Exploring the Influence of Gender and Education on Perceptions and Priorities in Managing a Pandemic: A Study Using Italian Survey Data
Mingdi Zhou
2024-03-30
# List of packages
packages <- c("tidyverse", "infer", "fst", "modelsummary", "effects", "survey", "interactions", "kableExtra", "flextable") # add any you need here
# Install packages if they aren't installed already
new_packages <- packages[!(packages %in% installed.packages()[,"Package"])]
if(length(new_packages)) install.packages(new_packages)
# Load the packages
lapply(packages, library, character.only = TRUE)## Warning: package 'ggplot2' was built under R version 4.3.2## ── 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 3.4.4 ✔ tibble 3.2.1
## ✔ lubridate 1.9.2 ✔ tidyr 1.3.0
## ✔ 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 errors## Warning: package 'infer' was built under R version 4.3.2## Warning: package 'fst' was built under R version 4.3.3## Warning: package 'modelsummary' was built under R version 4.3.3## Version 2.0.0 of `modelsummary`, to be released soon, will introduce a
## breaking change: The default table-drawing package will be `tinytable`
## instead of `kableExtra`. All currently supported table-drawing packages
## will continue to be supported for the foreseeable future, including
## `kableExtra`, `gt`, `huxtable`, `flextable, and `DT`.
##
## You can always call the `config_modelsummary()` function to change the
## default table-drawing package in persistent fashion. To try `tinytable`
## now:
##
## config_modelsummary(factory_default = 'tinytable')
##
## To set the default back to `kableExtra`:
##
## config_modelsummary(factory_default = 'kableExtra')## Warning: package 'effects' was built under R version 4.3.2## Loading required package: carData
## lattice theme set by effectsTheme()
## See ?effectsTheme for details.## Warning: package 'survey' was built under R version 4.3.2## Loading required package: grid
## Loading required package: Matrix
##
## Attaching package: 'Matrix'
##
## The following objects are masked from 'package:tidyr':
##
## expand, pack, unpack
##
## Loading required package: survival## Warning: package 'survival' was built under R version 4.3.2##
## Attaching package: 'survey'
##
## The following object is masked from 'package:graphics':
##
## dotchart## Warning: package 'interactions' was built under R version 4.3.3##
## Attaching package: 'kableExtra'
##
## The following object is masked from 'package:dplyr':
##
## group_rows## Warning: package 'flextable' was built under R version 4.3.3##
## Attaching package: 'flextable'
##
## The following objects are masked from 'package:kableExtra':
##
## as_image, footnote
##
## The following object is masked from 'package:purrr':
##
## compose## [[1]]
## [1] "lubridate" "forcats" "stringr" "dplyr" "purrr" "readr"
## [7] "tidyr" "tibble" "ggplot2" "tidyverse" "stats" "graphics"
## [13] "grDevices" "utils" "datasets" "methods" "base"
##
## [[2]]
## [1] "infer" "lubridate" "forcats" "stringr" "dplyr" "purrr"
## [7] "readr" "tidyr" "tibble" "ggplot2" "tidyverse" "stats"
## [13] "graphics" "grDevices" "utils" "datasets" "methods" "base"
##
## [[3]]
## [1] "fst" "infer" "lubridate" "forcats" "stringr" "dplyr"
## [7] "purrr" "readr" "tidyr" "tibble" "ggplot2" "tidyverse"
## [13] "stats" "graphics" "grDevices" "utils" "datasets" "methods"
## [19] "base"
##
## [[4]]
## [1] "modelsummary" "fst" "infer" "lubridate" "forcats"
## [6] "stringr" "dplyr" "purrr" "readr" "tidyr"
## [11] "tibble" "ggplot2" "tidyverse" "stats" "graphics"
## [16] "grDevices" "utils" "datasets" "methods" "base"
##
## [[5]]
## [1] "effects" "carData" "modelsummary" "fst" "infer"
## [6] "lubridate" "forcats" "stringr" "dplyr" "purrr"
## [11] "readr" "tidyr" "tibble" "ggplot2" "tidyverse"
## [16] "stats" "graphics" "grDevices" "utils" "datasets"
## [21] "methods" "base"
##
## [[6]]
## [1] "survey" "survival" "Matrix" "grid" "effects"
## [6] "carData" "modelsummary" "fst" "infer" "lubridate"
## [11] "forcats" "stringr" "dplyr" "purrr" "readr"
## [16] "tidyr" "tibble" "ggplot2" "tidyverse" "stats"
## [21] "graphics" "grDevices" "utils" "datasets" "methods"
## [26] "base"
##
## [[7]]
## [1] "interactions" "survey" "survival" "Matrix" "grid"
## [6] "effects" "carData" "modelsummary" "fst" "infer"
## [11] "lubridate" "forcats" "stringr" "dplyr" "purrr"
## [16] "readr" "tidyr" "tibble" "ggplot2" "tidyverse"
## [21] "stats" "graphics" "grDevices" "utils" "datasets"
## [26] "methods" "base"
##
## [[8]]
## [1] "kableExtra" "interactions" "survey" "survival" "Matrix"
## [6] "grid" "effects" "carData" "modelsummary" "fst"
## [11] "infer" "lubridate" "forcats" "stringr" "dplyr"
## [16] "purrr" "readr" "tidyr" "tibble" "ggplot2"
## [21] "tidyverse" "stats" "graphics" "grDevices" "utils"
## [26] "datasets" "methods" "base"
##
## [[9]]
## [1] "flextable" "kableExtra" "interactions" "survey" "survival"
## [6] "Matrix" "grid" "effects" "carData" "modelsummary"
## [11] "fst" "infer" "lubridate" "forcats" "stringr"
## [16] "dplyr" "purrr" "readr" "tidyr" "tibble"
## [21] "ggplot2" "tidyverse" "stats" "graphics" "grDevices"
## [26] "utils" "datasets" "methods" "base"# Lets now set the working directory based on where we stored the data
setwd("C:/Users/Administrator/Desktop/Analysis")
