Cleaning Data and Basic Statistics HW
Lydia Schwartz
2023-05-22
1 Data Cleaning
1.1 Load Libraries
library(tidyverse) # for the map() command## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.2 ✔ readr 2.1.4
## ✔ forcats 1.0.0 ✔ stringr 1.5.0
## ✔ ggplot2 3.4.2 ✔ tibble 3.2.1
## ✔ lubridate 1.9.2 ✔ tidyr 1.3.0
## ✔ purrr 1.0.1
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errorslibrary(psych) # for the describe () command##
## Attaching package: 'psych'
##
## The following objects are masked from 'package:ggplot2':
##
## %+%, alphalibrary(naniar) # for the gg_miss-upset() command
library(expss) # for the cross_cases() command## Loading required package: maditr
##
## To select columns from data: columns(mtcars, mpg, vs:carb)
##
##
## Attaching package: 'maditr'
##
## The following objects are masked from 'package:dplyr':
##
## between, coalesce, first, last
##
## The following object is masked from 'package:purrr':
##
## transpose
##
## The following object is masked from 'package:readr':
##
## cols
##
##
## Attaching package: 'expss'
##
## The following object is masked from 'package:naniar':
##
## is_na
##
## The following objects are masked from 'package:stringr':
##
## fixed, regex
##
## The following objects are masked from 'package:dplyr':
##
## compute, contains, na_if, recode, vars, where
##
## The following objects are masked from 'package:purrr':
##
## keep, modify, modify_if, when
##
## The following objects are masked from 'package:tidyr':
##
## contains, nest
##
## The following object is masked from 'package:ggplot2':
##
## varslibrary(ggplot2)1.2 Import Data
df <- read.csv(file="/Users/lydiaschwartz/Desktop/r studio/Data Cleaning and Basic Statistics HW/EAMMi2-Data1.2.csv", header=T)1.3 Viewing Data
names(df)## [1] "StartDate" "EndDate" "Status"
