packages <- c( "tidyverse", "readxl", "xlsx", "haven", "labelled", "tidyr", "knitr", "kableExtra", "dplyr", "openxlsx")
installed <- packages %in% rownames(installed.packages())
if (any(!installed)) install.packages(packages[!installed])Internet Access Locations
This page guides you through the harmonisation process of the Internet Access Locations item.
The item was administered in EB 2001 and ESS 2020. Before we start harmonising, please download these data sets from the respective repositories. You can find links to the survey repositories on the Make It Digital! data documentation page, in the section devoted to Internet Access Locations. If you click on the single year, the link takes you to the specific data set. We are working with the .sav format. So please make sure to download the datasets in this format.
Set-up
Please download the statistical software R (R Core Team, 2024) and RStudio (RStudio Team, 2023). Then start a project in RStudio by clicking File > New Project and set up a new directory or assign your project to an existing directory (i.e., folder). Within the project directory, create a folder called “data”. Now save the downloaded ESS and EB survey data into this “data” folder. Lastly, please download the following packages using the install.packages() function if they have not been installed before.
Every package installed in R must also be loaded. This is what the library-function is for.
library(tidyverse)
library(readxl)
library(openxlsx) # If you have problems installing or loading the xlsx-package, use the openxlsx.
library(haven)
library(labelled)
library(tidyr)
library(knitr)
library(kableExtra)
library(dplyr)An important step during the harmonisation process is to prepare the source data sets in a consistent and systematic way. For that, the functions “codebook” (create_codebook_short()) and ”crosswalk table” (create_cwt()) by Kołczyńska (2022) are used. They show the correspondence between source data sets and harmonised data regarding variable names and values. These functions are adopted into our needs and the R file containing them can be downloaded here . Please save this file in the R project folder and import it into the R project via source("kolczynska2022_i4ng.R").
If you can not download the R-file and if it is opened in a new tab, please open a new file in your R-Studio project under File -> New File -> R Script and copy the text from the kolczynska2022-file into this new file. Make sure that you save this new file in your project folder under the name “kolczynska2022_i4ng.R”.
source("kolczynska2022_i4ng.R")Now we can name our target variable as “d_iu_acce”. The name is a combination of “d” representing the main topic “Digital”, the concept “Internet Usage” and the variable label “Internet Access Locations”.
target_var_hrms <- "d_iu_acce"Both the ESS and EB items are “Tick all that apply” questions. This required harmonisation to be implemented at the data import, rather than in a later harmonisation step. Each response category is transformed into a separate dichotomous variable coded 1 = Marked and 0 = Not marked. The harmonised response categories are: (01) At home, (02) At my workplace, (03) On the move, (04) At some other place (such as a café or a friend’s house), and (05) NA.
1. Prepare Data: EB 2001
Six steps must be carried out in the following coding section:
1.1 Import data
Separate dichotomous variables are created for each of the harmonised response categories. The categories At home (“Q49 INTERNET USE: AT HOME”) and At work (“Q49 INTERNET USE: AT WORK”) are taken directly from the original variables. A combined category, On the move, is created by merging the categories “Q49 INTERNET USE: FROM LAPTOP”, “Q49 INTERNET USE: FROM POCKET COMPUTER”, and “Q49 INTERNET USE: FROM MOBILE PHONE”, coded as 1 if at least one is selected. Another combined category, Other place, is created by merging “Q49 INTERNET USE: AT SCHOOL UNIVERSITY”, “Q49 INTERNET USE: PUBLIC ACCESS POINT”, “Q49 INTERNET USE: IN A CYBERCAFE”, “Q49 INTERNET USE: IN OTHER’S HOUSE”, and “Q49 INTERNET USE: ELSEWHERE”, coded as 1 if at least one is selected. The DK category (“Q49 INTERNET USE: DK”) is retained as a separate variable.