getwd()## [1] "C:/Users/Administrator/Desktop/Analysis"# Let's now load the Italy Dataset to R:
italy <- read_fst("italy_data.fst")## Warning: package 'fstcore' was built under R version 4.3.3# Selecting specific variables
italy_selected <- italy %>%
select(gndr, essround, edulvla, edulvlb, panpriph, panmonpb, panfolru, panclobo, panresmo)
# Convert all variables to numeric
italy_selected <- italy_selected %>%
mutate(across(where(is.numeric), as.numeric))
# Setting values greater than 10 to NA
italy_selected$panpriph <- ifelse(italy_selected$panpriph > 10, NA, italy_selected$panpriph)
italy_selected$panmonpb <- ifelse(italy_selected$panmonpb > 10, NA, italy_selected$panmonpb)
italy_selected$panfolru <- ifelse(italy_selected$panfolru > 10, NA, italy_selected$panfolru)
italy_selected$panclobo <- ifelse(italy_selected$panclobo > 10, NA, italy_selected$panclobo)
italy_selected$panresmo <- ifelse(italy_selected$panresmo > 10, NA, italy_selected$panresmo)
# Creating and rescaling the trust variable
italy_selected$perceptions <- scales::rescale(italy_selected$panpriph + italy_selected$panmonpb + italy_selected$panfolru + italy_selected$panclobo + italy_selected$panresmo, na.rm = TRUE, to = c(0, 100))
italy_selected$misperception <- scales::rescale(italy_selected$perceptions, na.rm = TRUE, to=c(100,0))
ggplot(italy_selected, aes(x = misperception)) +
geom_histogram(bins = 30, fill = "blue", color = "black") +
theme_minimal() +
labs(title = "Distribution of Perception on Managing Pandemic Scale for Italy",
x = "Perception Scale",
y = "Count")## Warning: Removed 8958 rows containing non-finite values (`stat_bin()`).
It is clear that Italy exemplifies the right wing perception in managing the pandemic.
italy_selected <- italy_selected %>%
mutate(
ID = case_when(
perceptions <= 50 ~ "Left", # Categorize perceptions <= 50 as "Left"
perceptions > 50 ~ "Right", # Categorize perceptions > 50 as "Right"
TRUE ~ NA_character_ # Any other values not explicitly matched above
)
)
table(italy_selected$ID)##
## Left Right
## 669 551italy_pop_model <- lm(misperception ~ ID, data = italy_selected)
italy_pop_model##
## Call:
## lm(formula = misperception ~ ID, data = italy_selected)
##
## Coefficients:
## (Intercept) IDRight
## 61.24 -21.41Intercept (61.24):
- This value represents the average score on the perception scale for the reference group in Italy, which is the “Left” group. Clearly, the expected average perception scale score would be 61.24 for the left, since it is the reference category.
IDRight Coefficient (-21.41):
- The negative coefficient associated with the “Right” group indicates that, on average, individuals who identify as ideologically right in Italy have perception scale scores that are 21.41 points lower than those who identify as left.
Comparing right-leaning individuals to left-leaning ones in Italy, we expect to see the average perception scale score to be 21.41 points lower for the right-leaning group. This suggests that left-leaning individuals exhibit stronger perception attitudes than their right-leaning counterparts.
library(broom)## Registered S3 methods overwritten by 'broom':
## method from
## tidy.glht jtools
## tidy.summary.glht jtoolstidy(italy_pop_model)tidy(italy_pop_model) |>
knitr::kable(digits = 3)| term | estimate | std.error | statistic | p.value |
|---|---|---|---|---|
| (Intercept) | 61.241 | 0.315 | 194.119 | 0 |
| IDRight | -21.414 | 0.469 | -45.616 | 0 |
This coefficient is associated with an extremely low p-value, suggesting strong evidence against the null hypothesis that the intercept is zero. The p-value associated with IDRight is also extremely low, indicating strong evidence against the null hypothesis that the coefficient for IDRight is zero. These low p-values imply that both the intercept and IDRight are statistically significant predictors in the model, meaning they have a significant impact on the response variable.
