORROIDES Y NECESITA OPERACION , ELIMINA SANGRE" ~ 1,
EDU_D6_Q1_O == "LA NIÑA CUENTA CON HIDROCEFALIA" ~ 1,
EDU_D6_Q1_O == "La familia estuvo delicada de salud y no pudieron inscribirla." ~ 1,
EDU_D6_Q1_O == "PORQUE LO OPERARON HACE QUINCE DIAS Y NO LO HA PODIDO MATRICULAR" ~ 1,
EDU_D6_Q1_O == "Todavía no pueden inscribirlo por su salud." ~ 1,
EDU_D1_Q1 == "0" ~ 0),
EDU_D6_Q1_96 = case_when(
EDU_D6_Q1_O == "LA NIÑA TIENE AUTISMO" ~ 0,
EDU_D6_Q1_O == "INCAPACIDAD" ~ 0,
EDU_D6_Q1_O == "Dificultad en el desarrollo del lenguaje" ~ 0,
EDU_D6_Q1_O == "DISCAPACIDAD, TIENE DIFICULTADES PARA COMER" ~ 0,