############################################################
# 1. Required Packages
############################################################
library(haven)Warning: package 'haven' was built under R version 4.4.3library(tidyverse)Warning: package 'tidyverse' was built under R version 4.4.3Warning: package 'ggplot2' was built under R version 4.4.3Warning: package 'tidyr' was built under R version 4.4.2Warning: package 'dplyr' was built under R version 4.4.3Warning: package 'lubridate' was built under R version 4.4.3── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
✔ dplyr 1.1.4 ✔ readr 2.1.5
✔ forcats 1.0.0 ✔ stringr 1.5.1
✔ ggplot2 4.0.2 ✔ tibble 3.2.1
✔ lubridate 1.9.4 ✔ tidyr 1.3.1
✔ purrr 1.0.2
── 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(janitor)Warning: package 'janitor' was built under R version 4.4.3
Attaching package: 'janitor'
The following objects are masked from 'package:stats':
chisq.test, fisher.testlibrary(skimr)Warning: package 'skimr' was built under R version 4.4.3############################################################
# 2. Data Import
############################################################
TEDS_2016 <- haven::read_dta(
"https://github.com/datageneration/home/blob/master/DataProgramming/data/TEDS_2016.dta?raw=true"
)
############################################################
# 3. Cleaning Missing Values
############################################################
TEDS_2016 <- TEDS_2016 %>%
mutate(across(everything(), ~na_if(., 96))) %>%
mutate(across(everything(), ~na_if(., 97))) %>%
mutate(across(everything(), ~na_if(., 98))) %>%
mutate(across(everything(), ~na_if(., 99)))
############################################################
# 4. Summary Statistics
############################################################
summary(TEDS_2016) District Sex Age Edu Arear
Min. : 201 Min. :1.000 Min. :1.0 Min. :1.000 Min. :1.000
1st Qu.:1401 1st Qu.:1.000 1st Qu.:2.0 1st Qu.:2.000 1st Qu.:1.000
Median :6406 Median :1.000 Median :3.0 Median :3.000 Median :3.000
Mean :4661 Mean :1.486 Mean :3.3 Mean :3.334 Mean :2.744
3rd Qu.:6604 3rd Qu.:2.000 3rd Qu.:5.0 3rd Qu.:5.000 3rd Qu.:4.000
Max. :6806 Max. :2.000 Max. :5.0 Max. :9.000 Max. :6.000
Career Career8 Ethnic Party
Min. :1.000 Min. :1.000 Min. :1.000 Min. : 1.00
1st Qu.:1.000 1st Qu.:2.000 1st Qu.:1.000 1st Qu.: 5.00
Median :2.000 Median :4.000 Median :1.000 Median : 7.00
Mean :2.683 Mean :3.811 Mean :1.658 Mean :13.02
3rd Qu.:4.000 3rd Qu.:5.000 3rd Qu.:2.000 3rd Qu.:25.00
Max. :5.000 Max. :8.000 Max. :9.000 Max. :26.00
PartyID Tondu Tondu3 nI2
Min. :1.000 Min. :1.000 Min. :1.000 Min. :1.000
1st Qu.:2.000 1st Qu.:3.000 1st Qu.:2.000 1st Qu.:1.000