eb <- haven::read_sav("data/ZA3627_v1-0-1.sav", user_na=TRUE) %>%
mutate(d_iu_acce_home = v308,
d_iu_acce_home = labelled_spss(d_iu_acce_home, label = "At home"),
d_iu_acce_work = v309,
d_iu_acce_work = labelled_spss(d_iu_acce_work, label = "At work"),
move = rowSums(across(c(v314, v315, v316), ~.)), # laptop, pocket comp, mobile phone
d_iu_acce_move = ifelse(move >= 1, 1, 0),
d_iu_acce_move = labelled_spss(d_iu_acce_move, label = "On the move"),
othr = rowSums(across(c(v310, v311, v312, v313, v317), ~.)),
d_iu_acce_othr = ifelse(othr >= 1, 1, 0),
d_iu_acce_othr = labelled_spss(d_iu_acce_othr, label = "Other place"),
d_iu_acce_na = v319,
d_iu_acce_na = labelled_spss(d_iu_acce_na, label = "DK"))The following codes can be used to check:
# check labels
sapply(eb %>% select(starts_with("d_iu_acce")), var_label)
# checks
eb %>% count(v308, d_iu_acce_home)
eb %>% count(v309, d_iu_acce_work)
eb %>% count(v314, v315, v316, move, d_iu_acce_move)
print(eb %>% count(v310, v311, v312, v313, v317, othr, d_iu_acce_othr), n=30)
eb %>% count(v319, d_iu_acce_na)1.2. Create codebook
Not just the substantive variables but also protocol variables need to be selected from this data set. Protocol variables selected for this harmonisation are the source data’s country, weight, and ID variables. In this step, we create a codebook that provides an overview of the selected variables and their naming in the harmonised data.
codebook_eb <- create_codebook_short(eb %>% select(-move, -othr)) %>%
mutate(survey = "EB",
target_var = ifelse(var_source == "isocntry", "country_source", NA),
target_var = ifelse(var_source == "v11", "w_poststr", target_var),
target_var = ifelse(grepl("ORIGINAL RESPONDENT", var_label_source, perl = TRUE), "caseID_source", target_var),
target_var = ifelse(grepl("Q49 INTERNET USE:", var_label_source), var_source, target_var),
target_var = ifelse(grepl("d_iu_acce", var_source), var_source, target_var),
target_var = gsub(" ", "_", target_var),
target_var = tolower(target_var))codebook_eb includes the columns called: var_source, var_label_source, survey, target_var.
1.3. Retrieve names of the chosen source variables
variables <- codebook_eb %>% drop_na(target_var) %>% pull(var_source)The retrieved variables are: isocntry, v11, v308, v309, v310, v311, v312, v313, v314, v315, v316, v317, v318, v319, v476, d_iu_acce_home, d_iu_acce_work, d_iu_acce_move, d_iu_acce_othr, d_iu_acce_na.
1.4. Select a subset of the survey data containing only the chosen variables
eb_small <- eb %>% select(all_of(variables)) %>% mutate(caseid = row_number())You will see that the following data set is a subset of the EB 2001 including the chosen variables for the harmonised data. The first six rows of the dataset are as follows:
| isocntry | v11 | v308 | v309 | v310 | v311 | v312 | v313 | v314 | v315 | v316 | v317 | v318 | v319 | v476 | d_iu_acce_home | d_iu_acce_work | d_iu_acce_move | d_iu_acce_othr | d_iu_acce_na | caseid |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| BE | 1.0472 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 10001 | 0 | 0 | 0 | 0 | 0 | 1 |
| BE | 1.0220 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 10002 | 0 | 0 | 0 | 0 | 0 | 2 |
| BE | 1.0472 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 10003 | 0 | 0 | 0 | 0 | 0 | 3 |
| BE | 0.8740 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 10004 | 0 | 0 | 0 | 1 | 0 | 4 |
| BE | 0.9289 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 10005 | 0 | 1 | 0 | 0 | 0 | 5 |
| BE | 0.8740 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 10006 | 1 | 0 | 1 | 0 | 0 | 6 |
1.5. Create a crosswalk table for the chosen variables
A crosswalk table provides a connection between the source variable values and the target variable values. First, it provides the variables, their labels, and the possible values. Then, the information is linked with the codebook information of the newly specified target variables. Lastly, target values are defined in a variable called target_value.
Here, weight and ID variables are excluded from the crosswalk table. Original codes for the country variable are preserved.
eb_cwt <- create_cwt(eb_small %>% select(isocntry, starts_with("d_iu_acce"))) %>%
left_join(codebook_eb, by = join_by(var_label_source, var_source)) %>%
mutate(target_value = NA,
target_value = value_code,
value_code = as.character(value_code))The utility of creating a crosswalk table is that the results of these decisions can be seen explicitly by comparing the value_code and target_value columns.
