We will be going through
library(tidyverse)
library(readxl)
library(ggplot2)TAS_data_long_format_age <- read_excel("TAS_data_long_format_age.xlsx")view(TAS_data_long_format_age)head(TAS_data_long_format_age)## # A tibble: 6 × 42
## TAS TAS05 TAS09 TAS15 `1968 Interview Number` `Person Number` Gender
## <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 2 1 1 NA 4 180 2
## 2 2 1 1 NA 5 32 2
## 3 2 1 1 NA 6 34 1
## 4 2 1 1 NA 14 30 1
## 5 1 1 NA NA 18 38 2
## 6 2 1 1 NA 47 34 2
## # ℹ 35 more variables: `Individual is sample` <dbl>, `Year ID Number` <dbl>,
## # `Sequence Number` <dbl>, `Relationship to Head` <dbl>,
## # `Release Number` <dbl>, B5A <dbl>, B5D <dbl>, B6C <dbl>, C2D <dbl>,
## # C2E <dbl>, C2F <dbl>, D2D3_month <dbl>, D2D3_year <dbl>,
## # E1_1st_mention <dbl>, E1_2nd_mention <dbl>, E1_3rd_mention <dbl>, E3 <dbl>,
## # G1 <dbl>, G2_month <dbl>, G2_year <dbl>, G10 <dbl>, G11 <dbl>, G30A <dbl>,
## # G41A <dbl>, G41B <dbl>, G41C <dbl>, G41H <dbl>, G41P <dbl>, H1 <dbl>, …Filter the data (2005 & 2009)
Long_format_2005_2009 <- TAS_data_long_format_age %>% filter(year < 2010) %>% filter (TAS05 == 1) %>% filter (TAS09 == 1) %>% unite("TAS_ID", c("1968 Interview Number", "Person Number")) %>% mutate(year_new = case_when(year == 2005 ~ -1, year == 2009 ~ 0,year == 2015 ~ 1)) %>% group_by(TAS_ID) %>% mutate(Age_18_graduate = case_when(Age_18_graduate == 2027 ~ Age_18_graduate[year == 2005] + 4, Age_18_graduate == 2023 ~ Age_18_graduate[year == 2009] - 4, TRUE ~ Age_18_graduate)) %>% ungroup() %>% filter (Age_18_graduate <100) %>% group_by(TAS_ID) %>% mutate(age_difference = Age_18_graduate[year == 2009] - Age_18_graduate[year == 2005]) %>% filter(age_difference < 6) %>% filter(age_difference > 2) %>% ungroup()view(Long_format_2005_2009)knitr::kable(head(Long_format_2005_2009[, 1:43]))| TAS | TAS05 | TAS09 | TAS15 | TAS_ID | Gender | Individual is sample | Year ID Number | Sequence Number | Relationship to Head | Release Number | B5A | B5D | B6C | C2D | C2E | C2F | D2D3_month | D2D3_year | E1_1st_mention | E1_2nd_mention | E1_3rd_mention | E3 | G1 | G2_month | G2_year | G10 | G11 | G30A | G41A | G41B | G41C | G41H | G41P | H1 | L7_1st_mention | L7_2nd_mention | L7_3rd_mention | Age_17_graduate | Age_18_graduate | year | year_new | age_difference |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 1 | 1 | NA | 5_32 | 2 | 2 | 624 | 3 | 30 | 5 | 5 | 5 | 5 | 7 | 7 | 7 | 0 | 0 | 1 | 7 | 0 | 0 | 1 | 5 | 2002 | 1 | 1 | 7 | 7 | 6 | 6 | 7 | 5 | 2 | 1 | 0 | 0 | 20 | 21 | 2005 | -1 | 4 |
| 2 | 1 | 1 | NA | 6_34 | 1 | 2 | 1202 | 51 | 30 | 5 | 2 | 2 | 6 | 1 | 1 | 1 | 0 | 0 | 7 | 0 | 0 | 5 | 1 | 5 | 2002 | 1 | 1 | 0 | 7 | 5 | 7 | 5 | 3 | 1 | 1 | 0 | 0 | 20 | 21 | 2005 | -1 | 4 |
| 2 | 1 | 1 | NA | 14_30 | 1 | 2 | 736 | 51 | 30 | 5 | 4 | 4 | 4 | 2 | 1 | 1 | 0 | 0 | 2 | 0 | 0 | 0 | 1 | 6 | 2003 | 1 | 5 | 6 | 5 | 6 | 6 | 5 | 5 | 2 | 1 | 0 | 0 | 19 | 20 | 2005 | -1 | 4 |