## [4] "Progress" "Duration..in.seconds." "Finished"
## [7] "RecordedDate" "ResponseId" "RecipientLastName"
## [10] "RecipientFirstName" "RecipientEmail" "ExternalReference"
## [13] "DistributionChannel" "informedconsent" "moa1.1_1"
## [16] "moa1.1_2" "moa1.1_3" "moa1.1_4"
## [19] "moa1.1_5" "moa1.1_6" "moa1.1_7"
## [22] "moa1.1_8" "moa1.1_9" "moa1.1_10"
## [25] "moa1.2_1" "moa1.2_2" "moa1.2_3"
## [28] "moa1.2_4" "moa1.2_5" "moa1.2_6"
## [31] "moa1.2_7" "moa1.2_8" "moa1.2_9"
## [34] "moa1.2_10" "moa2.1_1" "moa2.1_2"
## [37] "moa2.1_3" "moa2.1_4" "moa2.1_5"
## [40] "moa2.1_6" "moa2.1_7" "moa2.1_8"
## [43] "moa2.1_9" "moa2.1_10" "moa2.2_1"
## [46] "moa2.2_2" "moa2.2_3" "moa2.2_4"
## [49] "moa2.2_5" "moa2.2_6" "moa2.2_7"
## [52] "moa2.2_8" "moa2.2_9" "moa2.2_10"
## [55] "adult_Q" "MOA_IMP_biascheck" "MOA_ach_biascheck"
## [58] "MOA_IMP_dummy" "MOA.ACH_dummy" "Q65_First.Click"
## [61] "Q65_Last.Click" "Q65_Page.Submit" "Q65_Click.Count"
## [64] "IDEA_1" "IDEA_2" "IDEA_3"
## [67] "IDEA_4" "IDEA_5" "IDEA_6"
## [70] "IDEA_7" "IDEA_8" "IDEA.biascheck"
## [73] "IDEA.bias.dummy" "Q66_First.Click" "Q66_Last.Click"
## [76] "Q66_Page.Submit" "Q66_Click.Count" "politics"
## [79] "party" "president" "Q74_First.Click"
## [82] "Q74_Last.Click" "Q74_Page.Submit" "Q74_Click.Count"
## [85] "swb_1" "swb_2" "swb_3"
## [88] "swb_4" "swb_5" "swb_6"
## [91] "Q67_First.Click" "Q67_Last.Click" "Q67_Page.Submit"
## [94] "Q67_Click.Count" "mindful_1" "mindful_2"
## [97] "mindful_3" "mindful_4" "mindful_5"
## [100] "mindful_6" "mindful_7" "mindful_8"
## [103] "mindful_9" "mindful_10" "mindful_11"
## [106] "mindful_12" "mindful_13" "mindful_14"
## [109] "mindful_15" "mindful_biascheck" "mindful_bias_dummy"
## [112] "Q68_First.Click" "Q68_Last.Click" "Q68_Page.Submit"
## [115] "Q68_Click.Count" "belong_1" "belong_2"
## [118] "belong_3" "belong_4" "belong_5"
## [121] "belong_6" "belong_7" "belong_8"
## [124] "belong_9" "belong_10" "belnow"
## [127] "belong_biascheck" "belong_bias_dummy" "Q72_First.Click"
## [130] "Q72_Last.Click" "Q72_Page.Submit" "Q72_Click.Count"
## [133] "efficacy_1" "efficacy_2" "efficacy_3"
## [136] "efficacy_4" "efficacy_5" "efficacy_6"
## [139] "efficacy_7" "efficacy_8" "efficacy_9"
## [142] "efficacy_10" "efficacy_biascheck" "efficacy_bias_dummy"
## [145] "Q77_First.Click" "Q77_Last.Click" "Q77_Page.Submit"
## [148] "Q77_Click.Count" "support_1" "support_2"
## [151] "support_3" "support_4" "support_5"
## [154] "support_6" "support_7" "support_8"
## [157] "support_9" "support_10" "support_11"
## [160] "support_12" "support_biascheck" "support_bias_dummy"
## [163] "Q96_First.Click" "Q96_Last.Click" "Q96_Page.Submit"
## [166] "Q96_Click.Count" "SocMedia_1" "SocMedia_2"
## [169] "SocMedia_3" "SocMedia_4" "SocMedia_5"
## [172] "SocMedia_6" "SocMedia_7" "SocMedia_8"
## [175] "SocMedia_9" "SocMedia_10" "SocMedia_11"
## [178] "SocMedia_biascheck" "SocMedia_bias_dummy" "Q80_First.Click"
## [181] "Q80_Last.Click" "Q80_Page.Submit" "Q80_Click.Count"
## [184] "usdream_1" "usdream_2" "usdream_3"
## [187] "Q73_First.Click" "Q73_Last.Click" "Q73_Page.Submit"
## [190] "Q73_Click.Count" "freq" "transgres"
## [193] "relation" "relation_10_TEXT" "fault"
## [196] "feel" "common" "attenion2"
## [199] "Q78_First.Click" "Q78_Last.Click" "Q78_Page.Submit"
## [202] "Q78_Click.Count" "transgres_1" "transgres_2"
## [205] "transgres_3" "transgres_4" "Q79_First.Click"
## [208] "Q79_Last.Click" "Q79_Page.Submit" "Q79_Click.Count"
## [211] "NPI1" "NPI2" "NPI3"
## [214] "NPI4" "NPI5" "NPI6"
## [217] "NPI7" "NPI8" "NPI9"
## [220] "NPI10" "NPI11" "NPI12"
## [223] "NPI13" "exploit_1" "exploit_2"
## [226] "exploit_3" "NPI_biascheck" "NPI_bias_dummy"
## [229] "Q76_First.Click" "Q76_Last.Click" "Q76_Page.Submit"
## [232] "Q76_Click.Count" "Q11" "Q14_1"
## [235] "Q14_2" "Q14_3" "Q14_4"
## [238] "Q14_5" "Q14_6" "Q14_6_TEXT"
## [241] "Q10_1" "Q10_2" "Q10_3"
## [244] "Q10_4" "Q10_5" "Q10_6"
## [247] "Q10_7" "Q10_8" "Q10_9"
## [250] "Q10_10" "Q10_11" "Q10_12"
## [253] "Q10_13" "Q10_14" "Q10_15"
## [256] "Q71_First.Click" "Q71_Last.Click" "Q71_Page.Submit"
## [259] "Q71_Click.Count" "physSx_1" "physSx_2"
## [262] "physSx_3" "physSx_4" "physSx_5"
## [265] "physSx_6" "physSx_7" "physSx_8"
## [268] "physSx_9" "physSx_10" "physSx_11"
## [271] "physSx_12" "physSx_13" "phys_sx_biaschec"
## [274] "phys_sym_bias_dummy." "Q70_First.Click" "Q70_Last.Click"