In this case, however, since the EB item is a “Tick all that apply” question, the harmonisation was implemented already during data import and variable construction. Therefore, no additional recoding is performed at the crosswalk table stage for this item. The crosswalk structure is still retained for consistency with the overall harmonisation workflow applied to other items, even though its added value is limited here.
Let’s look at the d_iu_acce items:
eb_cwt %>% filter(!(var_source == "isocntry")) %>%
kable(row.names = FALSE) %>%
kable_styling(full_width = FALSE, bootstrap_options = c("striped", "hover"))| var_source | var_label_source | npos | value_n | value_label_source | value_code | survey | target_var | target_value |
|---|---|---|---|---|---|---|---|---|
| d_iu_acce_home | At home | 1 | [0] 0: 11375 | [0] 0 | 0 | EB | d_iu_acce_home | 0 |
| d_iu_acce_home | At home | 2 | [1] 1: 4564 | [1] 1 | 1 | EB | d_iu_acce_home | 1 |
| d_iu_acce_work | At work | 1 | [0] 0: 13319 | [0] 0 | 0 | EB | d_iu_acce_work | 0 |
| d_iu_acce_work | At work | 2 | [1] 1: 2620 | [1] 1 | 1 | EB | d_iu_acce_work | 1 |
| d_iu_acce_move | On the move | 1 | [0] 0: 15647 | [0] 0 | 0 | EB | d_iu_acce_move | 0 |
| d_iu_acce_move | On the move | 2 | [1] 1: 292 | [1] 1 | 1 | EB | d_iu_acce_move | 1 |
| d_iu_acce_othr | Other place | 1 | [0] 0: 13782 | [0] 0 | 0 | EB | d_iu_acce_othr | 0 |
| d_iu_acce_othr | Other place | 2 | [1] 1: 2157 | [1] 1 | 1 | EB | d_iu_acce_othr | 1 |
| d_iu_acce_na | DK | 1 | [0] 0: 15786 | [0] 0 | 0 | EB | d_iu_acce_na | 0 |
| d_iu_acce_na | DK | 2 | [1] 1: 153 | [1] 1 | 1 | EB | d_iu_acce_na | 1 |
1.6. Recode survey data using the crosswalk table
To be able to merge survey data with the crosswalk table information, we first need to convert the wide data format to a long data format.
eb_small_long <- eb_small %>%
mutate(across(everything(), as.character)) %>%
pivot_longer(cols = c(starts_with("d_iu_acce"), isocntry),
names_to = "var_source", values_to = "value_source")This is how the first six rows of the eb_small_long should look like:
| v11 | v308 | v309 | v310 | v311 | v312 | v313 | v314 | v315 | v316 | v317 | v318 | v319 | v476 | caseid | var_source | value_source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1.0472 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 10001 | 1 | d_iu_acce_home | 0 |
| 1.0472 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 10001 | 1 | d_iu_acce_work | 0 |
| 1.0472 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 10001 | 1 | d_iu_acce_move | 0 |
| 1.0472 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 10001 | 1 | d_iu_acce_othr | 0 |
| 1.0472 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 10001 | 1 | d_iu_acce_na | 0 |
| 1.0472 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 10001 | 1 | isocntry | BE |
Now we use left_join() to recode source values according to the crosswalk table, eb_cwt.
eb_hrmsd <- eb_small_long %>%
left_join(eb_cwt, by = c("value_source" = "value_code", "var_source")) %>%
select(-c(npos, value_n)) %>%
mutate(target_value = as.character(target_value)) %>%
pivot_wider(
id_cols = c(v476, v11, v308:v319, survey, caseid), # Columns to keep as unique identifiers
names_from = target_var, # Column that will become the new column names
values_from = target_value # Column containing the values for those new columns
) %>% pivot_longer(
cols = starts_with("d_iu_acce"),
names_to = "target_var", values_to = "target_value") %>%
rename(caseID_source = v476)Now, EB 2001 data is ready for harmonisation. This is how the first six rows of the eb_hrmsd should look like:
| caseID_source | v11 | v308 | v309 | v310 | v311 | v312 | v313 | v314 | v315 | v316 | v317 | v318 | v319 | survey | caseid | country_source | target_var | target_value |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 10001 | 1.0472 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | EB | 1 | BE | d_iu_acce_home | 0 |
| 10001 | 1.0472 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | EB | 1 | BE | d_iu_acce_work | 0 |
| 10001 | 1.0472 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | EB | 1 | BE | d_iu_acce_move | 0 |
| 10001 | 1.0472 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | EB | 1 | BE | d_iu_acce_othr | 0 |
| 10001 | 1.0472 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | EB | 1 | BE | d_iu_acce_na | 0 |
| 10002 | 1.022 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | EB | 2 | BE | d_iu_acce_home | 0 |
At this step, the prepared data can be exported as an Rdata file and saved for later re-use. This data includes both the source variables and target variables. Users might benefit from the inclusion of both source and target variables.