summary(italy_pop_model)##
## Call:
## lm(formula = misperception ~ ID, data = italy_selected)
##
## Residuals:
## Min 1Q Median 3Q Max
## -39.827 -5.922 0.461 4.854 38.759
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 61.2410 0.3155 194.12 <2e-16 ***
## IDRight -21.4140 0.4694 -45.62 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 8.16 on 1218 degrees of freedom
## (8958 observations deleted due to missingness)
## Multiple R-squared: 0.6308, Adjusted R-squared: 0.6305
## F-statistic: 2081 on 1 and 1218 DF, p-value: < 2.2e-16# remotes::install_github("datalorax/equatiomatic")equatiomatic::extract_eq(italy_pop_model, use_coefs = TRUE)\[ \operatorname{\widehat{misperception}} = 61.24 - 21.41(\operatorname{ID}_{\operatorname{Right}}) \]
datasummary_skim(italy_selected, title = "Summary Statistics")| Unique | Missing Pct. | Mean | SD | Min | Median | Max | ||
|---|---|---|---|---|---|---|---|---|
| gndr | 3 | 0 | 1.5 | 0.6 | 1.0 | 2.0 | 9.0 | |
| essround | 5 | 0 | 7.8 | 2.7 | 1.0 | 9.0 | 10.0 | |
| edulvla | 6 | 88 | 2.5 | 2.7 | 1.0 | 2.0 | 88.0 | |
| edulvlb | 21 | 12 | 404.6 | 804.6 | 0.0 | 313.0 | 9999.0 | |
| panpriph | 12 | 87 | 3.9 | 2.5 | 0.0 | 4.0 | 10.0 | |
| panmonpb | 12 | 88 | 4.5 | 2.7 | 0.0 | 5.0 | 10.0 | |
| panfolru | 12 | 75 | 3.8 | 2.5 | 0.0 | 4.0 | 10.0 | |
| panclobo | 12 | 75 | 6.9 | 2.4 | 0.0 | 7.0 | 10.0 | |
| panresmo | 12 | 75 | 6.6 | 2.4 | 0.0 | 7.0 | 10.0 | |
| perceptions | 43 | 88 | 48.4 | 13.4 | 0.0 | 48.9 | 100.0 | |
| misperception | 43 | 88 | 51.6 | 13.4 | 0.0 | 51.1 | 100.0 |
# Recoding gender
italy_selected$gndr <- case_when(
italy_selected$gndr == 1 ~ "Male",
italy_selected$gndr == 2 ~ "Female",
italy_selected$gndr == 9 ~ NA_character_,
TRUE ~ as.character(italy_selected$gndr)
)
# Create the table with the table() function
table_data <- table(italy_selected$gndr)
# Convert the table to a data frame
table_df <- as.data.frame(table_data)
# Add a caption to the table using kable() function
table_kable <- kable(table_df, caption = "Table 1: Gender Distribution")
# Print the table
print(table_kable)## <table>
## <caption>Table 1: Gender Distribution</caption>
## <thead>
## <tr>
## <th style="text-align:left;"> Var1 </th>
## <th style="text-align:right;"> Freq </th>
## </tr>
## </thead>
## <tbody>
## <tr>
## <td style="text-align:left;"> Female </td>
## <td style="text-align:right;"> 5329 </td>
## </tr>
## <tr>
## <td style="text-align:left;"> Male </td>
## <td style="text-align:right;"> 4836 </td>
## </tr>
## </tbody>
## </table>The data presents the distribution of respondents by gender, indicating that there were 5,329 female respondents and 4,836 male respondents. This suggests that in the sample population, there were more female respondents than male respondents.
# Recoding education with case_when for consistency
italy_selected <- italy_selected %>%
mutate(
educ.ba = case_when(
essround < 5 & edulvla == 5 ~ "BA or more",
essround >= 5 & edulvlb > 600 ~ "BA or more",
TRUE ~ "No BA"
),
edulvla = ifelse(edulvla %in% c(77, 88), NA_integer_, edulvla),
edulvlb = ifelse(edulvlb %in% c(5555, 7777, 8888), NA_integer_, edulvlb),
educ.ba = as.character(educ.ba) # Force educ.ba to be treated as character
)
# Create the table with the table() function
table_data <- table(italy_selected$edulvla)
# Convert the table to a data frame
table_df <- as.data.frame(table_data)
# Add a title using add_header_above()
table_kable <- kable(table_df, caption = "Table 2: Education Levels") %>%
add_header_above(c("Education Level" = 2), align = "c")
# Print the table
print(table_kable)## <table>
## <caption>Table 2: Education Levels</caption>
## <thead>
## <tr><th style="border-bottom:hidden;padding-bottom:0; padding-left:3px;padding-right:3px;text-align: center; " colspan="2"><div style="border-bottom: 1px solid #ddd; padding-bottom: 5px; ">Education Level</div></th></tr>
## <tr>
## <th style="text-align:left;"> Var1 </th>
## <th style="text-align:right;"> Freq </th>
## </tr>
## </thead>
## <tbody>
## <tr>
## <td style="text-align:left;"> 1 </td>
## <td style="text-align:right;"> 283 </td>
## </tr>
## <tr>
## <td style="text-align:left;"> 2 </td>
## <td style="text-align:right;"> 394 </td>
## </tr>
## <tr>
## <td style="text-align:left;"> 3 </td>
## <td style="text-align:right;"> 415 </td>
## </tr>
## <tr>
## <td style="text-align:left;"> 5 </td>
## <td style="text-align:right;"> 114 </td>
## </tr>
## </tbody>
## </table># Recode variables with new interpretation
italy_selected <- italy_selected %>%
mutate(
panpriph = case_when(
panpriph == 0 ~ "Much more important to prioritise public health",
panpriph == 1 ~ "Slightly more important to prioritise public health",
panpriph == 2 ~ "Somewhat more important to prioritise public health",
panpriph == 3 ~ "Moderately more important to prioritise public health",
panpriph == 4 ~ "Slightly more important to prioritise economic activity",
panpriph == 5 ~ "Somewhat more important to prioritise economic activity",