| 2 | 1 | 1 | NA | 47_34 | 2 | 2 | 2516 | 3 | 30 | 5 | 4 | 5 | 6 | 4 | 5 | 2 | 0 | 0 | 1 | 0 | 0 | 0 | 1 | 5 | 2005 | 5 | 0 | 6 | 3 | 6 | 4 | 7 | 4 | 1 | 1 | 0 | 0 | 17 | 18 | 2005 | -1 | 4 |
| 2 | 1 | 1 | NA | 53_35 | 2 | 2 | 1392 | 3 | 33 | 5 | 4 | 5 | 5 | 3 | 1 | 1 | 0 | 0 | 1 | 0 | 0 | 0 | 1 | 6 | 2002 | 1 | 1 | 7 | 6 | 7 | 7 | 7 | 5 | 1 | 1 | 0 | 0 | 20 | 21 | 2005 | -1 | 4 |
| 2 | 1 | 1 | NA | 53_36 | 2 | 2 | 1616 | 3 | 30 | 5 | 4 | 5 | 7 | 4 | 1 | 1 | 0 | 0 | 6 | 0 | 0 | 1 | 1 | 6 | 2005 | 1 | 5 | 7 | 7 | 7 | 5 | 7 | 6 | 2 | 1 | 0 | 0 | 17 | 18 | 2005 | -1 | 4 |
Year
count(Long_format_2005_2009, year)## # A tibble: 2 × 2
## year n
## <dbl> <int>
## 1 2005 542
## 2 2009 542Age
count(Long_format_2005_2009, Age_18_graduate)## # A tibble: 12 × 2
## Age_18_graduate n
## <dbl> <int>
## 1 14 1
## 2 17 7
## 3 18 166
## 4 19 150
## 5 20 141
## 6 21 83
## 7 22 167
## 8 23 150
## 9 24 140
## 10 25 76
## 11 26 2
## 12 27 1Age by year(2005)
Long_format_2005_2009 %>% filter(year == 2005) %>% count(Age_18_graduate)## # A tibble: 8 × 2
## Age_18_graduate n
## <dbl> <int>
## 1 14 1
## 2 17 7
## 3 18 165
## 4 19 150
## 5 20 141
## 6 21 76
## 7 22 1
## 8 23 1Age by year (2009)
Long_format_2005_2009 %>% filter(year == 2009) %>% count(Age_18_graduate)## # A tibble: 8 × 2
## Age_18_graduate n
## <dbl> <int>
## 1 18 1
## 2 21 7
## 3 22 166
## 4 23 149
## 5 24 140
## 6 25 76
## 7 26 2
## 8 27 1Gender 1 = Male 2 = Female
Long_format_2005_2009 %>% group_by(year) %>% count(Gender)## # A tibble: 4 × 3
## # Groups: year [2]
## year Gender n
## <dbl> <dbl> <int>
## 1 2005 1 245
## 2 2005 2 297
## 3 2009 1 245
## 4 2009 2 297G2: Years graduated high school
Long_format_2005_2009 %>% group_by(year) %>% count(G2_year)## # A tibble: 15 × 3
## # Groups: year [2]
## year G2_year n
## <dbl> <dbl> <int>
## 1 2005 0 18
## 2 2005 2000 1
## 3 2005 2001 1
## 4 2005 2002 76
## 5 2005 2003 139
## 6 2005 2004 148
## 7 2005 2005 159
## 8 2009 0 6
## 9 2009 2001 2
## 10 2009 2002 76
## 11 2009 2003 140
## 12 2009 2004 146
## 13 2009 2005 164
## 14 2009 2006 7
## 15 2009 2009 1Long_format_2005_2009 %>% filter(G2_year != 0) %>% group_by(TAS_ID) %>% filter(n_distinct(year) == 2) %>% ungroup() %>% group_by(year) %>% count(G2_year) %>% ungroup() ## # A tibble: 10 × 3
## year G2_year n
## <dbl> <dbl> <int>
## 1 2005 2001 1
## 2 2005 2002 76
## 3 2005 2003 139
## 4 2005 2004 145
## 5 2005 2005 157
## 6 2009 2001 2
## 7 2009 2002 76
## 8 2009 2003 138
## 9 2009 2004 144
## 10 2009 2005 158Long_format_2005_2009 %>% filter(G2_year != 0) %>% group_by(TAS_ID) %>% filter(n_distinct(year) == 2) %>% ungroup() %>% count(year) ## # A tibble: 2 × 2
## year n
## <dbl> <int>
## 1 2005 518
## 2 2009 518mean_year_graduation <- Long_format_2005_2009 %>% filter(G2_year != 0) %>% group_by(TAS_ID) %>% filter(n_distinct(year) == 2) %>% ungroup() %>% group_by(year) %>% summarize(mean_graduation = mean(G2_year, na.rm = TRUE)) %>% ungroup()
