Introduction
In Table 2, the overall response rates are compared within the incentive group samples. Therefore the three variable dimensions “Education”, “Occupational position”, and “Personal income” (including all their single items) are being taken into account.
Education
# Table with absolute frequencies
t1 <- WaveOne %>%
filter(rr=="Response") %>%
with(table(edu,Pumavers)) %>%
vcd::mar_table()
# Table with relative frequencies
t2 <- WaveOne %>%
filter(rr=="Response") %>%
with(table(edu,Pumavers)) %>%
cbind(rowSums(.)) %>%
prop.table(2) %>%
vcd::mar_table()
# Combine both tables
paste0(t1, " (", scales::percent(t2[,1:5], accuracy = 0.1), ")") %>%
matrix(ncol = 5) %>%
cbind(c(levels(WaveOne$edu),
"Total"
),.) %>%
as.data.frame() %>%
setNames(c("Answer",
"Brochure",
"2€ token",
"5€ token",
"Voucher",
"Total")) %>%
kable("html") %>%
kable_styling("striped") %>%
column_spec(1, width = "30em")
| Answer |
Brochure |
2€ token |
5€ token |
Voucher |
Total |
| Max. compulsory schooling |
2 (1.2%) |
8 (3.2%) |
13 (4.9%) |
11 (4.4%) |
34 (3.7%) |
| Apprenticeship |
39 (23.5%) |
73 (29.3%) |
74 (27.7%) |
79 (31.9%) |
265 (28.5%) |
| Vocational or commercial school |
23 (13.9%) |
17 (6.8%) |
42 (15.7%) |
21 (8.5%) |
103 (11.1%) |
| Matura |
46 (27.7%) |
68 (27.3%) |
63 (23.6%) |
59 (23.8%) |
236 (25.4%) |
| Higher degree after Matura |
10 (6.0%) |
12 (4.8%) |
11 (4.1%) |
12 (4.8%) |
45 (4.8%) |
| University degree |
46 (27.7%) |
71 (28.5%) |
64 (24.0%) |
66 (26.6%) |
247 (26.6%) |
| Total |
166 (100.0%) |
249 (100.0%) |
267 (100.0%) |
248 (100.0%) |
930 (100.0%) |
Occupational position
# Table with absolute frequencies
t1 <- WaveOne %>%
filter(rr=="Response") %>%
with(table(job,Pumavers)) %>%
vcd::mar_table()
# Table with relative frequencies
t2 <- WaveOne %>%
filter(rr=="Response") %>%
with(table(job,Pumavers)) %>%
cbind(rowSums(.)) %>%
prop.table(2) %>%
vcd::mar_table()
# Combine both tables
paste0(t1, " (", scales::percent(t2[,1:5], accuracy = 0.1), ")") %>%
matrix(ncol = 5) %>%
cbind(c(levels(WaveOne$job),
"Total"
),.) %>%
as.data.frame() %>%
setNames(c("Answer",
"Brochure",
"2€ token",
"5€ token",
"Voucher",
"Total")) %>%
kable("html") %>%
kable_styling("striped") %>%
column_spec(1, width = "30em")
| Answer |
Brochure |
2€ token |
5€ token |
Voucher |
Total |
| Clerk |
84 (44.7%) |
120 (43.5%) |
132 (45.4%) |
123 (44.9%) |
459 (44.6%) |
| Worker |
5 (2.7%) |
24 (8.7%) |
20 (6.9%) |
18 (6.6%) |
67 (6.5%) |
| Civil servant |
19 (10.1%) |
26 (9.4%) |
22 (7.6%) |
18 (6.6%) |
85 (8.3%) |
| Contract agent |
11 (5.9%) |
13 (4.7%) |
14 (4.8%) |
25 (9.1%) |
63 (6.1%) |
| Pensioner |
31 (16.5%) |
38 (13.8%) |
34 (11.7%) |
31 (11.3%) |
134 (13.0%) |
| Unemployed (inactive) |
24 (12.8%) |
34 (12.3%) |
42 (14.4%) |
39 (14.2%) |
139 (13.5%) |
| Self-employed |
14 (7.4%) |
21 (7.6%) |
27 (9.3%) |
20 (7.3%) |
82 (8.0%) |
| Total |
188 (100.0%) |
276 (100.0%) |
291 (100.0%) |
274 (100.0%) |
1029 (100.0%) |
Personal income
# Table with absolute frequencies
t1 <- WaveOne %>%
filter(rr=="Response") %>%
with(table(inc,Pumavers)) %>%
vcd::mar_table()
# Table with relative frequencies
t2 <- WaveOne %>%
filter(rr=="Response") %>%
with(table(inc,Pumavers)) %>%
cbind(rowSums(.)) %>%
prop.table(2) %>%
vcd::mar_table()
# Combine both tables
paste0(t1, " (", scales::percent(t2[,1:5], accuracy = 0.1), ")") %>%
matrix(ncol = 5) %>%
cbind(c(levels(WaveOne$inc),
"Total"
),.) %>%
as.data.frame() %>%
setNames(c("Answer",
"Brochure",
"2€ token",
"5€ token",
"Voucher",
"Total")) %>%
kable("html") %>%
kable_styling("striped") %>%
column_spec(1, width = "30em")
| Answer |
Brochure |
2€ token |
5€ token |
Voucher |
Total |
| up to 1.300€ |
43 (24.3%) |
68 (25.7%) |
65 (23.2%) |
64 (24.3%) |
240 (24.4%) |
| 1.301 to 2.500€ |
48 (27.1%) |
92 (34.7%) |
94 (33.6%) |
79 (30.0%) |
313 (31.8%) |
| 2.501 to 4.000€ |
52 (29.4%) |
59 (22.3%) |
82 (29.3%) |
69 (26.2%) |
262 (26.6%) |
| more than 4.000€ |
34 (19.2%) |
46 (17.4%) |
39 (13.9%) |
51 (19.4%) |
170 (17.3%) |
| Total |
177 (100.0%) |
265 (100.0%) |
280 (100.0%) |
263 (100.0%) |
985 (100.0%) |
Table summary
Line_s <- WaveOne %>%
filter(rr=="Response") %>%
dplyr::select(rr, Pumavers) %>%
table() %>%
cbind(rowSums(.))
line_sf <- WaveOne %>%
filter(is.na(PUMA1)==FALSE) %>%
dplyr::select(Pumavers) %>%
table() %>%
c(sum(.))
# Combine both tables
paste0(t1, " (", scales::percent(t2[,1:5], accuracy = 0.1), ")") %>%
matrix(ncol = 5) %>%
cbind(c(levels(WaveOne$inc),
"Total"
),.) %>%
as.data.frame() %>%
setNames(c("Answer",
"Brochure",
"2€ token",
"5€ token",
"Voucher",
"Total")) %>%
kable("html") %>%
kable_styling("striped") %>%
column_spec(1, width = "30em")
| |
Brochure |
2€ token |
5€ token |
Voucher |
Total |
| Sample |
188 |
276 |
291 |
274 |
1029 |
| Sampling frame |
1120 |
1063 |
1064 |
1043 |
4290 |
| Response rate |
16.8% |
26.0% |
27.3% |
26.3% |
24.0% |