panpriph == 6 ~ "Moderately more important to prioritise economic activity",
panpriph == 7 ~ "Much more important to prioritise economic activity",
panpriph == 8 ~ "Much more important to prioritise economic activity",
panpriph == 9 ~ "Much more important to prioritise economic activity",
panpriph == 10 ~ "Much more important to prioritise economic activity",
TRUE ~ NA_character_
),
panmonpb = case_when(
panmonpb == 0 ~ "Much more important to monitor and track the public",
panmonpb == 1 ~ "Slightly more important to monitor and track the public",
panmonpb == 2 ~ "Somewhat more important to monitor and track the public",
panmonpb == 3 ~ "Moderately more important to monitor and track the public",
panmonpb == 4 ~ "Slightly more important to maintain public privacy",
panmonpb == 5 ~ "Somewhat more important to maintain public privacy",
panmonpb == 6 ~ "Moderately more important to maintain public privacy",
panmonpb == 7 ~ "Much more important to maintain public privacy",
panmonpb == 8 ~ "Much more important to maintain public privacy",
panmonpb == 9 ~ "Much more important to maintain public privacy",
panmonpb == 10 ~ "Much more important to maintain public privacy",
TRUE ~ NA_character_
),
panfolru = case_when(
panfolru == 0 ~ "Much more important to follow government rules",
panfolru == 1 ~ "Slightly more important to follow government rules",
panfolru == 2 ~ "Somewhat more important to follow government rules",
panfolru == 3 ~ "Moderately more important to follow government rules",
panfolru == 4 ~ "Slightly more important to make own decisions",
panfolru == 5 ~ "Somewhat more important to make own decisions",
panfolru == 6 ~ "Moderately more important to make own decisions",
panfolru == 7 ~ "Much more important to make own decisions",
panfolru == 8 ~ "Much more important to make own decisions",
panfolru == 9 ~ "Much more important to make own decisions",
panfolru == 10 ~ "Much more important to make own decisions",
TRUE ~ NA_character_
),
panclobo = case_when(
panclobo == 0 ~ "Not at all important to close borders",
panclobo == 1 ~ "Slightly important to close borders",
panclobo == 2 ~ "Somewhat important to close borders",
panclobo == 3 ~ "Moderately important to close borders",
panclobo == 4 ~ "Very important to close borders",
panclobo == 5 ~ "Extremely important to close borders",
panclobo == 6 ~ "Extremely important to close borders",
panclobo == 7 ~ "Extremely important to close borders",
panclobo == 8 ~ "Extremely important to close borders",
panclobo == 9 ~ "Extremely important to close borders",
panclobo == 10 ~ "Extremely important to close borders",
TRUE ~ NA_character_
),
panresmo = case_when(
panresmo == 0 ~ "Not at all important to restrict movement",
panresmo == 1 ~ "Slightly important to restrict movement",
panresmo == 2 ~ "Somewhat important to restrict movement",
panresmo == 3 ~ "Moderately important to restrict movement",
panresmo == 4 ~ "Very important to restrict movement",
panresmo == 5 ~ "Extremely important to restrict movement",
panresmo == 6 ~ "Extremely important to restrict movement",
panresmo == 7 ~ "Extremely important to restrict movement",
panresmo == 8 ~ "Extremely important to restrict movement",
panresmo == 9 ~ "Extremely important to restrict movement",
panresmo == 10 ~ "Extremely important to restrict movement",
TRUE ~ NA_character_
)
)
datasummary_skim(italy_selected, type = "categorical", title = "Table 1: Summary of Categorical Variables")| N | % | ||
|---|---|---|---|
| gndr | Female | 5329 | 52.4 |
| Male | 4836 | 47.5 | |
| NA | 13 | 0.1 | |
| panpriph | Moderately more important to prioritise economic activity | 128 | 1.3 |
| Moderately more important to prioritise public health | 142 | 1.4 | |
| Much more important to prioritise economic activity | 189 | 1.9 | |
| Much more important to prioritise public health | 190 | 1.9 | |
| Slightly more important to prioritise economic activity | 143 | 1.4 | |
| Slightly more important to prioritise public health | 64 | 0.6 | |
| Somewhat more important to prioritise economic activity | 291 | 2.9 | |
| Somewhat more important to prioritise public health | 140 | 1.4 | |
| NA | 8891 | 87.4 | |
| panmonpb | Moderately more important to maintain public privacy | 117 | 1.1 |
| Moderately more important to monitor and track the public | 127 | 1.2 | |
| Much more important to maintain public privacy | 330 | 3.2 | |
| Much more important to monitor and track the public | 148 | 1.5 | |
| Slightly more important to maintain public privacy | 129 | 1.3 | |
| Slightly more important to monitor and track the public | 70 | 0.7 | |
| Somewhat more important to maintain public privacy | 234 | 2.3 | |
| Somewhat more important to monitor and track the public | 109 | 1.1 | |
| NA | 8914 | 87.6 | |
| panfolru | Moderately more important to follow government rules | 314 | 3.1 |
| Moderately more important to make own decisions | 291 | 2.9 | |
| Much more important to follow government rules | 371 | 3.6 | |