mean_year_graduation## # A tibble: 2 × 2
## year mean_graduation
## <dbl> <dbl>
## 1 2005 2004.
## 2 2009 2004.sd_year_graduation <- Long_format_2005_2009 %>% filter(G2_year != 0) %>% group_by(TAS_ID) %>% filter(n_distinct(year) == 2) %>% ungroup() %>% group_by(year) %>% summarize(sd_graduation = sd(G2_year, na.rm = TRUE)) %>% ungroup()
sd_year_graduation## # A tibble: 2 × 2
## year sd_graduation
## <dbl> <dbl>
## 1 2005 1.05
## 2 2009 1.06L7: Race – 1st mention 1 = White 2 = Black, African-American, or Negro 3 = American Indian or Alaska Native 4 = Asian 5 = Native Hawaiian or Pacific Islander 7 = Some other race 8 = DK 9 = NA; refused
Long_format_2005_2009 %>% group_by(year) %>% count(L7_1st_mention)## # A tibble: 14 × 3
## # Groups: year [2]
## year L7_1st_mention n
## <dbl> <dbl> <int>
## 1 2005 1 293
## 2 2005 2 208
## 3 2005 3 3
## 4 2005 4 6
## 5 2005 5 3
## 6 2005 7 6
## 7 2005 8 2
## 8 2005 9 21
## 9 2009 1 306
## 10 2009 2 206
## 11 2009 3 5
## 12 2009 4 7
## 13 2009 7 17
## 14 2009 9 1L7: Race – 2nd mention
Long_format_2005_2009 %>% group_by(year) %>% count(L7_2nd_mention)## # A tibble: 12 × 3
## # Groups: year [2]
## year L7_2nd_mention n
## <dbl> <dbl> <int>
## 1 2005 0 529
## 2 2005 1 1
## 3 2005 2 4
## 4 2005 3 4
## 5 2005 5 2
## 6 2005 7 2
## 7 2009 0 514
## 8 2009 1 1
## 9 2009 2 6
## 10 2009 3 17
## 11 2009 4 1
## 12 2009 7 3L7: Race – 3rd mention
Long_format_2005_2009 %>% group_by(year) %>% count(L7_3rd_mention)## # A tibble: 7 × 3
## # Groups: year [2]
## year L7_3rd_mention n
## <dbl> <dbl> <int>
## 1 2005 0 540
## 2 2005 3 1
## 3 2005 5 1
## 4 2009 0 536
## 5 2009 3 3
## 6 2009 5 1
## 7 2009 7 2D2D3: Widowed – year
Long_format_2005_2009 %>% group_by(year) %>% count(D2D3_year)## # A tibble: 5 × 3
## # Groups: year [2]
## year D2D3_year n
## <dbl> <dbl> <int>
## 1 2005 0 542
## 2 2009 0 538
## 3 2009 2006 2
## 4 2009 2007 1
## 5 2009 2009 1E1: Employment status – 1st mention 1 = Working now, including military 2 = Only temporarily laid off; sick or maternity leave 3 = Looking for work, unemployed 4 = Retired 5 = Disabled, permanently or temporarily 6 = Keeping house 7 = Student 8 = Other
Long_format_2005_2009 %>% group_by(year) %>% count(E1_1st_mention)## # A tibble: 14 × 3
## # Groups: year [2]
## year E1_1st_mention n
## <dbl> <dbl> <int>
## 1 2005 1 260
## 2 2005 2 3
## 3 2005 3 50
## 4 2005 5 1
## 5 2005 6 10
## 6 2005 7 213
## 7 2005 8 5
## 8 2009 1 376
## 9 2009 2 1
## 10 2009 3 77
## 11 2009 5 2
## 12 2009 6 20
## 13 2009 7 65
## 14 2009 8 1E1: Employment status – 2nd mention
Long_format_2005_2009 %>% group_by(year) %>% count(E1_2nd_mention)## # A tibble: 13 × 3
## # Groups: year [2]
## year E1_2nd_mention n
## <dbl> <dbl> <int>
## 1 2005 0 399
## 2 2005 1 27
## 3 2005 3 8
## 4 2005 5 1
## 5 2005 6 2
## 6 2005 7 105
## 7 2009 0 405
## 8 2009 1 23
## 9 2009 3 10
## 10 2009 5 2
## 11 2009 6 10
## 12 2009 7 91
## 13 2009 8 1E1: Employment status – 3rd mention
Long_format_2005_2009 %>% group_by(year) %>% count(E1_3rd_mention)## # A tibble: 7 × 3
## # Groups: year [2]
## year E1_3rd_mention n
## <dbl> <dbl> <int>
## 1 2005 0 538
## 2 2005 1 1
## 3 2005 3 1
## 4 2005 6 1
## 5 2005 7 1
## 6 2009 0 541
## 7 2009 1 1E3: Work for money 1 = Yes 5 = No 8 = DK 9 = NA; refused
Long_format_2005_2009 %>% group_by(year) %>% count(E3)## # A tibble: 7 × 3