Median :2.000 Median :4.000 Median :2.000 Median :2.000
Mean :4.522 Mean :4.127 Mean :2.667 Mean :1.846
3rd Qu.:9.000 3rd Qu.:5.000 3rd Qu.:3.000 3rd Qu.:3.000
Max. :9.000 Max. :9.000 Max. :9.000 Max. :3.000
NA's :585
votetsai green votetsai_nm votetsai_all
Min. :0.0000 Min. :0.0000 Min. :0.0000 Min. :0.0000
1st Qu.:0.0000 1st Qu.:0.0000 1st Qu.:0.0000 1st Qu.:0.0000
Median :1.0000 Median :0.0000 Median :1.0000 Median :1.0000
Mean :0.6265 Mean :0.3781 Mean :0.6265 Mean :0.5478
3rd Qu.:1.0000 3rd Qu.:1.0000 3rd Qu.:1.0000 3rd Qu.:1.0000
Max. :1.0000 Max. :1.0000 Max. :1.0000 Max. :1.0000
NA's :429 NA's :429 NA's :248
Independence Unification sq Taiwanese
Min. :0.0000 Min. :0.0000 Min. :0.0000 Min. :0.0000
1st Qu.:0.0000 1st Qu.:0.0000 1st Qu.:0.0000 1st Qu.:0.0000
Median :0.0000 Median :0.0000 Median :1.0000 Median :1.0000
Mean :0.2888 Mean :0.1225 Mean :0.5172 Mean :0.6272
3rd Qu.:1.0000 3rd Qu.:0.0000 3rd Qu.:1.0000 3rd Qu.:1.0000
Max. :1.0000 Max. :1.0000 Max. :1.0000 Max. :1.0000
edu female whitecollar lowincome
Min. :1.000 Min. :0.0000 Min. :0.0000 Min. :1.000
1st Qu.:2.000 1st Qu.:0.0000 1st Qu.:0.0000 1st Qu.:4.000
Median :3.000 Median :0.0000 Median :1.0000 Median :5.000
Mean :3.301 Mean :0.4864 Mean :0.5373 Mean :4.343
3rd Qu.:5.000 3rd Qu.:1.0000 3rd Qu.:1.0000 3rd Qu.:5.000
Max. :5.000 Max. :1.0000 Max. :1.0000 Max. :5.000
NA's :10
income income_nm age KMT
Min. : 1.000 Min. : 1.000 Min. : 20.00 Min. :0.0000
1st Qu.: 3.000 1st Qu.: 2.000 1st Qu.: 35.00 1st Qu.:0.0000
Median : 5.500 Median : 5.000 Median : 49.00 Median :0.0000
Mean : 5.324 Mean : 5.281 Mean : 49.11 Mean :0.2296
3rd Qu.: 7.000 3rd Qu.: 8.000 3rd Qu.: 61.00 3rd Qu.:0.0000
Max. :10.000 Max. :10.000 Max. :100.00 Max. :1.0000
NA's :330
DPP npp noparty pfp
Min. :0.0000 Min. :0.00000 Min. :0.0000 Min. :0.00000
1st Qu.:0.0000 1st Qu.:0.00000 1st Qu.:0.0000 1st Qu.:0.00000
Median :0.0000 Median :0.00000 Median :0.0000 Median :0.00000
Mean :0.3497 Mean :0.02544 Mean :0.3716 Mean :0.01893
3rd Qu.:1.0000 3rd Qu.:0.00000 3rd Qu.:1.0000 3rd Qu.:0.00000
Max. :1.0000 Max. :1.00000 Max. :1.0000 Max. :1.00000
South north Minnan_father Mainland_father
Min. :0.0000 Min. :0.0000 Min. :0.0000 Min. :0.0000
1st Qu.:0.0000 1st Qu.:0.0000 1st Qu.:0.0000 1st Qu.:0.0000
Median :0.0000 Median :0.0000 Median :1.0000 Median :0.0000
Mean :0.4947 Mean :0.4799 Mean :0.7225 Mean :0.1024
3rd Qu.:1.0000 3rd Qu.:1.0000 3rd Qu.:1.0000 3rd Qu.:0.0000
Max. :1.0000 Max. :1.0000 Max. :1.0000 Max. :1.0000
Econ_worse Inequality inequality5 econworse5
Min. :0.0000 Min. :0.0000 Min. :1.000 Min. :1.000
1st Qu.:0.0000 1st Qu.:1.0000 1st Qu.:4.000 1st Qu.:3.000
Median :1.0000 Median :1.0000 Median :5.000 Median :4.000