saveRDS(eb_hrmsd, paste("data/", target_var_hrms, "_eb.rds", sep = ''))
2. Prepare Data: ESS 2020
We will follow the same steps used for the EB 2001 item.
2.1. Import data
ess <- haven::read_sav("data/ESS10.sav", user_na=TRUE) Use the output to inspect individual source variables such as acchome. The same check can be applied to other variables, including accwrk, accmove, accoth, accnone, accref, accdk, and accna:
ess %>% count(acchome)# A tibble: 2 × 2
acchome n
<dbl+lbl> <int>
1 0 [Not marked] 5677
2 1 [Marked] 31934
ess <- ess %>%
mutate(d_iu_acce_na = ifelse(rowSums(across(c(accnone, accref, accdk, accna), ~.)) == 0,
0, #0: not marked, 1: marked
1),
d_iu_acce_na = labelled_spss(d_iu_acce_na, label = "d_iu_acce harmonised NA"))The variable d_iu_acce_na is a harmonised indicator capturing whether any non-response or non-substantive categories are selected in the original ESS item. It is constructed from four source variables: accnone (“Location able to access the internet: None of the above”), accref (“Refusal”), accdk (“Don’t know”), and accna (“No answer”). The variable is coded as 0 = not marked when none of these categories is selected, and 1 = marked when at least one of them is selected. Please note that EB does not include a category equivalent to “None of the above.” For this reason, accnone is included in the d_iu_acce_na category.
2.2. Create codebook
Protocol variables selected for this harmonisation are the source data’s country, weight, and ID variables. Note that there are two weight variables: design and post-stratification weights. Both of them are included.
codebook_ess <- create_codebook_short(ess) %>%
mutate(survey = "ESS",
target_var = ifelse(var_source == "cntry", "country_source", NA),
target_var = ifelse(grepl("Design weight", var_label_source), "w1_design", target_var),
target_var = ifelse(grepl("Post-stratification weight", var_label_source), "w2_poststr", target_var),
target_var = ifelse(grepl("unified respondent number|Respondent's identification number|respondent ID", var_label_source, perl = TRUE), "caseID_source", target_var),
target_var = ifelse(var_source == "acchome", "d_iu_acce_home", target_var),
target_var = ifelse(var_source == "accwrk", "d_iu_acce_work", target_var),
target_var = ifelse(var_source == "accmove", "d_iu_acce_move", target_var),
target_var = ifelse(var_source == "accoth", "d_iu_acce_othr", target_var),
target_var = ifelse(var_source == "d_iu_acce_na", var_source, target_var),
target_var = gsub(" ", "_", target_var),
target_var = tolower(target_var))The variable names which will be used in the harmonised data are listed under target_var.
| var_source | var_label_source | survey | target_var |
|---|---|---|---|
| idno | Respondent's identification number | ESS | caseid_source |
| cntry | Country | ESS | country_source |
| dweight | Design weight | ESS | w1_design |
| pspwght | Post-stratification weight including design weight | ESS | w2_poststr |
| acchome | Location able to access the internet: Home | ESS | d_iu_acce_home |
| accwrk | Location able to access the internet: Workplace | ESS | d_iu_acce_work |
| accmove | Location able to access the internet: On the move | ESS | d_iu_acce_move |
| accoth | Location able to access the internet: Some other place | ESS | d_iu_acce_othr |
| d_iu_acce_na | d_iu_acce harmonised NA | ESS | d_iu_acce_na |
2.3. Retrieve names of the chosen source variables
variables <- codebook_ess %>% drop_na(target_var) %>% pull(var_source)The retrieved variables are: idno, cntry, dweight, pspwght, acchome, accwrk, accmove, accoth, d_iu_acce_na.