## [277] "Q70_Page.Submit" "Q70_Click.Count" "stress_1"
## [280] "stress_2" "stress_3" "stress_4"
## [283] "stress_5" "stress_6" "stress_7"
## [286] "stress_8" "stress_9" "stress_10"
## [289] "stress_biascheck" "stress_bias_dummy" "Q69_First.Click"
## [292] "Q69_Last.Click" "Q69_Page.Submit" "Q69_Click.Count"
## [295] "marriage1_1" "marriage1_2" "marriage1_3"
## [298] "marriage1_4" "marriage2" "marriage3"
## [301] "marriage4" "marriage5" "Q75_First.Click"
## [304] "Q75_Last.Click" "Q75_Page.Submit" "Q75_Click.Count"
## [307] "school" "sex" "age"
## [310] "edu" "sibling" "race"
## [313] "race_6_TEXT" "Q82" "Q83"
## [316] "income" "place2" "Q80"
## [319] "place" "Q81" "Q81_First.Click"
## [322] "Q81_Last.Click" "Q81_Page.Submit" "Q81_Click.Count"
## [325] "comments" "affiliation" "response_bias_SUM"
## [328] "school_coded"head(df)## StartDate EndDate Status Progress Duration..in.seconds. Finished
## 1 12/02/16 12/02/16 0 100 1839 1
## 2 11/16/16 11/16/16 0 100 1467 1
## 3 11/09/16 11/09/16 0 99 2185 0
## 4 11/07/16 11/07/16 0 100 2904 1
## 5 11/18/16 11/18/16 0 100 1229 1
## 6 11/07/16 11/07/16 0 100 2068 1
## RecordedDate ResponseId RecipientLastName RecipientFirstName
## 1 12/2/2016 5:38 R_BJN3bQqi1zUMid3 NA NA
## 2 11/16/2016 11:53 R_2TGbiBXmAtxywsD NA NA
## 3 11/16/2016 1:22 R_12G7bIqN2wB2N65 NA NA
## 4 11/7/2016 4:54 R_39pldNoon8CePfP NA NA
## 5 11/18/2016 0:30 R_1QiKb2LdJo1Bhvv NA NA
## 6 11/7/2016 14:42 R_pmwDTZyCyCycXwB NA NA
## RecipientEmail ExternalReference DistributionChannel informedconsent moa1.1_1
## 1 NA NA anonymous 1 4
## 2 NA NA anonymous 1 4
## 3 NA NA anonymous 1 4
## 4 NA NA anonymous 1 4
## 5 NA NA anonymous 1 4
## 6 NA NA anonymous 1 4
## moa1.1_2 moa1.1_3 moa1.1_4 moa1.1_5 moa1.1_6 moa1.1_7 moa1.1_8 moa1.1_9
## 1 4 3 2 2 3 2 1 4
## 2 4 4 2 3 3 4 3 3
## 3 4 4 1 1 4 2 3 4
## 4 3 3 1 1 2 1 1 1
## 5 4 4 1 1 3 1 1 4
## 6 3 4 2 3 4 2 1 3
## moa1.1_10 moa1.2_1 moa1.2_2 moa1.2_3 moa1.2_4 moa1.2_5 moa1.2_6 moa1.2_7
## 1 3 2 1 2 1 1 1 2
## 2 3 1 1 2 2 1 1 1
## 3 3 2 1 1 1 1 1 2
## 4 1 1 1 1 1 1 1 2
## 5 3 2 1 2 1 3 3 1
## 6 4 1 1 1 1 1 1 1
## moa1.2_8 moa1.2_9 moa1.2_10 moa2.1_1 moa2.1_2 moa2.1_3 moa2.1_4 moa2.1_5
## 1 3 3 2 4 4 4 4 3
## 2 1 2 3 3 4 2 4 4
## 3 3 3 3 4 2 2 4 3
## 4 3 2 3 4 2 2 4 3
## 5 1 3 2 4 4 3 4 4
## 6 1 1 3 4 4 4 4 2
## moa2.1_6 moa2.1_7 moa2.1_8 moa2.1_9 moa2.1_10 moa2.2_1 moa2.2_2 moa2.2_3
## 1 4 4 4 3 2 2 1 1
## 2 3 2 4 2 1 3 1 2
## 3 3 4 4 3 2 2 1 1
## 4 2 4 2 3 2 2 1 1
## 5 3 4 4 3 3 3 3 3
## 6 4 3 4 4 4 2 1 1
## moa2.2_4 moa2.2_5 moa2.2_6 moa2.2_7 moa2.2_8 moa2.2_9 moa2.2_10 adult_Q
## 1 3 2 3 3 2 2 1 1
## 2 2 1 2 2 2 2 1 1
## 3 2 1 2 3 1 1 1 1
## 4 2 1 2 2 2 2 1 1
## 5 3 3 2 3 3 2 3 1
## 6 2 1 2 2 1 2 1 1
## MOA_IMP_biascheck MOA_ach_biascheck MOA_IMP_dummy MOA.ACH_dummy
## 1 64 38 0 0
## 2 62 33 0 0
## 3 61 33 0 0
## 4 46 32 0 0
## 5 62 47 0 0
## 6 67 27 0 0
## Q65_First.Click Q65_Last.Click Q65_Page.Submit Q65_Click.Count IDEA_1 IDEA_2
## 1 37.139 307.731 308.890 45 3 4
## 2 120.026 336.428 338.177 58 4 4
## 3 27.705 154.447 155.544 47 4 4
## 4 19.656 297.285 298.509 43 4 4
## 5 12.867 121.932 122.254 46 4 4
## 6 15.652 223.372 225.431 50 3 4
## IDEA_3 IDEA_4 IDEA_5 IDEA_6 IDEA_7 IDEA_8 IDEA.biascheck IDEA.bias.dummy
## 1 4 3 4 4 4 4 30 0
## 2 4 4 3 4 4 4 31 0
## 3 4 4 4 4 3 3 30 0
## 4 3 3 4 4 4 4 30 0
## 5 3 4 3 3 3 4 28 0
## 6 3 3 4 4 3 2 26 0
## Q66_First.Click Q66_Last.Click Q66_Page.Submit Q66_Click.Count politics party
## 1 44.705 86.585 87.514 11 2 3
## 2 19.927 65.200 67.162 13 1 4
## 3 23.170 51.401 52.408 11 2 8
## 4 27.467 172.797 174.119 9 8 8
## 5 23.952 52.176 53.355 9 1 8
## 6 9.475 72.935 73.937 13 8 8
## president
## 1
## 2 None, but I was a US Citizen and had a gun next to my head, I would vote for Trump
## 3 Hillary Clinton
## 4 Hillary Clinton
## 5 Sanders
## 6 No one.