## # Groups: year [2]
## year E3 n
## <dbl> <dbl> <int>
## 1 2005 0 290
## 2 2005 1 71
## 3 2005 5 180
## 4 2005 9 1
## 5 2009 0 401
## 6 2009 1 20
## 7 2009 5 121G1: Education status 1 = Graduated from high school 2 = Got a GED 3 = Neither
Long_format_2005_2009 %>% group_by(year) %>% count(G1)## # A tibble: 7 × 3
## # Groups: year [2]
## year G1 n
## <dbl> <dbl> <int>
## 1 2005 1 526
## 2 2005 2 1
## 3 2005 3 13
## 4 2005 9 2
## 5 2009 1 537
## 6 2009 2 4
## 7 2009 3 1G10: Attended College 1 = Yes 5 = No
Long_format_2005_2009 %>% group_by(year) %>% count(G10)## # A tibble: 7 × 3
## # Groups: year [2]
## year G10 n
## <dbl> <dbl> <int>
## 1 2005 0 14
## 2 2005 1 414
## 3 2005 5 113
## 4 2005 9 1
## 5 2009 0 1
## 6 2009 1 443
## 7 2009 5 98G11: Attending College 1 = Yes 5 = No
Long_format_2005_2009 %>% group_by(year) %>% count(G11)## # A tibble: 6 × 3
## # Groups: year [2]
## year G11 n
## <dbl> <dbl> <int>
## 1 2005 0 128
## 2 2005 1 347
## 3 2005 5 67
## 4 2009 0 99
## 5 2009 1 166
## 6 2009 5 277Filter the data (2009 & 2015)
Long_format_2009_2015 <- TAS_data_long_format_age %>% filter (TAS09 == 1) %>% filter (TAS15 == 1) %>% unite("TAS_ID", c("1968 Interview Number", "Person Number")) %>% mutate(year_new = case_when(year == 2005 ~ -1, year == 2009 ~ 0,year == 2015 ~ 1)) %>% group_by(TAS_ID) %>% mutate(Age_18_graduate = case_when(Age_18_graduate == 2033 ~ Age_18_graduate[year == 2009] + 6, Age_18_graduate == 2027 ~ Age_18_graduate[year == 2015] - 6, TRUE ~ Age_18_graduate)) %>% ungroup() %>% filter (Age_18_graduate <100) %>% group_by(TAS_ID) %>% mutate(age_difference = Age_18_graduate[year == 2015] - Age_18_graduate[year == 2009]) %>% filter(age_difference < 8) %>% filter(age_difference > 4) %>% ungroup()view(Long_format_2009_2015)knitr::kable(head(Long_format_2009_2015[, 1:43]))| TAS | TAS05 | TAS09 | TAS15 | TAS_ID | Gender | Individual is sample | Year ID Number | Sequence Number | Relationship to Head | Release Number | B5A | B5D | B6C | C2D | C2E | C2F | D2D3_month | D2D3_year | E1_1st_mention | E1_2nd_mention | E1_3rd_mention | E3 | G1 | G2_month | G2_year | G10 | G11 | G30A | G41A | G41B | G41C | G41H | G41P | H1 | L7_1st_mention | L7_2nd_mention | L7_3rd_mention | Age_17_graduate | Age_18_graduate | year | year_new | age_difference |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | NA | 1 | 1 | 4_39 | 2 | 2 | 13 | 3 | 60 | 3 | 4 | 5 | 4 | 6 | 7 | 5 | 0 | 0 | 1 | 0 | 0 | 0 | 1 | 5 | 2008 | 1 | 5 | 5 | 6 | 5 | 2 | 7 | 6 | 2 | 1 | 0 | 0 | 18 | 19 | 2009 | 0 | 6 |
| 2 | NA | 1 | 1 | 7_40 | 2 | 2 | 3836 | 2 | 22 | 3 | 2 | 2 | 7 | 7 | 3 | 4 | 0 | 0 | 6 | 0 | 0 | 5 | 1 | 6 | 2007 | 5 | 0 | 5 | 5 | 2 | 5 | 6 | 5 | 3 | 1 | 0 | 0 | 19 | 20 | 2009 | 0 | 6 |
| 2 | NA | 1 | 1 | 7_41 | 1 | 2 | 576 | 2 | 30 | 3 | 3 | 4 | 7 | 4 | 5 | 4 | 0 | 0 | 3 | 0 | 0 | 5 | 1 | 5 | 2009 | 5 | 0 | 7 | 5 | 6 | 5 | 7 | 5 | 2 | 1 | 0 | 0 | 17 | 18 | 2009 | 0 | 6 |
| 2 | NA | 1 | 1 | 10_34 | 2 | 2 | 3276 | 3 | 30 | 3 | 4 | 5 | 6 | 4 | 1 | 1 | 0 | 0 | 1 | 0 | 0 | 0 | 1 | 6 | 2008 | 1 | 5 | 7 | 7 | 5 | 4 | 7 | 5 | 2 | 2 | 0 | 0 | 18 | 19 | 2009 | 0 | 6 |
| 2 | NA | 1 | 1 | 14_31 | 2 | 2 | 713 | 1 | 10 | 3 | 5 | 5 | 7 | 4 | 4 | 4 | 0 | 0 | 1 | 0 | 0 | 0 | 1 | 6 | 2005 | 5 | 0 | 6 | 5 | 7 | 6 | 7 | 2 | 4 | 1 | 0 | 0 | 21 | 22 | 2009 | 0 | 6 |
| 2 | NA | 1 | 1 | 22_30 | 2 | 2 | 907 | 2 | 30 | 3 | 5 | 1 | 4 | 3 | 1 | 1 | 0 | 0 | 1 | 0 | 0 | 0 | 1 | 5 | 2006 | 1 | 1 | 7 | 6 | 6 | 6 | 6 | 6 | 1 | 2 | 0 | 0 | 20 | 21 | 2009 | 0 | 6 |