| Much more important to make own decisions | 369 | 3.6 | |
| Slightly more important to follow government rules | 166 | 1.6 | |
| Slightly more important to make own decisions | 305 | 3.0 | |
| Somewhat more important to follow government rules | 279 | 2.7 | |
| Somewhat more important to make own decisions | 494 | 4.9 | |
| NA | 7589 | 74.6 | |
| panclobo | Extremely important to close borders | 2181 | 21.4 |
| Moderately important to close borders | 122 | 1.2 | |
| Not at all important to close borders | 30 | 0.3 | |
| Slightly important to close borders | 20 | 0.2 | |
| Somewhat important to close borders | 66 | 0.6 | |
| Very important to close borders | 147 | 1.4 | |
| NA | 7612 | 74.8 | |
| panresmo | Extremely important to restrict movement | 2136 | 21.0 |
| Moderately important to restrict movement | 122 | 1.2 | |
| Not at all important to restrict movement | 42 | 0.4 | |
| Slightly important to restrict movement | 25 | 0.2 | |
| Somewhat important to restrict movement | 70 | 0.7 | |
| Very important to restrict movement | 176 | 1.7 | |
| NA | 7607 | 74.7 | |
| ID | Left | 669 | 6.6 |
| Right | 551 | 5.4 | |
| NA | 8958 | 88.0 | |
| educ.ba | BA or more | 1515 | 14.9 |
| No BA | 8663 | 85.1 |
Interpretation:
The summary of categorical variables in Table 1 provides insights into the distribution of responses among the surveyed individuals in Italy regarding various factors related to pandemic response. The table illustrates the gender distribution, with 52.4% of respondents identifying as female and 47.5% as male. Notably, the majority of respondents did not disclose their gender, constituting only 0.1% of the sample. Regarding the importance of prioritizing public health versus economic activity during a pandemic (panpriph), a substantial portion of respondents (87.4%) did not provide a definitive preference, resulting in a significant number of missing values. However, among those who did respond, the distribution was relatively balanced between prioritizing public health and economic activity, with a slight inclination toward the former. Similarly, opinions on government monitoring versus maintaining public privacy (panmonpb) exhibited a significant proportion of missing values (87.6%). Among respondents who provided a preference, there was a diverse range of opinions, although maintaining public privacy appeared to be slightly favored. Regarding personal decision-making versus following government rules (panfolru), the data again revealed a notable proportion of missing values (74.6%). Among respondents who expressed a preference, there was a relatively even split between those favoring government rules and those advocating for personal decision-making. In terms of the importance of closing borders (panclobo) and restricting movement (panresmo) during a pandemic, a substantial majority of respondents expressed high levels of concern, with a significant proportion considering these measures extremely important.
datasummary_skim(italy_selected, title = "Table 2: Summary Statistics")| Unique | Missing Pct. | Mean | SD | Min | Median | Max | ||
|---|---|---|---|---|---|---|---|---|
| essround | 5 | 0 | 7.8 | 2.7 | 1.0 | 9.0 | 10.0 | |
| edulvla | 5 | 88 | 2.4 | 1.1 | 1.0 | 2.0 | 5.0 | |
| edulvlb | 18 | 13 | 325.0 | 289.5 | 0.0 | 313.0 | 9999.0 | |
| perceptions | 43 | 88 | 48.4 | 13.4 | 0.0 | 48.9 | 100.0 | |
| misperception | 43 | 88 | 51.6 | 13.4 | 0.0 | 51.1 | 100.0 |
Interpretation:
The summary statistics presented in Table 2 provide an overview of key variables within the dataset, including the round of the European Social Survey (essround), educational level based on ISCED 1997 levels (edulvla), and educational level based on ISCED 2011 levels (edulvlb). For the essround variable, which denotes the round of the European Social Survey, the data encompass five unique values ranging from 1 to 10, indicating the survey rounds. There are no missing values for this variable. The mean round of the survey is approximately 7.8, with a standard deviation of 2.7. The minimum round is 1, while the maximum is 10, with a median value of 9. Regarding educational attainment based on ISCED 1997 levels (edulvla), there are five unique levels ranging from 1 to 5, representing different educational qualifications. However, there are 88 missing values for this variable. The mean educational level is approximately 2.4, with a standard deviation of 1.1. The minimum level is 1, indicating incomplete primary education, while the maximum level is 5, indicating tertiary education. The median educational level is 2.0. For educational attainment based on ISCED 2011 levels (edulvlb), there are 18 unique levels, but 13 missing values are present. The mean educational level is 325.0, with a standard deviation of 289.5. The minimum level is 0.0, while the maximum level is 9999.0, suggesting potential outliers or coding inconsistencies. The median educational level is 313.0.