## Q74_First.Click Q74_Last.Click Q74_Page.Submit Q74_Click.Count swb_1 swb_2
## 1 13.052 40.445 46.399 2 4 6
## 2 4.899 28.125 55.107 6 3 4
## 3 34.868 48.402 56.371 4 1 2
## 4 66.886 119.219 135.295 4 5 6
## 5 23.614 32.221 35.338 4 2 5
## 6 12.314 41.232 54.436 6 4 4
## swb_3 swb_4 swb_5 swb_6 Q67_First.Click Q67_Last.Click Q67_Page.Submit
## 1 5 5 3 3 9.627 40.388 41.198
## 2 5 5 4 4 8.607 29.115 29.955
## 3 2 2 2 2 37.656 53.240 54.603
## 4 6 5 6 3 13.587 55.197 56.150
## 5 5 3 2 5 6.798 22.246 23.138
## 6 6 5 1 4 7.927 44.108 48.227
## Q67_Click.Count mindful_1 mindful_2 mindful_3 mindful_4 mindful_5 mindful_6
## 1 7 4 2 2 2 4 1
## 2 7 2 2 2 1 3 1
## 3 9 2 3 1 2 3 1
## 4 7 2 2 1 2 2 1
## 5 7 4 5 3 2 4 1
## 6 7 1 4 3 3 5 1
## mindful_7 mindful_8 mindful_9 mindful_10 mindful_11 mindful_12 mindful_13
## 1 2 2 2 2 2 4 1
## 2 1 1 2 2 1 2 1
## 3 2 2 5 3 2 1 1
## 4 2 2 3 2 2 3 3
## 5 4 2 1 2 2 6 5
## 6 5 6 3 5 1 3 2
## mindful_14 mindful_15 mindful_biascheck mindful_bias_dummy Q68_First.Click
## 1 2 4 36 0 32.692
## 2 1 5 27 0 13.184
## 3 1 4 33 0 48.022
## 4 2 4 33 0 110.432
## 5 2 5 48 0 81.124
## 6 4 5 51 0 33.458
## Q68_Last.Click Q68_Page.Submit Q68_Click.Count belong_1 belong_2 belong_3
## 1 154.123 157.391 15 4 2 4
## 2 76.856 77.629 22 2 3 1
## 3 142.665 143.398 20 4 4 2
## 4 255.734 257.134 17 3 4 1
## 5 134.499 135.848 16 4 3 3
## 6 212.770 213.511 25 2 3 2
## belong_4 belong_5 belong_6 belong_7 belong_8 belong_9 belong_10 belnow
## 1 4 4 2 5 2 4 3 4
## 2 5 4 4 2 4 5 4 4
## 3 5 4 4 2 3 4 4 2
## 4 5 4 5 2 4 4 4 4
## 5 4 4 5 1 3 2 3 4
## 6 5 4 5 1 4 4 4 3
## belong_biascheck belong_bias_dummy Q72_First.Click Q72_Last.Click
## 1 38 0 8.221 80.460
## 2 38 0 6.774 65.987
## 3 38 0 5.697 71.192
## 4 40 0 6.096 86.373
## 5 36 0 58.613 121.436
## 6 37 0 6.124 70.638
## Q72_Page.Submit Q72_Click.Count efficacy_1 efficacy_2 efficacy_3 efficacy_4
## 1 82.781 13 4 3 4 3
## 2 67.158 18 3 3 3 4
## 3 72.176 13 3 3 1 2
## 4 87.231 14 4 1 2 3
## 5 122.620 11 3 3 2 3
## 6 72.503 15 3 2 3 2
## efficacy_5 efficacy_6 efficacy_7 efficacy_8 efficacy_9 efficacy_10
## 1 3 4 3 3 4 3
## 2 4 4 3 3 3 4
## 3 2 3 1 3 2 2
## 4 2 4 2 3 4 3
## 5 3 3 3 3 4 3
## 6 1 3 2 3 3 2
## efficacy_biascheck efficacy_bias_dummy Q77_First.Click Q77_Last.Click
## 1 34 0 15.372 104.315
## 2 34 0 11.711 74.768
## 3 22 0 38.964 179.667
## 4 28 0 16.050 168.886
## 5 30 0 32.150 59.030
## 6 24 0 6.259 69.817
## Q77_Page.Submit Q77_Click.Count support_1 support_2 support_3 support_4
## 1 105.195 11 7 4 6 5
## 2 75.558 21 7 7 7 6
## 3 182.727 13 6 6 5 2
## 4 170.530 10 6 6 7 3
## 5 60.273 11 6 6 5 5
## 6 70.970 13 7 7 6 6
## support_5 support_6 support_7 support_8 support_9 support_10 support_11
## 1 6 6 7 7 7 4 6
## 2 7 6 6 7 7 7 7
## 3 7 5 5 3 6 6 5
## 4 7 6 5 4 6 6 6
## 5 6 6 7 6 6 6 7
## 6 7 2 2 1 1 7 6
## support_12 support_biascheck support_bias_dummy Q96_First.Click
## 1 7 72 0 12.241
## 2 7 81 0 7.482
## 3 6 62 0 18.845
## 4 5 67 0 30.307
## 5 6 72 0 13.096
## 6 2 54 0 24.841
## Q96_Last.Click Q96_Page.Submit Q96_Click.Count SocMedia_1 SocMedia_2
## 1 91.497 92.381 17 4 2
## 2 34.247 35.467 19 3 2
## 3 74.388 76.037 14 3 3
## 4 150.285 151.869 18 4 2
## 5 43.727 45.041 12 3 3
## 6 110.942 111.636 18 1 1
## SocMedia_3 SocMedia_4 SocMedia_5 SocMedia_6 SocMedia_7 SocMedia_8 SocMedia_9
## 1 5 3 5 5 5 4 5
## 2 4 2 1 1 1 1 2
## 3 4 2 3 4 4 2 3
## 4 5 2 2 4 4 1 3
## 5 5 2 2 4 4 2 4
## 6 2 1 1 1 2 1 1
## SocMedia_10 SocMedia_11 SocMedia_biascheck SocMedia_bias_dummy
## 1 5 4 47 0
## 2 4 2 23 0
## 3 3 3 34 0
## 4 4 4 35 0
## 5 4 4 37 0
## 6 1 1 13 0
## Q80_First.Click Q80_Last.Click Q80_Page.Submit Q80_Click.Count usdream_1
## 1 17.470 59.573 60.431 11 4
## 2 10.768 45.340 47.007 15 4
## 3 30.059 66.498 68.018 12 2
## 4 112.432 161.455 163.036 11 1
## 5 22.246 53.406 55.275 12 3
## 6 5.361 89.568 90.785 15 1
## usdream_2 usdream_3 Q73_First.Click Q73_Last.Click Q73_Page.Submit
## 1 4 1 14.144 24.073 27.558
## 2 4 1 5.240 27.206 36.973
## 3 2 1 5.671 16.751 19.891
## 4 3 1 71.153 82.926 98.687
## 5 4 1 21.293 32.533 35.448
## 6 1 2 6.771 37.203 45.268
## Q73_Click.Count freq
## 1 3 3
## 2 5 4
## 3 3 6
## 4 3 3
## 5 3 4
## 6 4 2
## transgres
## 1 told my friend that something he did was wrong and hurtful to somebody else.
## 2 got very passive
## 3 you don't want to see me
## 4 I tried to excuse myself and said I was sorry
## 5 Got angry.
## 6 why didn't you tell him?