2.4. Select a subset of the survey data containing only the chosen variables
ess_small <- ess %>% select(all_of(variables)) %>% mutate(caseid = row_number())You will see that the following data set is a subset of the ESS 2020 with the chosen variables for the harmonised data. The first six rows of the dataset are as follows:
| idno | cntry | dweight | pspwght | acchome | accwrk | accmove | accoth | d_iu_acce_na | caseid |
|---|---|---|---|---|---|---|---|---|---|
| 10038 | BE | 0.8822203 | 0.9722756 | 1 | 0 | 1 | 1 | 0 | 1 |
| 10053 | BE | 1.0476425 | 0.8886350 | 1 | 0 | 0 | 1 | 0 | 2 |
| 10055 | BE | 1.0877413 | 0.7228110 | 1 | 0 | 0 | 1 | 0 | 3 |
| 10062 | BE | 0.9099100 | 1.0055653 | 0 | 1 | 0 | 0 | 0 | 4 |
| 10064 | BE | 0.9189489 | 0.6387054 | 1 | 1 | 1 | 1 | 0 | 5 |
| 10077 | BE | 0.9137402 | 0.7061659 | 1 | 1 | 1 | 0 | 0 | 6 |
2.5. Create a crosswalk table for the chosen variables
Similar to what is implemented in step 1.5, weight and ID variables are excluded from the crosswalk table. Only country and the substantive variable are used for creating the crosswalk table. Original codes for the country variable are preserved.
ess_cwt <- create_cwt(ess_small %>% select(cntry, starts_with("acc"), d_iu_acce_na)) %>%
left_join(codebook_ess, by = join_by(var_source, var_label_source)) %>%
mutate(target_value = NA,
target_value = value_code,
value_code = as.character(value_code)
)Although no recoding is done at this stage, the crosswalk table is still generated in order to maintain consistency with the established harmonisation workflow and to assign the target variable names.
Let’s look at the ess_cwt:
ess_cwt %>% filter(! var_source == "cntry") %>%
kable(row.names = FALSE) %>%
kable_styling(full_width = FALSE, bootstrap_options = c("striped", "hover"))| var_source | var_label_source | npos | value_n | value_label_source | value_code | survey | target_var | target_value |
|---|---|---|---|---|---|---|---|---|
| acchome | Location able to access the internet: Home | 1 | [0] Not marked: 5677 | [0] Not marked | 0 | ESS | d_iu_acce_home | 0 |
| acchome | Location able to access the internet: Home | 2 | [1] Marked: 31934 | [1] Marked | 1 | ESS | d_iu_acce_home | 1 |
| accwrk | Location able to access the internet: Workplace | 1 | [0] Not marked: 20717 | [0] Not marked | 0 | ESS | d_iu_acce_work | 0 |
| accwrk | Location able to access the internet: Workplace | 2 | [1] Marked: 16894 | [1] Marked | 1 | ESS | d_iu_acce_work | 1 |
| accmove | Location able to access the internet: On the move | 1 | [0] Not marked: 17078 | [0] Not marked | 0 | ESS | d_iu_acce_move | 0 |
| accmove | Location able to access the internet: On the move | 2 | [1] Marked: 20533 | [1] Marked | 1 | ESS | d_iu_acce_move | 1 |
| accoth | Location able to access the internet: Some other place | 1 | [0] Not marked: 19578 | [0] Not marked | 0 | ESS | d_iu_acce_othr | 0 |
| accoth | Location able to access the internet: Some other place | 2 | [1] Marked: 18033 | [1] Marked | 1 | ESS | d_iu_acce_othr | 1 |
| d_iu_acce_na | d_iu_acce harmonised NA | 1 | [0] 0: 32962 | [0] 0 | 0 | ESS | d_iu_acce_na | 0 |
| d_iu_acce_na | d_iu_acce harmonised NA | 2 | [1] 1: 4649 | [1] 1 | 1 | ESS | d_iu_acce_na | 1 |
It might be useful to export the crosswalk table as a spreadsheet since it serves as a reference document that visualises the connection between the source and harmonised data set.
write.xlsx(ess_cwt, paste("data/", target_var_hrms, "_cwt_ess.xlsx", sep = ''))
2.6. Recode survey data using the crosswalk table
We first convert the wide data format to a long data format, and then merge survey data with the crosswalk table information.
