Data for assigning a proxy variable for office worker in open-ended responses on occupation

These three datasets contain data and R code to assign a proxy variable for office worker, based on responses to an open-ended question (OEQ) about occupation in Swedish surveys. The R code and proxy variable can be applied to any dataset with Swedish OEQ about occupation; the R code is also adaptable for OEQ in any language, provided there is a standard classification of occupations in that language. The R code can be found in the dataset Assigning_office_worker_proxy.R, and the proxy variable in the dataset SSYK12_modified.xlsx (and SSYK12_modified.csv). The dataset Occupation_response.xlsx (and Occupation_response.csv) gives an example of what can be extracted from a Swedish questionnaire with an OEQ about occupation. The dataset can be replaced with optional data as long as it includes two variables named “ID” and “Occupation_swe” (i.e., occupation title given by respondent).