# Crosstabulation and visualization for panpriph and gndr*educ.ba
datasummary_crosstab(panpriph ~ gndr*educ.ba, data = italy_selected, title = "Table 3: Crosstabulation of panpriph with gndr and educ.ba")| panpriph | BA or more | No BA | BA or more | No BA | All | |
|---|---|---|---|---|---|---|
| Moderately more important to prioritise economic activity | N | 10 | 44 | 13 | 61 | 128 |
| % row | 7.8 | 34.4 | 10.2 | 47.7 | 100.0 | |
| Moderately more important to prioritise public health | N | 18 | 52 | 11 | 61 | 142 |
| % row | 12.7 | 36.6 | 7.7 | 43.0 | 100.0 | |
| Much more important to prioritise economic activity | N | 10 | 80 | 20 | 79 | 189 |
| % row | 5.3 | 42.3 | 10.6 | 41.8 | 100.0 | |
| Much more important to prioritise public health | N | 19 | 89 | 12 | 70 | 190 |
| % row | 10.0 | 46.8 | 6.3 | 36.8 | 100.0 | |
| Slightly more important to prioritise economic activity | N | 15 | 60 | 10 | 58 | 143 |
| % row | 10.5 | 42.0 | 7.0 | 40.6 | 100.0 | |
| Slightly more important to prioritise public health | N | 10 | 24 | 5 | 25 | 64 |
| % row | 15.6 | 37.5 | 7.8 | 39.1 | 100.0 | |
| Somewhat more important to prioritise economic activity | N | 36 | 126 | 18 | 111 | 291 |
| % row | 12.4 | 43.3 | 6.2 | 38.1 | 100.0 | |
| Somewhat more important to prioritise public health | N | 14 | 66 | 13 | 47 | 140 |
| % row | 10.0 | 47.1 | 9.3 | 33.6 | 100.0 | |
| All | N | 780 | 4549 | 732 | 4104 | 10178 |
| % row | 7.7 | 44.7 | 7.2 | 40.3 | 100.0 |
Interpretation:
Table 3 illustrates the cross tabulation of responses to the variable “panpriph,” representing the perceived importance of prioritizing public health or economic activity during a pandemic, with gender (“gndr”) and educational attainment (“educ.ba”). Across the various combinations of gender and educational attainment, respondents expressed different preferences regarding pandemic response priorities. Notably, the majority of both males and females with and without a BA or more believed that prioritizing public health was “Moderately more important” or “Much more important” compared to economic activity. However, there were variations in response proportions across different demographic groups. For instance, among females with a BA or more, 34.4% indicated that prioritizing public health was “Moderately more important,” while only 10.2% believed the same among males with a BA or more. Conversely, a higher percentage of males without a BA considered prioritizing public health to be “Moderately more important” compared to females without a BA (47.7% vs. 7.8%, respectively).
# Crosstabulation and visualization for panmonpb and gndr*educ.ba
datasummary_crosstab(panmonpb ~ gndr*educ.ba, data = italy_selected, title = "Table 4: Crosstabulation of panmonpb with gndr and educ.ba")| panmonpb | BA or more | No BA | BA or more | No BA | All | |
|---|---|---|---|---|---|---|
| Moderately more important to maintain public privacy | N | 11 | 53 | 6 | 47 | 117 |
| % row | 9.4 | 45.3 | 5.1 | 40.2 | 100.0 | |
| Moderately more important to monitor and track the public | N | 13 | 56 | 6 | 52 | 127 |
| % row | 10.2 | 44.1 | 4.7 | 40.9 | 100.0 | |
| Much more important to maintain public privacy | N | 26 | 139 | 37 | 128 | 330 |
| % row | 7.9 | 42.1 | 11.2 | 38.8 | 100.0 | |
| Much more important to monitor and track the public | N | 15 | 64 | 9 | 60 | 148 |
| % row | 10.1 | 43.2 | 6.1 | 40.5 | 100.0 | |
| Slightly more important to maintain public privacy | N | 17 | 50 | 7 | 55 | 129 |
| % row | 13.2 | 38.8 | 5.4 | 42.6 | 100.0 | |
| Slightly more important to monitor and track the public | N | 10 | 32 | 8 | 20 | 70 |
| % row | 14.3 | 45.7 | 11.4 | 28.6 | 100.0 | |
| Somewhat more important to maintain public privacy | N | 20 | 89 | 20 | 105 | 234 |
| % row | 8.5 | 38.0 | 8.5 | 44.9 | 100.0 | |
| Somewhat more important to monitor and track the public | N | 19 | 41 | 9 | 40 | 109 |
| % row | 17.4 | 37.6 | 8.3 | 36.7 | 100.0 | |
| All | N | 780 | 4549 | 732 | 4104 | 10178 |
| % row | 7.7 | 44.7 | 7.2 | 40.3 | 100.0 |
Interpretation:
Table 4 presents the cross tabulation of responses to the variable “panmonpb,” reflecting the perceived importance of maintaining public privacy or monitoring and tracking the public during a pandemic, with gender (“gndr”) and educational attainment (“educ.ba”). The table reveals varying attitudes toward privacy and public monitoring across different demographic groups. Overall, respondents tended to express a higher preference for maintaining public privacy compared to monitoring and tracking the public. Among females with a BA or more, 45.3% believed that maintaining public privacy was “Moderately more important,” while only 5.1% of males with a BA or more shared this view. Conversely, a higher percentage of males without a BA considered maintaining public privacy to be “Moderately more important” compared to females without a BA (40.2% vs. 9.4%, respectively).