ess_small_long <- ess_small %>%
mutate(across(everything(), as.character)) %>%
pivot_longer(cols = c(d_iu_acce_na, acchome, accwrk, accmove, accoth, cntry),
names_to = "var_source", values_to = "value_source")This is how the first six rows of the ess_small_long should look like:
| idno | dweight | pspwght | caseid | var_source | value_source |
|---|---|---|---|---|---|
| 10038 | 0.882220268249512 | 0.97227555513382 | 1 | d_iu_acce_na | 0 |
| 10038 | 0.882220268249512 | 0.97227555513382 | 1 | acchome | 1 |
| 10038 | 0.882220268249512 | 0.97227555513382 | 1 | accwrk | 0 |
| 10038 | 0.882220268249512 | 0.97227555513382 | 1 | accmove | 1 |
| 10038 | 0.882220268249512 | 0.97227555513382 | 1 | accoth | 1 |
| 10038 | 0.882220268249512 | 0.97227555513382 | 1 | cntry | BE |
Now we use left_join() to recode source values according to the crosswalk table, ess_cwt.
ess_hrmsd <- ess_small_long %>%
left_join(ess_cwt, by = c("value_source" = "value_code", "var_source")) %>%
select(-c(npos, value_n)) %>%
mutate(target_value = as.character(target_value)) %>%
pivot_wider(
id_cols = c(dweight, pspwght, idno, caseid, survey), # Columns to keep as unique identifiers
names_from = target_var, # Column that will become the new column names
values_from = target_value # Column containing the values for those new columns
) %>% pivot_longer(
cols = starts_with("d_iu_acce"),
names_to = "target_var", values_to = "target_value") %>%
rename(caseID_source = idno) ESS 2020 data is ready for harmonisation. This is how the first six rows of the ess_hrmsd should look like:
head(ess_hrmsd) %>%
kable(row.names = FALSE) %>%
kable_styling(full_width = FALSE, bootstrap_options = c("striped", "hover"))| dweight | pspwght | caseID_source | caseid | survey | country_source | target_var | target_value |
|---|---|---|---|---|---|---|---|
| 0.882220268249512 | 0.97227555513382 | 10038 | 1 | ESS | BE | d_iu_acce_na | 0 |
| 0.882220268249512 | 0.97227555513382 | 10038 | 1 | ESS | BE | d_iu_acce_home | 1 |
| 0.882220268249512 | 0.97227555513382 | 10038 | 1 | ESS | BE | d_iu_acce_work | 0 |
| 0.882220268249512 | 0.97227555513382 | 10038 | 1 | ESS | BE | d_iu_acce_move | 1 |
| 0.882220268249512 | 0.97227555513382 | 10038 | 1 | ESS | BE | d_iu_acce_othr | 1 |
| 1.04764246940613 | 0.888634979724884 | 10053 | 2 | ESS | BE | d_iu_acce_na | 0 |
At this step, the prepared data can be exported as an Rdata file and saved for later re-use.
saveRDS(ess_hrmsd, paste("data/", target_var_hrms, "_ess.rds", sep = ''))
3. Harmonisation
With the following steps, we will create the harmonised Internet Access Locations data.
3.1. Standardise country names & apply labels
There are functions specifically written to standardise country names and apply labels. Please download the R file containing these functions here . Then save this file in the R project folder and import it into the R project via source("func_recoded_country.R").
If you cannot download the R-file, please open a new file in your R-Studio project under File -> New File -> R Script and copy the text from the func_recoded_country-file into this new file. Make sure that you save this new file in your project folder under the name “func_recoded_country.R”.
source("func_recoded_country.R")ess_1 <- ess_hrmsd %>%
recoded_country("country_source") %>%
country_new_labels("country_new") %>%
func_country_sample("country_source") %>%
country_source_recoded_labels("country_source_recoded")
eb_1 <- eb_hrmsd %>%
recoded_country("country_source") %>%
country_new_labels("country_new") %>%
func_country_sample("country_source") %>%
country_source_recoded_labels("country_source_recoded")You can run the following code to check the country variable:
table(eb_hrmsd$country_source, eb_1$country_new)
3.2. Weights
For details on decisions and procedures for including weight variables, please see the Make It Digital! data documentation page, section Weight Variables.