## relation relation_10_TEXT fault feel common attenion2 Q78_First.Click
## 1 4 6 3 3 7 22.366
## 2 7 2 1,4,5,6,7,8 4 7 6.174
## 3 5 3 6 5 7 9.705
## 4 4 3 10,4,6 2 7 58.517
## 5 7 2 5,6 3 NA 5.647
## 6 6 3 1 4 7 15.862
## Q78_Last.Click Q78_Page.Submit Q78_Click.Count transgres_1 transgres_2
## 1 148.934 153.134 12 3 1
## 2 72.626 74.609 22 4 3
## 3 109.167 111.847 10 3 1
## 4 195.290 199.227 14 4 2
## 5 61.894 65.304 13 4 2
## 6 174.894 177.914 21 1 3
## transgres_3 transgres_4 Q79_First.Click Q79_Last.Click Q79_Page.Submit
## 1 1 1 16.239 27.208 28.488
## 2 2 1 20.400 31.697 32.941
## 3 4 1 57.079 77.311 82.171
## 4 1 1 23.005 49.246 50.303
## 5 2 1 11.727 23.987 25.130
## 6 1 1 14.701 35.077 40.711
## Q79_Click.Count NPI1 NPI2 NPI3 NPI4 NPI5 NPI6 NPI7 NPI8 NPI9 NPI10 NPI11
## 1 4 1 1 1 2 1 2 2 1 2 2 1
## 2 4 2 2 1 2 1 2 1 1 1 1 2
## 3 5 2 1 1 2 1 2 1 1 1 2 2
## 4 5 2 2 1 2 1 2 2 1 1 2 1
## 5 8 1 2 1 2 1 2 2 2 1 2 1
## 6 6 2 2 2 1 2 2 2 2 1 2 1
## NPI12 NPI13 exploit_1 exploit_2 exploit_3 NPI_biascheck NPI_bias_dummy
## 1 2 1 2 2 2 19 0
## 2 1 1 4 4 3 18 0
## 3 2 1 5 5 3 19 0
## 4 2 1 2 1 2 20 0
## 5 2 2 5 4 3 21 0
## 6 2 2 1 1 2 23 0
## Q76_First.Click Q76_Last.Click Q76_Page.Submit Q76_Click.Count Q11 Q14_1
## 1 25.575 141.688 142.668 16 2 2
## 2 10.473 103.989 105.050 35 2 2
## 3 29.957 129.786 132.515 22 2 2
## 4 49.912 222.748 223.703 18 2 2
## 5 5.315 108.076 109.093 25 2 2
## 6 5.353 94.716 98.083 25 2 2
## Q14_2 Q14_3 Q14_4 Q14_5 Q14_6 Q14_6_TEXT Q10_1 Q10_2 Q10_3 Q10_4 Q10_5 Q10_6
## 1 2 2 2 2 2 NA NA NA NA NA NA
## 2 2 2 2 2 NA NA NA NA NA NA NA
## 3 2 2 1 2 2 4 3 4 2 4 5
## 4 2 2 2 2 2 NA NA NA NA NA NA
## 5 2 2 2 2 NA NA NA NA NA NA NA
## 6 2 2 2 2 2 NA NA NA NA NA NA
## Q10_7 Q10_8 Q10_9 Q10_10 Q10_11 Q10_12 Q10_13 Q10_14 Q10_15 Q71_First.Click
## 1 NA NA NA NA NA NA NA NA NA 5.199
## 2 NA NA NA NA NA NA NA NA NA 6.497
## 3 3 1 4 1 3 1 4 2 2 4.533
## 4 NA NA NA NA NA NA NA NA NA 7.430
## 5 NA NA NA NA NA NA NA NA NA 5.020
## 6 NA NA NA NA NA NA NA NA NA 15.872
## Q71_Last.Click Q71_Page.Submit Q71_Click.Count physSx_1 physSx_2 physSx_3
## 1 28.239 28.669 7 3 1 1
## 2 23.457 24.600 8 2 2 1
## 3 115.299 116.410 21 3 1 1
## 4 122.984 128.490 12 2 3 2
## 5 7.996 17.581 6 1 1 1
## 6 32.719 33.562 7 1 2 2
## physSx_4 physSx_5 physSx_6 physSx_7 physSx_8 physSx_9 physSx_10 physSx_11
## 1 2 1 2 1 2 2 2 2
## 2 1 3 1 1 3 2 1 1
## 3 3 2 2 1 3 2 1 2
## 4 3 1 2 1 2 1 1 2
## 5 2 1 1 1 1 2 1 1
## 6 1 2 2 1 3 1 2 2
## physSx_12 physSx_13 phys_sx_biaschec phys_sym_bias_dummy. Q70_First.Click
## 1 3 2 24 0 13.703
## 2 3 3 24 0 5.209
## 3 3 3 27 0 36.694
## 4 3 2 25 0 47.764
## 5 2 1 16 0 4.561
## 6 3 2 24 0 10.062
## Q70_Last.Click Q70_Page.Submit Q70_Click.Count stress_1 stress_2 stress_3
## 1 54.318 60.887 16 2 4 5
## 2 27.841 28.982 17 4 5 5
## 3 79.053 80.519 18 4 4 5
## 4 77.308 79.068 13 2 4 4
## 5 18.707 20.343 14 4 3 3
## 6 80.372 82.827 18 3 3 5
## stress_4 stress_5 stress_6 stress_7 stress_8 stress_9 stress_10
## 1 3 3 3 4 3 3 3
## 2 4 3 3 2 2 4 4
## 3 2 1 5 2 2 4 4
## 4 3 4 5 4 2 2 2
## 5 4 3 4 3 3 4 4
## 6 2 3 5 2 1 3 2
## stress_biascheck stress_bias_dummy Q69_First.Click Q69_Last.Click
## 1 33 0 10.383 100.428
## 2 36 0 9.729 43.281
## 3 33 0 42.213 89.329
## 4 32 0 43.206 180.767
## 5 35 0 63.797 76.765
## 6 29 0 16.412 94.543
## Q69_Page.Submit Q69_Click.Count marriage1_1 marriage1_2 marriage1_3
## 1 101.287 14 10 25 30
## 2 44.423 13 10 25 35
## 3 91.194 12 1 1 59
## 4 182.932 12 0 0 60
## 5 77.998 13 25 25 25
## 6 95.709 15 13 33 21
## marriage1_4 marriage2 marriage3 marriage4 marriage5 Q75_First.Click
## 1 35 2 20 1 2 20.229
## 2 30 3 19 1 1 11.100
## 3 39 2 19 1 1 40.807
## 4 40 1 16 1 1 74.778
## 5 25 2 14 3 1 21.347
## 6 33 3 17 1 1 19.366
## Q75_Last.Click Q75_Page.Submit Q75_Click.Count school sex
## 1 164.560 165.870 32 ACG 2
## 2 60.223 61.354 17 ACG,Deree 1
## 3 160.366 165.459 23 American College of Greece 1
## 4 155.971 156.974 13 American College of Greece 2
## 5 48.802 49.742 11 American College of Greece 1
## 6 181.747 183.288 25 American College of Greece 2
## age edu sibling race race_6_TEXT Q82 Q83 income place2 Q80 place Q81
## 1 20 2 2 1 3 NA 3 2 NA NA Greece
## 2 23 5 2 1 3 NA 3 2 NA NA Greece
## 3 23 2 5 1 3 NA 1 2 NA NA Greece
## 4 22 2 3,5,7 6 Greek 3 NA 1 2 NA NA Greece
## 5 18 2 3,5,7 1 3 NA 6 2 NA NA Greece
## 6 23 2 2,4 1 3 NA 1 2 NA NA Greece
## Q81_First.Click Q81_Last.Click Q81_Page.Submit Q81_Click.Count
## 1 0.000 0.000 5.781 0
## 2 2.424 2.424 6.621 1
## 3 0.000 0.000 9.294 0
## 4 2.679 2.679 5.803 1
## 5 1.632 1.632 5.500 1
## 6 2.766 2.766 6.995 1
## comments
## 1 I have completed this survey
## 2 i have completed this survey
## 3 Didn't know my household income.\nI have completed the last question about disability wrong. I read "not" the moment I pressed ">>"