Mean :0.5544 Mean :0.9355 Mean :4.495 Mean :3.644
3rd Qu.:1.0000 3rd Qu.:1.0000 3rd Qu.:5.000 3rd Qu.:4.000
Max. :1.0000 Max. :1.0000 Max. :5.000 Max. :5.000
Govt_for_public pubwelf5 Govt_dont_care highincome
Min. :0.0000 Min. :1.000 Min. :0.0000 Min. :0.0000
1st Qu.:0.0000 1st Qu.:2.000 1st Qu.:0.0000 1st Qu.:0.0000
Median :0.0000 Median :3.000 Median :0.0000 Median :1.0000
Mean :0.4249 Mean :2.877 Mean :0.4988 Mean :0.5765
3rd Qu.:1.0000 3rd Qu.:4.000 3rd Qu.:1.0000 3rd Qu.:1.0000
Max. :1.0000 Max. :5.000 Max. :1.0000 Max. :1.0000
NA's :330
votekmt votekmt_nm Blue Green No_Party
Min. :0.0000 Min. :0.0000 Min. :0 Min. :0 Min. :0
1st Qu.:0.0000 1st Qu.:0.0000 1st Qu.:0 1st Qu.:0 1st Qu.:0
Median :0.0000 Median :0.0000 Median :0 Median :0 Median :0
Mean :0.2053 Mean :0.2752 Mean :0 Mean :0 Mean :0
3rd Qu.:0.0000 3rd Qu.:1.0000 3rd Qu.:0 3rd Qu.:0 3rd Qu.:0
Max. :1.0000 Max. :1.0000 Max. :0 Max. :0 Max. :0
NA's :429
voteblue voteblue_nm votedpp_1 votekmt_1
Min. :0.0000 Min. :0.0000 Min. :0.0000 Min. :0.0000
1st Qu.:0.0000 1st Qu.:0.0000 1st Qu.:0.0000 1st Qu.:0.0000
Median :0.0000 Median :0.0000 Median :1.0000 Median :0.0000
Mean :0.2787 Mean :0.3735 Mean :0.5256 Mean :0.2309
3rd Qu.:1.0000 3rd Qu.:1.0000 3rd Qu.:1.0000 3rd Qu.:0.0000
Max. :1.0000 Max. :1.0000 Max. :1.0000 Max. :1.0000
NA's :429 NA's :187 NA's :187 skim(TEDS_2016)Warning in attr(x, "align"): 'xfun::attr()' is deprecated.
Use 'xfun::attr2()' instead.
See help("Deprecated")Warning in attr(x, "align"): 'xfun::attr()' is deprecated.
Use 'xfun::attr2()' instead.
See help("Deprecated")| Name | TEDS_2016 |
| Number of rows | 1690 |
| Number of columns | 54 |
| _______________________ | |
| Column type frequency: | |
| numeric | 54 |
| ________________________ | |
| Group variables | None |
Variable type: numeric
| skim_variable | n_missing | complete_rate | mean | sd | p0 | p25 | p50 | p75 | p100 | hist |
|---|---|---|---|---|---|---|---|---|---|---|
| District | 0 | 1.00 | 4660.58 | 2652.46 | 201 | 1401 | 6406.0 | 6604 | 6806 | ▃▁▁▁▇ |
| Sex | 0 | 1.00 | 1.49 | 0.50 | 1 | 1 | 1.0 | 2 | 2 | ▇▁▁▁▇ |
| Age | 0 | 1.00 | 3.30 | 1.44 | 1 | 2 | 3.0 | 5 | 5 | ▅▅▅▆▇ |
| Edu | 0 | 1.00 | 3.33 | 1.55 | 1 | 2 | 3.0 | 5 | 9 | ▆▇▇▁▁ |
| Arear | 0 | 1.00 | 2.74 | 1.56 | 1 | 1 | 3.0 | 4 | 6 | ▇▃▃▂▁ |
| Career | 0 | 1.00 | 2.68 | 1.43 | 1 | 1 | 2.0 | 4 | 5 | ▇▆▂▇▃ |
| Career8 | 0 | 1.00 | 3.81 | 1.98 | 1 | 2 | 4.0 | 5 | 8 | ▇▅▇▁▅ |
| Ethnic | 0 | 1.00 | 1.66 | 1.50 | 1 | 1 | 1.0 | 2 | 9 | ▇▁▁▁▁ |
| Party | 0 | 1.00 | 13.02 | 9.93 | 1 | 5 | 7.0 | 25 | 26 | ▇▂▁▁▇ |
| PartyID | 0 | 1.00 | 4.52 | 3.55 | 1 | 2 | 2.0 | 9 | 9 | ▇▁▁▁▅ |
| Tondu | 0 | 1.00 | 4.13 | 1.77 | 1 | 3 | 4.0 | 5 | 9 | ▂▇▃▁▁ |