eb_fnl <- eb_1 %>% mutate(w1_design = v11,
w2_poststr = v11,
w3_combined = as.numeric(w2_poststr))
ess_fnl <- ess_1 %>% mutate(w1_design = dweight,
w2_poststr = pspwght,
w3_combined = as.numeric(w2_poststr))
3.3. Import additional information about the source data sets
This file, including additional information, can be downloaded here . Please save it into the “data” folder you generated previously.
add_data <- read_excel("data/from_doi_links_digital.xlsx") %>%
select(-studyno_source, -wave)
3.4. Combine all data
commons <- c("caseID_source", "caseid", "survey",
"target_var","target_value","year", "country_new", "country_source_recoded",
"w1_design", "w2_poststr", "w3_combined")
eb_fnl$year <- "2001"
ess_fnl$year <- "2020"
all_comb <- bind_rows(ess_fnl[, commons],
eb_fnl[, commons]) %>%
left_join(add_data, by = c("target_var", "survey", "year")) %>%
mutate(
## variables To Be Added
studyno_I4NG = NA,
version_I4NG = NA,
doi_I4NG = NA,
# caseID_I4NG = paste(survey, year, country_new, caseID_source, sep = ''),
caseID_I4NG = paste(survey, year, country_new, caseid, sep = ''),
#country_year
country_year = paste(country_new, year, sep = '_'),
# caseID = NA,
caseID = row_number(),
# code the lengths of response scales in each project
npoints = NA) %>%
rename(caseid_sw = caseid) # Rename to avoid SPSS duplicate name errorLet’s check the data set:
head(all_comb) %>%
kable(row.names = FALSE) %>%
kable_styling(full_width = FALSE, bootstrap_options = c("striped", "hover"))| caseID_source | caseid_sw | survey | target_var | target_value | year | country_new | country_source_recoded | w1_design | w2_poststr | w3_combined | title_source | doi_source | studyno_I4NG | version_I4NG | doi_I4NG | caseID_I4NG | country_year | caseID | npoints |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 10038 | 1 | ESS | d_iu_acce_na | 0 | 2020 | BE | BE | 0.882220268249512 | 0.97227555513382 | 0.9722756 | Democracy, Digital social contacts | https://doi.org/10.21338/ess10e03_2 | NA | NA | NA | ESS2020BE1 | BE_2020 | 1 | NA |
| 10038 | 1 | ESS | d_iu_acce_home | 1 | 2020 | BE | BE | 0.882220268249512 | 0.97227555513382 | 0.9722756 | Democracy, Digital social contacts | https://doi.org/10.21338/ess10e03_2 | NA | NA | NA | ESS2020BE1 | BE_2020 | 2 | NA |
| 10038 | 1 | ESS | d_iu_acce_work | 0 | 2020 | BE | BE | 0.882220268249512 | 0.97227555513382 | 0.9722756 | Democracy, Digital social contacts | https://doi.org/10.21338/ess10e03_2 | NA | NA | NA | ESS2020BE1 | BE_2020 | 3 | NA |
| 10038 | 1 | ESS | d_iu_acce_move | 1 | 2020 | BE | BE | 0.882220268249512 | 0.97227555513382 | 0.9722756 | Democracy, Digital social contacts | https://doi.org/10.21338/ess10e03_2 | NA | NA | NA | ESS2020BE1 | BE_2020 | 4 | NA |
| 10038 | 1 | ESS | d_iu_acce_othr | 1 | 2020 | BE | BE | 0.882220268249512 | 0.97227555513382 | 0.9722756 | Democracy, Digital social contacts | https://doi.org/10.21338/ess10e03_2 | NA | NA | NA | ESS2020BE1 | BE_2020 | 5 | NA |
| 10053 | 2 | ESS | d_iu_acce_na | 0 | 2020 | BE | BE | 1.04764246940613 | 0.888634979724884 | 0.8886350 | Democracy, Digital social contacts | https://doi.org/10.21338/ess10e03_2 | NA | NA | NA | ESS2020BE2 | BE_2020 | 6 | NA |
distinct(all_comb, target_var, survey, year)# A tibble: 10 × 3
target_var survey year
<chr> <chr> <chr>
1 d_iu_acce_na ESS 2020
2 d_iu_acce_home ESS 2020
3 d_iu_acce_work ESS 2020
4 d_iu_acce_move ESS 2020
5 d_iu_acce_othr ESS 2020
6 d_iu_acce_home EB 2001
7 d_iu_acce_work EB 2001
8 d_iu_acce_move EB 2001
9 d_iu_acce_othr EB 2001
10 d_iu_acce_na EB 2001
3.5. Apply transformation
Since the items are “Tick all that apply” questions, we implemented the recoding in steps 1.1 and 2.1 Therefore, in this step we do not perform any additional transformations or recoding. The procedure is limited to organising the variables and reshaping the data from long to wide format.