Year
count(Long_format_2009_2015, year)## # A tibble: 2 × 2
## year n
## <dbl> <int>
## 1 2009 515
## 2 2015 515Age
count(Long_format_2009_2015, Age_18_graduate)## # A tibble: 11 × 2
## Age_18_graduate n
## <dbl> <int>
## 1 15 1
## 2 18 154
## 3 19 134
## 4 20 136
## 5 21 89
## 6 22 2
## 7 24 155
## 8 25 134
## 9 26 136
## 10 27 87
## 11 28 2Age by year(2009)
Long_format_2009_2015 %>% filter(year == 2009) %>% count(Age_18_graduate)## # A tibble: 6 × 2
## Age_18_graduate n
## <dbl> <int>
## 1 15 1
## 2 18 154
## 3 19 134
## 4 20 136
## 5 21 88
## 6 22 2Age by year (2015)
Long_format_2009_2015 %>% filter(year == 2015) %>% count(Age_18_graduate)## # A tibble: 6 × 2
## Age_18_graduate n
## <dbl> <int>
## 1 21 1
## 2 24 155
## 3 25 134
## 4 26 136
## 5 27 87
## 6 28 2Gender 1 = Male 2 = Female
Long_format_2009_2015 %>% group_by(year) %>% count(Gender)## # A tibble: 4 × 3
## # Groups: year [2]
## year Gender n
## <dbl> <dbl> <int>
## 1 2009 1 219
## 2 2009 2 296
## 3 2015 1 219
## 4 2015 2 296G2: Years graduated high school
Long_format_2009_2015 %>% group_by(year) %>% count(G2_year)## # A tibble: 12 × 3
## # Groups: year [2]
## year G2_year n
## <dbl> <dbl> <int>
## 1 2009 0 4
## 2 2009 2005 2
## 3 2009 2006 88
## 4 2009 2007 135
## 5 2009 2008 133
## 6 2009 2009 153
## 7 2015 0 387
## 8 2015 2006 13
## 9 2015 2007 30
## 10 2015 2008 33
## 11 2015 2009 51
## 12 2015 2012 1Long_format_2009_2015 %>% filter(G2_year != 0) %>% group_by(TAS_ID) %>% filter(n_distinct(year) == 2) %>% ungroup() %>% group_by(year) %>% count(G2_year) %>% ungroup() ## # A tibble: 8 × 3
## year G2_year n
## <dbl> <dbl> <int>
## 1 2009 2006 14
## 2 2009 2007 29
## 3 2009 2008 32
## 4 2009 2009 49
## 5 2015 2006 13
## 6 2015 2007 29
## 7 2015 2008 32
## 8 2015 2009 50Long_format_2009_2015 %>% filter(G2_year != 0) %>% group_by(TAS_ID) %>% filter(n_distinct(year) == 2) %>% ungroup() %>% count(year) ## # A tibble: 2 × 2
## year n
## <dbl> <int>
## 1 2009 124
## 2 2015 124mean_year_graduation <- Long_format_2009_2015 %>% filter(G2_year != 0) %>% group_by(TAS_ID) %>% filter(n_distinct(year) == 2) %>% ungroup() %>% group_by(year) %>% summarize(mean_graduation = mean(G2_year, na.rm = TRUE)) %>% ungroup()
mean_year_graduation## # A tibble: 2 × 2
## year mean_graduation
## <dbl> <dbl>
## 1 2009 2008.
## 2 2015 2008.sd_year_graduation <- Long_format_2009_2015 %>% filter(G2_year != 0) %>% group_by(TAS_ID) %>% filter(n_distinct(year) == 2) %>% ungroup() %>% group_by(year) %>% summarize(sd_graduation = sd(G2_year, na.rm = TRUE)) %>% ungroup()
sd_year_graduation## # A tibble: 2 × 2
## year sd_graduation
## <dbl> <dbl>
## 1 2009 1.04
## 2 2015 1.03L7: Race – 1st mention 1 = White 2 = Black, African-American, or Negro 3 = American Indian or Alaska Native 4 = Asian 5 = Native Hawaiian or Pacific Islander 7 = Some other race 8 = DK 9 = NA; refused
Long_format_2009_2015 %>% group_by(year) %>% count(L7_1st_mention)## # A tibble: 13 × 3
## # Groups: year [2]
## year L7_1st_mention n
## <dbl> <dbl> <int>
## 1 2009 1 261
## 2 2009 2 198
## 3 2009 3 7
## 4 2009 4 10
## 5 2009 7 37
## 6 2009 8 1
## 7 2009 9 1
## 8 2015 1 274
## 9 2015 2 195
## 10 2015 3 8
## 11 2015 4 8
## 12 2015 7 26
## 13 2015 9 4L7: Race – 2nd mention
Long_format_2009_2015 %>% group_by(year) %>% count(L7_2nd_mention)## # A tibble: 12 × 3