| Tondu3 | 0 | 1.00 | 2.67 | 1.86 | 1 | 2 | 2.0 | 3 | 9 | ▇▃▁▁▁ |
| nI2 | 585 | 0.65 | 1.85 | 0.82 | 1 | 1 | 2.0 | 3 | 3 | ▇▁▆▁▅ |
| votetsai | 429 | 0.75 | 0.63 | 0.48 | 0 | 0 | 1.0 | 1 | 1 | ▅▁▁▁▇ |
| green | 0 | 1.00 | 0.38 | 0.49 | 0 | 0 | 0.0 | 1 | 1 | ▇▁▁▁▅ |
| votetsai_nm | 429 | 0.75 | 0.63 | 0.48 | 0 | 0 | 1.0 | 1 | 1 | ▅▁▁▁▇ |
| votetsai_all | 248 | 0.85 | 0.55 | 0.50 | 0 | 0 | 1.0 | 1 | 1 | ▆▁▁▁▇ |
| Independence | 0 | 1.00 | 0.29 | 0.45 | 0 | 0 | 0.0 | 1 | 1 | ▇▁▁▁▃ |
| Unification | 0 | 1.00 | 0.12 | 0.33 | 0 | 0 | 0.0 | 0 | 1 | ▇▁▁▁▁ |
| sq | 0 | 1.00 | 0.52 | 0.50 | 0 | 0 | 1.0 | 1 | 1 | ▇▁▁▁▇ |
| Taiwanese | 0 | 1.00 | 0.63 | 0.48 | 0 | 0 | 1.0 | 1 | 1 | ▅▁▁▁▇ |
| edu | 10 | 0.99 | 3.30 | 1.49 | 1 | 2 | 3.0 | 5 | 5 | ▅▂▆▂▇ |
| female | 0 | 1.00 | 0.49 | 0.50 | 0 | 0 | 0.0 | 1 | 1 | ▇▁▁▁▇ |
| whitecollar | 0 | 1.00 | 0.54 | 0.50 | 0 | 0 | 1.0 | 1 | 1 | ▇▁▁▁▇ |
| lowincome | 0 | 1.00 | 4.34 | 0.82 | 1 | 4 | 5.0 | 5 | 5 | ▁▁▁▆▇ |
| income | 0 | 1.00 | 5.32 | 2.74 | 1 | 3 | 5.5 | 7 | 10 | ▅▃▇▃▃ |
| income_nm | 330 | 0.80 | 5.28 | 3.05 | 1 | 2 | 5.0 | 8 | 10 | ▇▅▆▆▆ |
| age | 0 | 1.00 | 49.11 | 16.81 | 20 | 35 | 49.0 | 61 | 100 | ▇▇▇▃▁ |
| KMT | 0 | 1.00 | 0.23 | 0.42 | 0 | 0 | 0.0 | 0 | 1 | ▇▁▁▁▂ |
| DPP | 0 | 1.00 | 0.35 | 0.48 | 0 | 0 | 0.0 | 1 | 1 | ▇▁▁▁▅ |
| npp | 0 | 1.00 | 0.03 | 0.16 | 0 | 0 | 0.0 | 0 | 1 | ▇▁▁▁▁ |
| noparty | 0 | 1.00 | 0.37 | 0.48 | 0 | 0 | 0.0 | 1 | 1 | ▇▁▁▁▅ |
| pfp | 0 | 1.00 | 0.02 | 0.14 | 0 | 0 | 0.0 | 0 | 1 | ▇▁▁▁▁ |
| South | 0 | 1.00 | 0.49 | 0.50 | 0 | 0 | 0.0 | 1 | 1 | ▇▁▁▁▇ |
| north | 0 | 1.00 | 0.48 | 0.50 | 0 | 0 | 0.0 | 1 | 1 | ▇▁▁▁▇ |
| Minnan_father | 0 | 1.00 | 0.72 | 0.45 | 0 | 0 | 1.0 | 1 | 1 | ▃▁▁▁▇ |
| Mainland_father | 0 | 1.00 | 0.10 | 0.30 | 0 | 0 | 0.0 | 0 | 1 | ▇▁▁▁▁ |
| Econ_worse | 0 | 1.00 | 0.55 | 0.50 | 0 | 0 | 1.0 | 1 | 1 | ▆▁▁▁▇ |
| Inequality | 0 | 1.00 | 0.94 | 0.25 | 0 | 1 | 1.0 | 1 | 1 | ▁▁▁▁▇ |
| inequality5 | 0 | 1.00 | 4.49 | 0.73 | 1 | 4 | 5.0 | 5 | 5 | ▁▁▁▅▇ |
| econworse5 | 0 | 1.00 | 3.64 | 0.78 | 1 | 3 | 4.0 | 4 | 5 | ▁▁▇▇▂ |
| Govt_for_public | 0 | 1.00 | 0.42 | 0.49 | 0 | 0 | 0.0 | 1 | 1 | ▇▁▁▁▆ |
| pubwelf5 | 0 | 1.00 | 2.88 | 1.17 | 1 | 2 | 3.0 | 4 | 5 | ▂▇▂▇▁ |
| Govt_dont_care | 0 | 1.00 | 0.50 | 0.50 | 0 | 0 | 0.0 | 1 | 1 | ▇▁▁▁▇ |
| highincome | 330 | 0.80 | 0.58 | 0.49 | 0 | 0 | 1.0 | 1 | 1 | ▆▁▁▁▇ |
| votekmt | 0 | 1.00 | 0.21 | 0.40 | 0 | 0 | 0.0 | 0 | 1 | ▇▁▁▁▂ |
| votekmt_nm | 429 | 0.75 | 0.28 | 0.45 | 0 | 0 | 0.0 | 1 | 1 | ▇▁▁▁▃ |
| Blue | 0 | 1.00 | 0.00 | 0.00 | 0 | 0 | 0.0 | 0 | 0 | ▁▁▇▁▁ |
| Green | 0 | 1.00 | 0.00 | 0.00 | 0 | 0 | 0.0 | 0 | 0 | ▁▁▇▁▁ |
| No_Party | 0 | 1.00 | 0.00 | 0.00 | 0 | 0 | 0.0 | 0 | 0 | ▁▁▇▁▁ |
| voteblue | 0 | 1.00 | 0.28 | 0.45 | 0 | 0 | 0.0 | 1 | 1 | ▇▁▁▁▃ |