## 4 I have completed this survey
## 5 i have completed this survey
## 6 The question saying "Select" was funny.
## affiliation response_bias_SUM school_coded
## 1 acgreece 0 acgreece
## 2 acgreece 0 acgreece
## 3 acgreece 0 acgreece
## 4 acgreece 0 acgreece
## 5 acgreece 0 acgreece
## 6 acgreece 0 acgreecestr(df)## 'data.frame': 3182 obs. of 328 variables:
## $ StartDate : chr "12/02/16" "11/16/16" "11/09/16" "11/07/16" ...
## $ EndDate : chr "12/02/16" "11/16/16" "11/09/16" "11/07/16" ...
## $ Status : int 0 0 0 0 0 0 0 0 0 0 ...
## $ Progress : int 100 100 99 100 100 100 99 99 100 100 ...
## $ Duration..in.seconds.: int 1839 1467 2185 2904 1229 2068 1656 1839 1160 2134 ...
## $ Finished : int 1 1 0 1 1 1 0 0 1 1 ...
## $ RecordedDate : chr "12/2/2016 5:38" "11/16/2016 11:53" "11/16/2016 1:22" "11/7/2016 4:54" ...
## $ ResponseId : chr "R_BJN3bQqi1zUMid3" "R_2TGbiBXmAtxywsD" "R_12G7bIqN2wB2N65" "R_39pldNoon8CePfP" ...
## $ RecipientLastName : logi NA NA NA NA NA NA ...
## $ RecipientFirstName : logi NA NA NA NA NA NA ...
## $ RecipientEmail : logi NA NA NA NA NA NA ...
## $ ExternalReference : logi NA NA NA NA NA NA ...
## $ DistributionChannel : chr "anonymous" "anonymous" "anonymous" "anonymous" ...
## $ informedconsent : int 1 1 1 1 1 1 1 1 1 1 ...
## $ moa1.1_1 : int 4 4 4 4 4 4 4 4 4 3 ...
## $ moa1.1_2 : int 4 4 4 3 4 3 4 4 4 2 ...
## $ moa1.1_3 : int 3 4 4 3 4 4 4 4 4 3 ...
## $ moa1.1_4 : int 2 2 1 1 1 2 3 3 4 1 ...
## $ moa1.1_5 : int 2 3 1 1 1 3 3 3 4 1 ...
## $ moa1.1_6 : int 3 3 4 2 3 4 4 4 4 2 ...
## $ moa1.1_7 : int 2 4 2 1 1 2 4 3 1 3 ...
## $ moa1.1_8 : int 1 3 3 1 1 1 4 3 2 3 ...
## $ moa1.1_9 : int 4 3 4 1 4 3 4 4 4 4 ...
## $ moa1.1_10 : int 3 3 3 1 3 4 3 3 4 3 ...
## $ moa1.2_1 : int 2 1 2 1 2 1 1 2 2 2 ...
## $ moa1.2_2 : int 1 1 1 1 1 1 1 2 2 2 ...
## $ moa1.2_3 : int 2 2 1 1 2 1 2 2 2 2 ...
## $ moa1.2_4 : int 1 2 1 1 1 1 1 1 1 1 ...
## $ moa1.2_5 : int 1 1 1 1 3 1 1 1 1 1 ...
## $ moa1.2_6 : int 1 1 1 1 3 1 1 1 2 2 ...
## $ moa1.2_7 : int 2 1 2 2 1 1 3 3 1 3 ...
## $ moa1.2_8 : int 3 1 3 3 1 1 3 3 3 3 ...
## $ moa1.2_9 : int 3 2 3 2 3 1 3 3 3 3 ...
## $ moa1.2_10 : int 2 3 3 3 2 3 3 3 1 3 ...
## $ moa2.1_1 : int 4 3 4 4 4 4 4 4 4 3 ...
## $ moa2.1_2 : int 4 4 2 2 4 4 4 4 4 3 ...
## $ moa2.1_3 : int 4 2 2 2 3 4 3 4 4 3 ...
## $ moa2.1_4 : int 4 4 4 4 4 4 4 4 4 4 ...
## $ moa2.1_5 : int 3 4 3 3 4 2 4 4 4 3 ...
## $ moa2.1_6 : int 4 3 3 2 3 4 4 3 4 4 ...
## $ moa2.1_7 : int 4 2 4 4 4 3 4 4 2 4 ...
## $ moa2.1_8 : int 4 4 4 2 4 4 3 4 4 4 ...
## $ moa2.1_9 : int 3 2 3 3 3 4 4 4 4 4 ...
## $ moa2.1_10 : int 2 1 2 2 3 4 2 4 2 2 ...
## $ moa2.2_1 : int 2 3 2 2 3 2 2 2 3 3 ...
## $ moa2.2_2 : int 1 1 1 1 3 1 1 1 1 2 ...
## $ moa2.2_3 : int 1 2 1 1 3 1 1 1 3 3 ...
## $ moa2.2_4 : int 3 2 2 2 3 2 2 3 3 3 ...
## $ moa2.2_5 : int 2 1 1 1 3 1 1 1 2 2 ...
## $ moa2.2_6 : int 3 2 2 2 2 2 2 2 3 3 ...
## $ moa2.2_7 : int 3 2 3 2 3 2 1 2 1 3 ...
## $ moa2.2_8 : int 2 2 1 2 3 1 2 3 2 2 ...
## $ moa2.2_9 : int 2 2 1 2 2 2 2 2 3 3 ...
## $ moa2.2_10 : int 1 1 1 1 3 1 1 1 1 2 ...
## $ adult_Q : int 1 1 1 1 1 1 1 1 1 2 ...
## $ MOA_IMP_biascheck : int 64 62 61 46 62 67 73 74 71 59 ...
## $ MOA_ach_biascheck : int 38 33 33 32 47 27 34 39 40 48 ...
## $ MOA_IMP_dummy : int 0 0 0 0 0 0 0 0 0 0 ...
## $ MOA.ACH_dummy : int 0 0 0 0 0 0 0 0 0 0 ...
## $ Q65_First.Click : num 37.1 120 27.7 19.7 12.9 ...
## $ Q65_Last.Click : num 308 336 154 297 122 ...
## $ Q65_Page.Submit : num 309 338 156 299 122 ...
## $ Q65_Click.Count : int 45 58 47 43 46 50 45 42 47 47 ...
## $ IDEA_1 : int 3 4 4 4 4 3 4 4 4 4 ...
## $ IDEA_2 : int 4 4 4 4 4 4 3 3 4 4 ...
## $ IDEA_3 : int 4 4 4 3 3 3 4 3 3 2 ...
## $ IDEA_4 : int 3 4 4 3 4 3 4 4 2 2 ...
## $ IDEA_5 : int 4 3 4 4 3 4 3 3 4 4 ...
## $ IDEA_6 : int 4 4 4 4 3 4 4 2 4 4 ...
## $ IDEA_7 : int 4 4 3 4 3 3 3 2 3 3 ...
## $ IDEA_8 : int 4 4 3 4 4 2 3 3 3 4 ...
## $ IDEA.biascheck : int 30 31 30 30 28 26 28 24 27 27 ...
## $ IDEA.bias.dummy : int 0 0 0 0 0 0 0 0 0 0 ...
## $ Q66_First.Click : num 44.7 19.9 23.2 27.5 24 ...
## $ Q66_Last.Click : num 86.6 65.2 51.4 172.8 52.2 ...
## $ Q66_Page.Submit : num 87.5 67.2 52.4 174.1 53.4 ...
## $ Q66_Click.Count : int 11 13 11 9 9 13 9 8 8 9 ...
## $ politics : int 2 1 2 8 1 8 4 2 8 4 ...
## $ party : int 3 4 8 8 8 8 4 1 3 8 ...
## $ president : chr "" "None, but I was a US Citizen and had a gun next to my head, I would vote for Trump" "Hillary Clinton" "Hillary Clinton" ...