## # Groups: year [2]
## year L7_2nd_mention n
## <dbl> <dbl> <int>
## 1 2009 0 489
## 2 2009 1 8
## 3 2009 2 3
## 4 2009 3 10
## 5 2009 4 1
## 6 2009 5 2
## 7 2009 7 2
## 8 2015 0 497
## 9 2015 1 4
## 10 2015 2 4
## 11 2015 3 8
## 12 2015 4 2L7: Race – 3rd mention
Long_format_2009_2015 %>% group_by(year) %>% count(L7_3rd_mention)## # A tibble: 5 × 3
## # Groups: year [2]
## year L7_3rd_mention n
## <dbl> <dbl> <int>
## 1 2009 0 513
## 2 2009 3 2
## 3 2015 0 513
## 4 2015 1 1
## 5 2015 3 1D2D3: Widowed – year
Long_format_2009_2015 %>% group_by(year) %>% count(D2D3_year)## # A tibble: 6 × 3
## # Groups: year [2]
## year D2D3_year n
## <dbl> <dbl> <int>
## 1 2009 0 512
## 2 2009 2009 3
## 3 2015 0 503
## 4 2015 2009 2
## 5 2015 2012 3
## 6 2015 2014 7E1: Employment status – 1st mention 1 = Working now, including military 2 = Only temporarily laid off; sick or maternity leave 3 = Looking for work, unemployed 4 = Retired 5 = Disabled, permanently or temporarily 6 = Keeping house 7 = Student 8 = Other
Long_format_2009_2015 %>% group_by(year) %>% count(E1_1st_mention)## # A tibble: 11 × 3
## # Groups: year [2]
## year E1_1st_mention n
## <dbl> <dbl> <int>
## 1 2009 1 242
## 2 2009 3 93
## 3 2009 6 12
## 4 2009 7 167
## 5 2009 99 1
## 6 2015 1 406
## 7 2015 2 2
## 8 2015 3 49
## 9 2015 5 4
## 10 2015 6 22
## 11 2015 7 32E1: Employment status – 2nd mention
Long_format_2009_2015 %>% group_by(year) %>% count(E1_2nd_mention)## # A tibble: 11 × 3
## # Groups: year [2]
## year E1_2nd_mention n
## <dbl> <dbl> <int>
## 1 2009 0 301
## 2 2009 1 35
## 3 2009 2 1
## 4 2009 3 28
## 5 2009 6 3
## 6 2009 7 147
## 7 2015 0 445
## 8 2015 1 6
## 9 2015 3 4
## 10 2015 6 16
## 11 2015 7 44E1: Employment status – 3rd mention
Long_format_2009_2015 %>% group_by(year) %>% count(E1_3rd_mention)## # A tibble: 3 × 3
## # Groups: year [2]
## year E1_3rd_mention n
## <dbl> <dbl> <int>
## 1 2009 0 514
## 2 2009 6 1
## 3 2015 0 515E3: Work for money 1 = Yes 5 = No 8 = DK 9 = NA; refused
Long_format_2009_2015 %>% group_by(year) %>% count(E3)## # A tibble: 6 × 3
## # Groups: year [2]
## year E3 n
## <dbl> <dbl> <int>
## 1 2009 0 277
## 2 2009 1 31
## 3 2009 5 207
## 4 2015 0 414
## 5 2015 1 8
## 6 2015 5 93G1: Education status 1 = Graduated from high school 2 = Got a GED 3 = Neither
Long_format_2009_2015 %>% group_by(year) %>% count(G1)## # A tibble: 7 × 3
## # Groups: year [2]
## year G1 n
## <dbl> <dbl> <int>
## 1 2009 1 511
## 2 2009 2 3
## 3 2009 3 1
## 4 2015 0 370
## 5 2015 1 139
## 6 2015 2 5
## 7 2015 3 1G10: Attended College 1 = Yes 5 = No
Long_format_2009_2015 %>% group_by(year) %>% count(G10)## # A tibble: 6 × 3
## # Groups: year [2]
## year G10 n
## <dbl> <dbl> <int>
## 1 2009 0 1
## 2 2009 1 385
## 3 2009 5 129
## 4 2015 0 403
## 5 2015 1 35
## 6 2015 5 77G11: Attending College 1 = Yes 5 = No
Long_format_2009_2015 %>% group_by(year) %>% count(G11)## # A tibble: 6 × 3
## # Groups: year [2]
## year G11 n
## <dbl> <dbl> <int>
## 1 2009 0 130
## 2 2009 1 323
## 3 2009 5 62
## 4 2015 0 79
## 5 2015 1 86
## 6 2015 5 350Filter the data (2005 & 2009 & 2015)
Long_format_2005_2009_2015_new <- TAS_data_long_format_age %>% filter(year==2005| year==2015| year == 2009) %>% filter(Age_18_graduate == 18|Age_18_graduate == 19) %>% mutate(year_new = case_when(year == 2005 ~ -1, year == 2009 ~ 0,year == 2015 ~ 1)) %>% unite("TAS_ID", c("1968 Interview Number", "Person Number")) %>% mutate(year_new = case_when(year == 2005 ~ -1, year == 2009 ~ 0,year == 2015 ~ 1))knitr::kable(head(Long_format_2005_2009_2015_new[, 1:42]))| TAS | TAS05 | TAS09 | TAS15 | TAS_ID | Gender | Individual is sample | Year ID Number | Sequence Number | Relationship to Head | Release Number | B5A | B5D | B6C | C2D | C2E | C2F | D2D3_month | D2D3_year | E1_1st_mention | E1_2nd_mention | E1_3rd_mention | E3 | G1 | G2_month | G2_year | G10 | G11 | G30A | G41A | G41B | G41C | G41H | G41P | H1 | L7_1st_mention | L7_2nd_mention | L7_3rd_mention | Age_17_graduate | Age_18_graduate | year | year_new |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | 1 | NA | NA | 18_38 | 2 | 2 | 5647 | 3 | 98 | 5 | 3 | 4 | 3 | 4 | 2 | 2 | 0 | 0 | 3 | 7 | 0 | 5 | 1 | 6 | 2004 | 1 | 5 | 6 | 5 | 5 | 5 | 7 | 5 | 2 | 1 | 0 | 0 | 18 | 19 | 2005 | -1 |
| 2 | 1 | 1 | NA | 47_34 | 2 | 2 | 2516 | 3 | 30 | 5 | 4 | 5 | 6 | 4 | 5 | 2 | 0 | 0 | 1 | 0 | 0 | 0 | 1 | 5 | 2005 | 5 | 0 | 6 | 3 | 6 | 4 | 7 | 4 | 1 | 1 | 0 | 0 | 17 | 18 | 2005 | -1 |
| 2 | 1 | 1 | NA | 53_36 | 2 | 2 | 1616 | 3 | 30 | 5 | 4 | 5 | 7 | 4 | 1 | 1 | 0 | 0 | 6 | 0 | 0 | 1 | 1 | 6 | 2005 | 1 | 5 | 7 | 7 | 7 | 5 | 7 | 6 | 2 | 1 | 0 | 0 | 17 | 18 | 2005 | -1 |
| 2 | 1 | 1 | NA | 79_32 | 2 | 2 | 6520 | 2 | 30 | 5 | 3 | 4 | 6 | 7 | 5 | 3 | 0 | 0 | 1 | 7 | 0 | 0 | 1 | 5 | 2004 | 1 | 1 | 0 | 7 | 7 | 6 | 7 | 4 | 1 | 1 | 0 | 0 | 18 | 19 | 2005 | -1 |
| 2 | 1 | 1 | NA | 88_35 | 1 | 2 | 3411 | 2 | 30 | 5 | 2 | 5 | 7 | 3 | 1 | 2 | 0 | 0 | 1 | 0 | 0 | 0 | 1 | 5 | 2005 | 1 | 1 | 7 | 2 | 6 | 5 | 6 | 7 | 2 | 1 | 0 | 0 | 17 | 18 | 2005 | -1 |
| 2 | 1 | 1 | NA | 89_34 | 2 | 2 | 4527 | 3 | 30 | 5 | 2 | 4 | 5 | 2 | 3 | 1 | 0 | 0 | 3 | 7 | 0 | 5 | 1 | 5 | 2005 | 1 | 1 | 7 | 5 | 6 | 4 | 7 | 5 | 1 | 1 | 0 | 0 | 17 | 18 | 2005 | -1 |
Long_format_2005_2009_2015_new %>% count(year)## # A tibble: 3 × 2
## year n
## <dbl> <int>
## 1 2005 348
## 2 2009 367
## 3 2015 254Year
count(Long_format_2005_2009_2015_new, year)## # A tibble: 3 × 2
## year n
## <dbl> <int>
## 1 2005 348
## 2 2009 367
## 3 2015 254Age
count(Long_format_2005_2009_2015_new, Age_18_graduate)## # A tibble: 2 × 2
## Age_18_graduate n
## <dbl> <int>
## 1 18 465
## 2 19 504Age by year(2005)
Long_format_2005_2009_2015_new %>% filter(year == 2005) %>% count(Age_18_graduate)## # A tibble: 2 × 2
## Age_18_graduate n
## <dbl> <int>
## 1 18 179
## 2 19 169Age by year(2009)
Long_format_2005_2009_2015_new %>% filter(year == 2009) %>% count(Age_18_graduate)## # A tibble: 2 × 2
## Age_18_graduate n
## <dbl> <int>
## 1 18 195
## 2 19 172Age by year (2015)
Long_format_2005_2009_2015_new %>% filter(year == 2015) %>% count(Age_18_graduate)## # A tibble: 2 × 2
## Age_18_graduate n
## <dbl> <int>
## 1 18 91
## 2 19 163Gender 1 = Male 2 = Female
Long_format_2005_2009_2015_new %>% group_by(year) %>% count(Gender)## # A tibble: 6 × 3
## # Groups: year [3]
## year Gender n
## <dbl> <dbl> <int>
## 1 2005 1 169
## 2 2005 2 179
## 3 2009 1 165
## 4 2009 2 202
## 5 2015 1 119
## 6 2015 2 135G2: Years graduated high school
Long_format_2005_2009_2015_new %>% group_by(year) %>% count(G2_year)## # A tibble: 6 × 3
## # Groups: year [3]
## year G2_year n
## <dbl> <dbl> <int>
## 1 2005 2004 169
## 2 2005 2005 179
## 3 2009 2008 172
## 4 2009 2009 195
## 5 2015 2014 163
## 6 2015 2015 91mean_year_graduation <- Long_format_2005_2009_2015_new %>% group_by(year) %>% summarize(mean_graduation = mean(G2_year, na.rm = TRUE)) %>% ungroup()