| voteblue_nm | 429 | 0.75 | 0.37 | 0.48 | 0 | 0 | 0.0 | 1 | 1 | ▇▁▁▁▅ |
| votedpp_1 | 187 | 0.89 | 0.53 | 0.50 | 0 | 0 | 1.0 | 1 | 1 | ▇▁▁▁▇ |
| votekmt_1 | 187 | 0.89 | 0.23 | 0.42 | 0 | 0 | 0.0 | 0 | 1 | ▇▁▁▁▂ |
############################################################
# 5. Recode Tondu Variable
############################################################
TEDS_2016$Tondu <- factor(
TEDS_2016$Tondu,
levels = 1:7,
labels = c(
"Unification now",
"Status quo, unif. in future",
"Status quo, decide later",
"Status quo forever",
"Status quo, indep. in future",
"Independence now",
"No response"
)
)
############################################################
# 6. Frequency Table
############################################################
tabyl(TEDS_2016, Tondu) Tondu n percent valid_percent
Unification now 27 0.01597633 0.01720841
Status quo, unif. in future 180 0.10650888 0.11472275
Status quo, decide later 546 0.32307692 0.34799235
Status quo forever 328 0.19408284 0.20905035
Status quo, indep. in future 380 0.22485207 0.24219248
Independence now 108 0.06390533 0.06883365
No response 0 0.00000000 0.00000000
<NA> 121 0.07159763 NA############################################################
# 7. Visualization
############################################################
ggplot(TEDS_2016, aes(x = Tondu)) +
geom_bar(fill = "steelblue") +
theme_minimal() +
labs(title = "Distribution of Tondu",
x = "Tondu Position",
y = "Count") +
theme(axis.text.x = element_text(angle = 45, hjust = 1))
############################################################
# 8. Regression Analysis (OLS)
############################################################
TEDS_reg <- TEDS_2016 %>%
dplyr::select(Tondu, female, DPP, age, income, edu, Taiwanese, Econ_worse) %>%
drop_na()
model1 <- lm(as.numeric(Tondu) ~ female + DPP + age + income +
edu + Taiwanese + Econ_worse,
data = TEDS_reg)
summary(model1)
Call:
lm(formula = as.numeric(Tondu) ~ female + DPP + age + income +
edu + Taiwanese + Econ_worse, data = TEDS_reg)
Residuals:
Min 1Q Median 3Q Max
-2.88351 -0.89814 0.00172 0.83385 3.15877
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 3.572392 0.179977 19.849 < 2e-16 ***
female 0.054122 0.054308 0.997 0.319
DPP 0.524908 0.059906 8.762 < 2e-16 ***
age -0.009040 0.002090 -4.324 1.63e-05 ***
income -0.008403 0.010395 -0.808 0.419
edu -0.003484 0.024434 -0.143 0.887
Taiwanese 0.753306 0.060913 12.367 < 2e-16 ***
Econ_worse -0.037809 0.055702 -0.679 0.497
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 1.061 on 1555 degrees of freedom
Multiple R-squared: 0.2082, Adjusted R-squared: 0.2046
F-statistic: 58.4 on 7 and 1555 DF, p-value: < 2.2e-16