# Crosstabulation and visualization for panfolru and gndr*educ.ba
datasummary_crosstab(panfolru ~ gndr*educ.ba, data = italy_selected, title = "Table 5: Crosstabulation of panfolru with gndr and educ.ba")| panfolru | BA or more | No BA | BA or more | No BA | All | |
|---|---|---|---|---|---|---|
| Moderately more important to follow government rules | N | 31 | 139 | 27 | 117 | 314 |
| % row | 9.9 | 44.3 | 8.6 | 37.3 | 100.0 | |
| Moderately more important to make own decisions | N | 17 | 121 | 28 | 125 | 291 |
| % row | 5.8 | 41.6 | 9.6 | 43.0 | 100.0 | |
| Much more important to follow government rules | N | 40 | 157 | 30 | 144 | 371 |
| % row | 10.8 | 42.3 | 8.1 | 38.8 | 100.0 | |
| Much more important to make own decisions | N | 29 | 171 | 32 | 137 | 369 |
| % row | 7.9 | 46.3 | 8.7 | 37.1 | 100.0 | |
| Slightly more important to follow government rules | N | 25 | 65 | 19 | 57 | 166 |
| % row | 15.1 | 39.2 | 11.4 | 34.3 | 100.0 | |
| Slightly more important to make own decisions | N | 26 | 125 | 17 | 137 | 305 |
| % row | 8.5 | 41.0 | 5.6 | 44.9 | 100.0 | |
| Somewhat more important to follow government rules | N | 37 | 109 | 38 | 95 | 279 |
| % row | 13.3 | 39.1 | 13.6 | 34.1 | 100.0 | |
| Somewhat more important to make own decisions | N | 40 | 225 | 34 | 195 | 494 |
| % row | 8.1 | 45.5 | 6.9 | 39.5 | 100.0 | |
| All | N | 780 | 4549 | 732 | 4104 | 10178 |
| % row | 7.7 | 44.7 | 7.2 | 40.3 | 100.0 |
Interpretation:
Table 5 presents the cross tabulation of responses to the variable “panfolru,” which reflects preferences regarding following government rules or making personal decisions during a pandemic, with gender (“gndr”) and educational attainment (“educ.ba”). The table illustrates diverse attitudes toward government directives and personal decision-making across different demographic groups. Overall, respondents exhibited a preference for making their own decisions rather than strictly following government rules. Among females with a BA or more, 44.3% expressed a preference for making their own decisions, while only 9.9% believed it was “Moderately more important” to follow government rules. Similarly, among males without a BA, a higher percentage (43.0%) favored making their own decisions compared to following government rules (8.6%).
# Crosstabulation and visualization for panclobo and gndr*educ.ba
datasummary_crosstab(panclobo ~ gndr*educ.ba, data = italy_selected, title = "Table 6: Crosstabulation of panclobo with gndr and educ.ba")| panclobo | BA or more | No BA | BA or more | No BA | All | |
|---|---|---|---|---|---|---|
| Extremely important to close borders | N | 200 | 949 | 196 | 836 | 2181 |
| % row | 9.2 | 43.5 | 9.0 | 38.3 | 100.0 | |
| Moderately important to close borders | N | 13 | 42 | 7 | 60 | 122 |
| % row | 10.7 | 34.4 | 5.7 | 49.2 | 100.0 | |
| Not at all important to close borders | N | 3 | 12 | 4 | 11 | 30 |
| % row | 10.0 | 40.0 | 13.3 | 36.7 | 100.0 | |
| Slightly important to close borders | N | 1 | 7 | 1 | 11 | 20 |
| % row | 5.0 | 35.0 | 5.0 | 55.0 | 100.0 | |
| Somewhat important to close borders | N | 11 | 26 | 8 | 21 | 66 |
| % row | 16.7 | 39.4 | 12.1 | 31.8 | 100.0 | |
| Very important to close borders | N | 15 | 64 | 8 | 60 | 147 |
| % row | 10.2 | 43.5 | 5.4 | 40.8 | 100.0 | |
| All | N | 780 | 4549 | 732 | 4104 | 10178 |
| % row | 7.7 | 44.7 | 7.2 | 40.3 | 100.0 |
Interpretation:
Table 6 presents the cross tabulation of responses to the variable “panclobo,” which reflects attitudes toward closing borders during a pandemic, with gender (“gndr”) and educational attainment (“educ.ba”). The table demonstrates variations in opinions regarding the importance of closing borders across different demographic groups. Overall, a significant portion of respondents expressed extreme importance attached to closing borders, irrespective of gender or educational background. Among females with a BA or more, 43.5% considered it “Extremely important” to close borders, while among males without a BA, 38.3% held a similar view. Conversely, only a minority of respondents viewed closing borders as “Not at all important,” with 10.0% of females with a BA or more and 13.3% of males with a BA or more expressing this sentiment.