mean_year_graduation## # A tibble: 3 × 2
## year mean_graduation
## <dbl> <dbl>
## 1 2005 2005.
## 2 2009 2009.
## 3 2015 2014.sd_year_graduation <- Long_format_2005_2009_2015_new %>% group_by(year) %>% summarize(sd_graduation = sd(G2_year, na.rm = TRUE)) %>% ungroup()
sd_year_graduation## # A tibble: 3 × 2
## year sd_graduation
## <dbl> <dbl>
## 1 2005 0.501
## 2 2009 0.500
## 3 2015 0.480L7: Race – 1st mention 1 = White 2 = Black, African-American, or Negro 3 = American Indian or Alaska Native 4 = Asian 5 = Native Hawaiian or Pacific Islander 7 = Some other race 8 = DK 9 = NA; refused
Long_format_2005_2009_2015_new %>% group_by(year) %>% count(L7_1st_mention)## # A tibble: 23 × 3
## # Groups: year [3]
## year L7_1st_mention n
## <dbl> <dbl> <int>
## 1 2005 1 192
## 2 2005 2 129
## 3 2005 3 1
## 4 2005 4 5
## 5 2005 5 3
## 6 2005 7 4
## 7 2005 8 1
## 8 2005 9 13
## 9 2009 1 184
## 10 2009 2 139
## # ℹ 13 more rowsL7: Race – 2nd mention
Long_format_2005_2009_2015_new %>% group_by(year) %>% count(L7_2nd_mention)## # A tibble: 18 × 3
## # Groups: year [3]
## year L7_2nd_mention n
## <dbl> <dbl> <int>
## 1 2005 0 341
## 2 2005 2 2
## 3 2005 3 2
## 4 2005 5 2
## 5 2005 7 1
## 6 2009 0 347
## 7 2009 1 8
## 8 2009 2 1
## 9 2009 3 6
## 10 2009 5 2
## 11 2009 7 3
## 12 2015 0 228
## 13 2015 1 4
## 14 2015 2 3
## 15 2015 3 15
## 16 2015 4 1
## 17 2015 5 1
## 18 2015 7 2L7: Race – 3rd mention
Long_format_2005_2009_2015_new %>% group_by(year) %>% count(L7_3rd_mention)## # A tibble: 6 × 3
## # Groups: year [3]
## year L7_3rd_mention n
## <dbl> <dbl> <int>
## 1 2005 0 348
## 2 2009 0 364
## 3 2009 3 3
## 4 2015 0 251
## 5 2015 1 2
## 6 2015 7 1D2D3: Widowed – year
Long_format_2005_2009_2015_new %>% group_by(year) %>% count(D2D3_year)## # A tibble: 3 × 3
## # Groups: year [3]
## year D2D3_year n
## <dbl> <dbl> <int>
## 1 2005 0 348
## 2 2009 0 367
## 3 2015 0 254E1: Employment status – 1st mention 1 = Working now, including military 2 = Only temporarily laid off; sick or maternity leave 3 = Looking for work, unemployed 4 = Retired 5 = Disabled, permanently or temporarily 6 = Keeping house 7 = Student 8 = Other
Long_format_2005_2009_2015_new %>% group_by(year) %>% count(E1_1st_mention)## # A tibble: 16 × 3
## # Groups: year [3]
## year E1_1st_mention n
## <dbl> <dbl> <int>
## 1 2005 1 163
## 2 2005 2 1
## 3 2005 3 38
## 4 2005 6 6
## 5 2005 7 136
## 6 2005 8 4
## 7 2009 1 149
## 8 2009 3 73
## 9 2009 6 5
## 10 2009 7 139
## 11 2009 99 1
## 12 2015 1 133
## 13 2015 2 1
## 14 2015 3 46
## 15 2015 6 7
## 16 2015 7 67E1: Employment status – 2nd mention
Long_format_2005_2009_2015_new %>% group_by(year) %>% count(E1_2nd_mention)## # A tibble: 15 × 3
## # Groups: year [3]
## year E1_2nd_mention n
## <dbl> <dbl> <int>
## 1 2005 0 261
## 2 2005 1 13
## 3 2005 3 5
## 4 2005 6 3
## 5 2005 7 66
## 6 2009 0 214
## 7 2009 1 19
## 8 2009 3 23
## 9 2009 6 4
## 10 2009 7 107
## 11 2015 0 158
## 12 2015 1 14
## 13 2015 3 10
## 14 2015 6 2
## 15 2015 7 70E1: Employment status – 3rd mention
Long_format_2005_2009_2015_new %>% group_by(year) %>% count(E1_3rd_mention)## # A tibble: 6 × 3
## # Groups: year [3]
## year E1_3rd_mention n
## <dbl> <dbl> <int>
## 1 2005 0 345
## 2 2005 1 1
## 3 2005 3 1
## 4 2005 7 1
## 5 2009 0 367
## 6 2015 0 254E3: Work for money 1 = Yes 5 = No 8 = DK 9 = NA; refused
Long_format_2005_2009_2015_new %>% group_by(year) %>% count(E3)## # A tibble: 10 × 3
## # Groups: year [3]
## year E3 n
## <dbl> <dbl> <int>
## 1 2005 0 177
## 2 2005 1 45
## 3 2005 5 125
## 4 2005 9 1
## 5 2009 0 168
## 6 2009 1 18
## 7 2009 5 181
## 8 2015 0 149
## 9 2015 1 6
## 10 2015 5 99G1: Education status 1 = Graduated from high school 2 = Got a GED 3 = Neither
Long_format_2005_2009_2015_new %>% group_by(year) %>% count(G1)## # A tibble: 3 × 3
## # Groups: year [3]
## year G1 n
## <dbl> <dbl> <int>
## 1 2005 1 348
## 2 2009 1 367
## 3 2015 1 254G10: Attended College 1 = Yes 5 = No
Long_format_2005_2009_2015_new %>% group_by(year) %>% count(G10)## # A tibble: 8 × 3
## # Groups: year [3]
## year G10 n
## <dbl> <dbl> <int>
## 1 2005 1 255
## 2 2005 5 92
## 3 2005 9 1
## 4 2009 1 265
## 5 2009 5 102
## 6 2015 0 1
## 7 2015 1 173
## 8 2015 5 80G11: Attending College 1 = Yes 5 = No
Long_format_2005_2009_2015_new %>% group_by(year) %>% count(G11)## # A tibble: 9 × 3
## # Groups: year [3]
## year G11 n
## <dbl> <dbl> <int>
## 1 2005 0 93
## 2 2005 1 221
## 3 2005 5 34
## 4 2009 0 102
## 5 2009 1 242
## 6 2009 5 23
## 7 2015 0 80
## 8 2015 1 139
## 9 2015 5 35