## $ Q74_First.Click : num 13.1 4.9 34.9 66.9 23.6 ...
## $ Q74_Last.Click : num 40.4 28.1 48.4 119.2 32.2 ...
## $ Q74_Page.Submit : num 46.4 55.1 56.4 135.3 35.3 ...
## $ Q74_Click.Count : int 2 6 4 4 4 6 3 3 3 3 ...
## $ swb_1 : int 4 3 1 5 2 4 4 5 5 5 ...
## $ swb_2 : int 6 4 2 6 5 4 4 5 5 4 ...
## $ swb_3 : int 5 5 2 6 5 6 5 6 5 6 ...
## $ swb_4 : int 5 5 2 5 3 5 4 5 5 4 ...
## $ swb_5 : int 3 4 2 6 2 1 1 6 5 6 ...
## $ swb_6 : int 3 4 2 3 5 4 4 6 5 4 ...
## $ Q67_First.Click : num 9.63 8.61 37.66 13.59 6.8 ...
## $ Q67_Last.Click : num 40.4 29.1 53.2 55.2 22.2 ...
## $ Q67_Page.Submit : num 41.2 30 54.6 56.1 23.1 ...
## $ Q67_Click.Count : int 7 7 9 7 7 7 7 7 6 13 ...
## $ mindful_1 : int 4 2 2 2 4 1 5 3 3 5 ...
## $ mindful_2 : int 2 2 3 2 5 4 6 2 3 6 ...
## $ mindful_3 : int 2 2 1 1 3 3 5 4 4 4 ...
## $ mindful_4 : int 2 1 2 2 2 3 4 2 3 5 ...
## $ mindful_5 : int 4 3 3 2 4 5 6 2 3 6 ...
## [list output truncated]1.4 Subsetting Data
d <- subset(df, select=c(belnow, marriage2,marriage5,income, race, politics, party, efficacy_1, efficacy_2, efficacy_3, efficacy_4, efficacy_5, efficacy_6, efficacy_7, efficacy_8, efficacy_9, efficacy_10))1.5 Basic Data Checking
1.5.1 Checking Values
d %>%
map(table, useNA = "always")## $belnow
##
## 1 2 3 4 5 <NA>
## 115 308 829 1371 555 4
##
## $marriage2
##
## 1 2 3 4 5 <NA>
## 154 361 746 1155 756 10
##
## $marriage5
##
## 1 2 3 4 <NA>
## 2137 736 48 251 10
##
## $income
##
## 1 2 3 4 5 6 7 8 9 <NA>
## 860 518 361 344 302 236 389 140 7 25
##
## $race
##
## 1 1,2 1,2,3 1,2,3,4,5 1,2,3,5 1,2,4 1,2,4,5
## 9 2026 26 2 1 3 4 3
## 1,2,5 1,2,6 1,3 1,3,4 1,3,5 1,4 1,4,5 1,5
## 4 2 98 6 8 39 2 35
## 1,6 2 2,3 2,3,4 2,3,4,5 2,3,5 2,3,6 2,4
## 15 249 5 1 1 1 1 6
## 2,5 2,5,6 2,6 3 3,4 3,4,5 3,5 4
## 5 1 6 286 9 1 5 210
## 4,6 5 6 <NA>
## 3 12 97 0
##
## $politics
##
## 1 2 3 4 5 6 7 8 <NA>
## 235 772 373 568 308 332 57 532 5
##
## $party
##
## 1 2 3 4 5 6 7 8 <NA>
## 345 595 669 330 329 320 136 441 17
##
## $efficacy_1
##
## 1 2 3 4 <NA>
## 26 219 1789 1145 3
##
## $efficacy_2
##
## 1 2 3 4 <NA>
## 89 802 1841 448 2
##
## $efficacy_3
##
## 1 2 3 4 <NA>
## 62 536 1790 792 2
##
## $efficacy_4
##
## 1 2 3 4 <NA>
## 69 446 1849 815 3
##
## $efficacy_5
##
## 1 2 3 4 <NA>
## 54 455 1928 742 3
##
## $efficacy_6
##
## 1 2 3 4 <NA>
## 11 122 1551 1495 3
##
## $efficacy_7
##
## 1 2 3 4 <NA>
## 126 580 1647 826 3
##
## $efficacy_8
##
## 1 2 3 4 <NA>
## 29 388 1949 812 4
##
## $efficacy_9
##
## 1 2 3 4 <NA>
## 17 195 1963 1005 2
##
## $efficacy_10
##
## 1 2 3 4 <NA>
## 39 273 1909 958 31.5.2 Recoding data
table(d$race, useNA = "always")##
## 1 1,2 1,2,3 1,2,3,4,5 1,2,3,5 1,2,4 1,2,4,5
## 9 2026 26 2 1 3 4 3
## 1,2,5 1,2,6 1,3 1,3,4 1,3,5 1,4 1,4,5 1,5
## 4 2 98 6 8 39 2 35
## 1,6 2 2,3 2,3,4 2,3,4,5 2,3,5 2,3,6 2,4
## 15 249 5 1 1 1 1 6
## 2,5 2,5,6 2,6 3 3,4 3,4,5 3,5 4
## 5 1 6 286 9 1 5 210
## 4,6 5 6 <NA>
## 3 12 97 0d$race_rc <- NA
d$race_rc[d$race == 1] <- "white"
d$race_rc[d$race == 2] <- "black"
d$race_rc[d$race == 3] <- "hispanic"
d$race_rc[d$race == 4] <- "asian"
d$race_rc[d$race == 5] <- "nativeamer"
d$race_rc[d$race == 6] <- "other"1.5.3 Factor Scores/Composite Variables
# use the str() command to check that your recoded variable is numeric so you can use mathematical operators on it
str(d)## 'data.frame': 3182 obs. of 18 variables:
## $ belnow : int 4 4 2 4 4 3 4 4 4 3 ...
## $ marriage2 : int 2 3 2 1 2 3 4 3 4 2 ...
## $ marriage5 : int 2 1 1 1 1 1 1 1 1 4 ...
## $ income : int 3 3 1 1 6 1 2 3 7 1 ...
## $ race : chr "1" "1" "1" "6" ...
## $ politics : int 2 1 2 8 1 8 4 2 8 4 ...
## $ party : int 3 4 8 8 8 8 4 1 3 8 ...
## $ efficacy_1 : int 4 3 3 4 3 3 3 3 3 4 ...
## $ efficacy_2 : int 3 3 3 1 3 2 3 3 3 3 ...
## $ efficacy_3 : int 4 3 1 2 2 3 2 3 3 4 ...
## $ efficacy_4 : int 3 4 2 3 3 2 1 3 3 4 ...
## $ efficacy_5 : int 3 4 2 2 3 1 2 3 3 4 ...
## $ efficacy_6 : int 4 4 3 4 3 3 3 3 3 4 ...
## $ efficacy_7 : int 3 3 1 2 3 2 2 3 3 3 ...
## $ efficacy_8 : int 3 3 3 3 3 3 2 3 3 4 ...
## $ efficacy_9 : int 4 3 2 4 4 3 2 3 3 4 ...
## $ efficacy_10: int 3 4 2 3 3 2 3 3 3 3 ...
## $ race_rc : chr "white" "white" "white" "other" ...d$efficacy <- (d$efficacy_1 + d$efficacy_2 + d$efficacy_3 + d$efficacy_4 + d$efficacy_5 + d$efficacy_6 + d$efficacy_7 + d$efficacy_8 + d$efficacy_9 + d$efficacy_10)/10
d$politicalviews <- (d$politics + d$party)/2
d$marriageimportance <- (d$marriage2)
d$belong <- (d$belnow)1.6 Exporting Data
d2 <- subset(d, select=c(efficacy, belong, marriageimportance, race_rc, politicalviews, income))
write.csv(d2, file="/Users/lydiaschwartz/Desktop/r studio/Data Cleaning and Basic Statistics HW/final.csv", row.names = F)2 Basic Statistics
2.1 Import Cleaned Data
d2 <- read.csv(file= "/Users/lydiaschwartz/Desktop/r studio/Data Cleaning and Basic Statistics HW/final.csv", header=T) 2.2 Check Data