all_hrmsd <- all_comb %>%
mutate(value_hrmsd = as.numeric(target_value)) %>%
rename(var_hrmsd = target_var) %>%
select(-var_hrmsd, -value_hrmsd, var_hrmsd, value_hrmsd, -caseID, caseID, -ends_with("_source"), ends_with("_source"), -target_value, -npoints) %>% rename(country_I4NG = country_new)%>%
pivot_wider(
id_cols = c(doi_source, title_source, caseID_source, caseid_sw, survey, country_I4NG, country_source_recoded, year, country_year, w1_design, w2_poststr, w3_combined, caseID_I4NG),
names_from = var_hrmsd, # Column that will become the new column names
values_from = value_hrmsd # Column containing the values for those new columns
)Now the harmonised Internet Access Locations data are ready. This is how the first six rows of the all_hrmsd should look like:
| doi_source | title_source | caseID_source | caseid_sw | survey | country_I4NG | country_source_recoded | year | country_year | w1_design | w2_poststr | w3_combined | caseID_I4NG | d_iu_acce_na | d_iu_acce_home | d_iu_acce_work | d_iu_acce_move | d_iu_acce_othr |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| https://doi.org/10.21338/ess10e03_2 | Democracy, Digital social contacts | 10038 | 1 | ESS | BE | BE | 2020 | BE_2020 | 0.882220268249512 | 0.97227555513382 | 0.9722756 | ESS2020BE1 | 0 | 1 | 0 | 1 | 1 |
| https://doi.org/10.21338/ess10e03_2 | Democracy, Digital social contacts | 10053 | 2 | ESS | BE | BE | 2020 | BE_2020 | 1.04764246940613 | 0.888634979724884 | 0.8886350 | ESS2020BE2 | 0 | 1 | 0 | 0 | 1 |
| https://doi.org/10.21338/ess10e03_2 | Democracy, Digital social contacts | 10055 | 3 | ESS | BE | BE | 2020 | BE_2020 | 1.08774125576019 | 0.722811043262482 | 0.7228110 | ESS2020BE3 | 0 | 1 | 0 | 0 | 1 |
| https://doi.org/10.21338/ess10e03_2 | Democracy, Digital social contacts | 10062 | 4 | ESS | BE | BE | 2020 | BE_2020 | 0.909909963607788 | 1.00556528568268 | 1.0055653 | ESS2020BE4 | 0 | 0 | 1 | 0 | 0 |
| https://doi.org/10.21338/ess10e03_2 | Democracy, Digital social contacts | 10064 | 5 | ESS | BE | BE | 2020 | BE_2020 | 0.918948888778687 | 0.638705432415009 | 0.6387054 | ESS2020BE5 | 0 | 1 | 1 | 1 | 1 |
| https://doi.org/10.21338/ess10e03_2 | Democracy, Digital social contacts | 10077 | 6 | ESS | BE | BE | 2020 | BE_2020 | 0.913740217685699 | 0.706165909767151 | 0.7061659 | ESS2020BE6 | 0 | 1 | 1 | 1 | 0 |
3.6. Export data
#Rdata
saveRDS(all_hrmsd, paste("data/", target_var_hrms, "_hrmsd.rds", sep = ''))
#SPSS file
write_sav(all_hrmsd, paste("data/", target_var_hrms, "_hrmsd.sav", sep = ''))
#STATA file
write_dta(all_hrmsd, paste("data/", target_var_hrms, "_hrmsd.dta", sep = ''))
#CSV file
write.csv(all_hrmsd, paste("data/", target_var_hrms, "_hrmsd.csv", sep = ''), row.names = F, quote = T)
Summary
Internet Access Locations was administered in EB 2001 and ESS 2020. Our script, first, prepares these two data sets for harmonisation so that they are consistent in format via codebooks and crosswalk tables. After this step, the item is ready for subsequent analysis!
To go back to the Make it Digital! Toolbox page, please click here!