| panresmo | BA or more | No BA | BA or more | No BA | All | |
|---|---|---|---|---|---|---|
| Extremely important to restrict movement | N | 194 | 949 | 178 | 815 | 2136 |
| % row | 9.1 | 44.4 | 8.3 | 38.2 | 100.0 | |
| Moderately important to restrict movement | N | 12 | 46 | 11 | 53 | 122 |
| % row | 9.8 | 37.7 | 9.0 | 43.4 | 100.0 | |
| Not at all important to restrict movement | N | 4 | 13 | 11 | 14 | 42 |
| % row | 9.5 | 31.0 | 26.2 | 33.3 | 100.0 | |
| Slightly important to restrict movement | N | 4 | 8 | 2 | 11 | 25 |
| % row | 16.0 | 32.0 | 8.0 | 44.0 | 100.0 | |
| Somewhat important to restrict movement | N | 12 | 23 | 7 | 28 | 70 |
| % row | 17.1 | 32.9 | 10.0 | 40.0 | 100.0 | |
| Very important to restrict movement | N | 14 | 67 | 15 | 80 | 176 |
| % row | 8.0 | 38.1 | 8.5 | 45.5 | 100.0 | |
| All | N | 780 | 4549 | 732 | 4104 | 10178 |
| % row | 7.7 | 44.7 | 7.2 | 40.3 | 100.0 |
Interpretation:
Table 7 presents the crosstabulation of responses to the variable “panresmo,” reflecting attitudes toward restricting movement during a pandemic, with gender (“gndr”) and educational attainment (“educ.ba”). The table illustrates varying opinions regarding the importance of movement restrictions across different demographic groups. Overall, a substantial proportion of respondents expressed extreme importance attached to restricting movement, irrespective of gender or educational background. Among females with a BA or more, 44.4% considered it “Extremely important” to restrict movement, while among males without a BA, 38.2% held a similar view. Conversely, a minority of respondents viewed movement restrictions as “Not at all important,” with 31.0% of females with a BA or more and 26.2% of males with a BA or more expressing this sentiment.
# Chi-square test for panfolru and gndr
chisq.test(italy_selected$panfolru, italy_selected$gndr)##
## Pearson's Chi-squared test
##
## data: italy_selected$panfolru and italy_selected$gndr
## X-squared = 5.3731, df = 7, p-value = 0.6145chisq.test(italy_selected$panfolru, italy_selected$educ.ba)##
## Pearson's Chi-squared test
##
## data: italy_selected$panfolru and italy_selected$educ.ba
## X-squared = 31.043, df = 7, p-value = 6.105e-05# Chi-square test for panpriph and gndr and education level
chisq.test(italy_selected$panpriph, italy_selected$gndr)##
## Pearson's Chi-squared test
##
## data: italy_selected$panpriph and italy_selected$gndr
## X-squared = 11.651, df = 7, p-value = 0.1126chisq.test(italy_selected$panpriph, italy_selected$educ.ba)##
## Pearson's Chi-squared test
##
## data: italy_selected$panpriph and italy_selected$educ.ba
## X-squared = 2.9827, df = 7, p-value = 0.8866# Chi-square test for panmonpb and gndr and education level
chisq.test(italy_selected$panmonpb, italy_selected$gndr)##
## Pearson's Chi-squared test
##
## data: italy_selected$panmonpb and italy_selected$gndr
## X-squared = 6.1947, df = 7, p-value = 0.5172chisq.test(italy_selected$panmonpb, italy_selected$educ.ba)##
## Pearson's Chi-squared test
##
## data: italy_selected$panmonpb and italy_selected$educ.ba
## X-squared = 9.3483, df = 7, p-value = 0.2286# Chi-square test for panclobo and gndr and education level
chisq.test(italy_selected$panclobo, italy_selected$gndr)##
## Pearson's Chi-squared test
##
## data: italy_selected$panclobo and italy_selected$gndr
## X-squared = 4.4475, df = 5, p-value = 0.4869chisq.test(italy_selected$panclobo, italy_selected$educ.ba)## Warning in chisq.test(italy_selected$panclobo, italy_selected$educ.ba):
## Chi-squared approximation may be incorrect##
## Pearson's Chi-squared test
##
## data: italy_selected$panclobo and italy_selected$educ.ba
## X-squared = 7.3184, df = 5, p-value = 0.198# Chi-square test for panresmo and gndr and education level
chisq.test(italy_selected$panresmo, italy_selected$gndr)##
## Pearson's Chi-squared test
##
## data: italy_selected$panresmo and italy_selected$gndr
## X-squared = 7.8289, df = 5, p-value = 0.1659chisq.test(italy_selected$panresmo, italy_selected$educ.ba)## Warning in chisq.test(italy_selected$panresmo, italy_selected$educ.ba):
## Chi-squared approximation may be incorrect##
## Pearson's Chi-squared test
##
## data: italy_selected$panresmo and italy_selected$educ.ba
## X-squared = 14.301, df = 5, p-value = 0.01381Interpretation:
The results of Pearson’s Chi-squared tests examining the association between categorical variables are as follows. Firstly, no statistically significant association was found between attitudes toward government rules (“panfolru”) and gender (“gndr”), χ^2 (7)= 5.3731,p = 0.6145. However, a significant association was observed between attitudes toward government rules and educational attainment, χ²(7) = 31.043,p < .001. Similarly, no significant association was found between attitudes toward prioritizing public health/economic activity (“panpriph”) and gender, χ²(7) = 11.651,p = .1126, or educational attainment, χ²(7) = 2.9827,p = .8866. Moreover, no significant association emerged between attitudes toward monitoring and tracking the public (“panmonpb”) and gender, χ²(7) = 6.1947,p = .5172, or educational attainment, χ²(7) = 9.3483,p = .2286. Additionally, no significant association was found between attitudes toward closing borders (“panclobo”) and gender, χ²(5) = 4.4475,p = .4869, or educational attainment, χ²(5) = 7.3184,p = .198. However, a statistically significant association was observed between attitudes toward restricting movement (“panresmo”) and educational attainment, χ²(5) = 14.301,p = .01381, but not gender, χ²(5) = 7.8289,p = .1659. These results suggest that while educational attainment plays a role in shaping attitudes toward government rules and movement restriction, gender does not appear to significantly influence these perspectives.