2.2.1 Formatting
head(d2)## efficacy belong marriageimportance race_rc politicalviews income
## 1 3.4 4 2 white 2.5 3
## 2 3.4 4 3 white 2.5 3
## 3 2.2 2 2 white 5.0 1
## 4 2.8 4 1 other 8.0 1
## 5 3.0 4 2 white 4.5 6
## 6 2.4 3 3 white 8.0 1str(d2)## 'data.frame': 3182 obs. of 6 variables:
## $ efficacy : num 3.4 3.4 2.2 2.8 3 2.4 2.3 3 3 3.7 ...
## $ belong : int 4 4 2 4 4 3 4 4 4 3 ...
## $ marriageimportance: int 2 3 2 1 2 3 4 3 4 2 ...
## $ race_rc : chr "white" "white" "white" "other" ...
## $ politicalviews : num 2.5 2.5 5 8 4.5 8 4 1.5 5.5 6 ...
## $ income : int 3 3 1 1 6 1 2 3 7 1 ...d2$race <- as.factor(d2$race)
d2$income <- as.factor(d2$income)2.3 Making a new subset with updated race (from numbers to written form)
d2 <- subset(d2, select=c(efficacy, belong, marriageimportance, race_rc, politicalviews, income))2.4 Univariate Normality
describe(d2)## vars n mean sd median trimmed mad min max range skew
## efficacy 1 3176 3.13 0.45 3.1 3.13 0.44 1 4 3 -0.29
## belong 2 3178 3.61 1.00 4.0 3.68 1.48 1 5 4 -0.62
## marriageimportance 3 3172 3.63 1.11 4.0 3.72 1.48 1 5 4 -0.59
## race_rc* 4 2880 4.95 1.75 6.0 5.28 0.00 1 6 5 -1.25
## politicalviews 5 3163 4.14 2.05 4.0 4.01 2.22 1 8 7 0.40
## income* 6 3157 3.54 2.30 3.0 3.37 2.97 1 9 8 0.47
## kurtosis se
## efficacy 0.63 0.01
## belong 0.04 0.02
## marriageimportance -0.35 0.02
## race_rc* -0.14 0.03
## politicalviews -0.93 0.04
## income* -1.12 0.042.5 Histograms
# use the hist() command to create a histogram for your continuous variables
hist(d$efficacy)
hist(d$belong)
hist(d$marriageimportance)
hist(d$politicalviews)
# use the table() command to create a table for your categorical variables (other than your ID variable)
table(d2$race_rc, useNA = "always")##
## asian black hispanic nativeamer other white <NA>
## 210 249 286 12 97 2026 302table(d2$income, useNA = "always")##
## 1 2 3 4 5 6 7 8 9 <NA>
## 860 518 361 344 302 236 389 140 7 252.6 Missing Data
# use the gg_miss_upset() command to visualize your missing data
gg_miss_upset(data=d, nsets = "6")
# create a new dataframe with only your complete cases/observations
d2 <- na.omit(d)2.7 Crosstabs & Scatterplots
2.7.1 Crosstabs
# use the cross_cases() command to create a crosstab of your categorical variables
cross_cases(d2, race_rc, income)|  income | |||||||||
|---|---|---|---|---|---|---|---|---|---|
| Â 1Â | Â 2Â | Â 3Â | Â 4Â | Â 5Â | Â 6Â | Â 7Â | Â 8Â | Â 9Â | |
|  race_rc | |||||||||
|    asian | 86 | 25 | 21 | 27 | 14 | 7 | 19 | 10 | |
|    black | 72 | 54 | 29 | 37 | 11 | 12 | 18 | 2 | 1 |
|    hispanic | 63 | 45 | 57 | 67 | 26 | 11 | 12 | 4 | |
|    nativeamer | 4 | 1 | 1 | 2 | 1 | 2 | 1 | ||
|    other | 41 | 18 | 10 | 8 | 1 | 6 | 4 | 4 | |
|    white | 513 | 319 | 195 | 171 | 222 | 174 | 299 | 104 | 6 |
|    #Total cases | 779 | 462 | 313 | 312 | 275 | 210 | 354 | 125 | 7 |
2.7.2 Scatterplots
# use the plot() command to create scatterplots of your continuous variables
plot(d2$efficacy, d2$belong,
main="scatterplot of efficacy and belonging",
xlab = "efficacy",
ylab = "belonging")
# use the plot() command to create scatterplots of your continuous variables
plot(d2$marriageimportance, d2$politicalviews,
main="scatterplot of marriage importance and political views",
xlab = "marriage importance",
ylab = "political views")
# use the plot() command to create scatterplots of your continuous variables
plot(d2$efficacy, d2$marriageimportance,
main="scatterplot of efficacy marriage importance",
xlab = "marriage importance",
ylab = "efficacy")
# use the plot() command to create scatterplots of your continuous variables
plot(d2$politicalviews, d2$belonging,
main="scatterplot of political views and belonging",
xlab = "political views",
ylab = "belonging")
2.8 Boxplots
# use the boxplot() command to create boxplots of your continuous and categorical variables
boxplot(data=d2, income~race_rc,
main="income and race",
xlab = "race",
ylab = "income")
boxplot(data=d2, marriageimportance~race_rc,
main="race and marriage",
xlab = "race",
ylab = "marriage importance")
boxplot(data=d2, efficacy~race_rc,
main="race and efficacy",
xlab = "race",
ylab = "efficacy")
num_na <- sum(is.na(d$income))
num_na <- sum(is.na(df$race_rc))
num_na <- sum(is.na(d$belong))
num_na <- sum(is.na(d$politicalviews))
num_na <- sum(is.na(d$marriageimportance))
num_na <- sum(is.na(d$efficacy))
sample_size <- nrow(d2)
sample_size <- nrow(d)
item_non_response_percentage <- (3182 - 3130) / 3182 * 1003 Homework Write up
do your continuous variables meet the criteria for univariate normality? Skew and kurtosis should be between -2 and +2.
Yes, my continuous variables meet this criteria.
Efficacy: skew = -0.24, kurtosis = 0.46
Marriage Opinions: skew = -0.60, kurtosis = -0.33
Political Views: skew = 0.40, kurtosis = -0.92
Belonging: skew = -0.62, kurtosis = 0.05
Do you have any missing data? Once you have removed the cases/participants with missing data, what is your total sample size? Please discuss how much data is missing and whether it’s due to survey design or individual non-response.
I do have missing data. 25 participants did not report an income. 19 participants did not report their political view. 10 Participants did not report their percieved marriage importance. 4 participants did not report their percieved belonging. 6 Participants did not report their percieved self-efficacy.
Due to how the the survey was designed (unit non response), 19 participants did not see the income question, 15 participants did not see the political views question, 6 did not see the marriage importance question, and 3 did not see the efficacy question. 12 participants skipped some of the items selected for analysis (item nonresponse). The percentage of item non response from the number of participants who responded fully is 1.63%, below the 5% cutoff considered a concern by the literature. The original sample size was 3182 Participants. After the missing data was removed, the sample size changed to 3130.