STATEC (Institut national de la statistique et des études économiques - Luxembourg).

Unit: SOC2 - Labour market and education

13 Rue Erasme, 1468 Luxembourg

The Adult Education Survey (AES) covers adults’ participation in education and training (formal - FED, non-formal - NFE and informal learning - INF). The 2022 AES focuses on people aged 18-69. The reference period for the participation in education and training is the twelve months prior to the interview.
Information available from the AES is grouped around the following topics:

• Participation in formal education, non-formal education and training and informal learning
• Volume of instruction hours
• Characteristics of the learning activities
• Reasons for participating
• Obstacles to participation
• Access to information on learning possibilities and guidance
• Employer financing and costs of learning
• Self-reported language skills

For further information see the 2022 AES legislation (http://ec.europa.eu/eurostat/web/education-and-training/legislation) and the 2022 AES implementation manual (http://ec.europa.eu/eurostat/web/education-and-training/methodology).

- Classification of Learning Activities (CLA, 2016 edition)
- International Standard Classification of Education 2011 (ISCED 2011)
- Classification of Occupations 2008 (ISCO 08)
- Classification of economic activities Rev. 2 (NACE Rev. 2)

AES covers all economic sectors.

Definitions as well as the list of variables covered are available in the 2022 AES implementation manual (http://ec.europa.eu/eurostat/web/education-and-training/methodology).

Individuals, non-formal learning activities.

Individuals aged 18-69 living in private households.

Luxembourg (country) (LU0).

Reference period: 12 months before the interview.

Fieldwork has taken place:

- AES2011-12: from 01/02/2012 to 30/06/2012

- AES2016-17: from 23/09/2016 to 31/03/2017

- AES2022-23: from 26/09/2022 to 28/02/2023

Not applicable.

Number, EUR.

Reference period: 12 months before the interview.

Fieldwork has taken place:

- AES2011-12: from 01/02/2012 to 30/06/2012

- AES2016-17: from 23/09/2016 to 31/03/2017

- AES2022-23: from 26/09/2022 to 28/02/2023

At European level:
Basic legal act: Regulation (EU) 2019/1700
Implementing act: Commission Implementing Regulation (EU) 2021/861

At national level:
/

Not applicable.

Eurostat's policy for dissemination will be followed.

Not applicable.

News releases linked to AES data will be made available on http://www.statistiques.public.lu/en/index.html as soon as possible.

No specific release calendar is applicable.

Not applicable.

News releases linked to AES data will be made available on http://www.statistiques.public.lu/en/index.html

Every 6 years.

News releases linked to AES data will be made available on http://www.statistiques.public.lu/en/index.html

Publications with analyses linked to AES data will be made available on http://www.statistiques.public.lu/en/index.html

Online tables of main AES data will be made available on http://www.statistiques.public.lu/en/index.html

Not applicable.

Not applicable.

Not applicable.

Not applicable.

Not applicable.

Not applicable.

Not applicable.

The AES has been conducted mainly using a web questionnaire (and incidentally on paper), so the respondent had to fill in the questionnaire on his own.

In order to guarantee the quality of the answers provided,

• clear definitions and examples had been provided in the online questionnaire
• collaborators of the national statistical office answered the questions of the respondents on the phone and by mail
• answers were crosschecked for inconsistencies and eventually discarded or corrected on a case-by-case basis.

Overall quality of the 2022-23 AES should be of good.

Strong points:

• The sample has been drawn on a random basis from the register.
• Response rate has been 60%.

Weak points:

• as the survey was based on a web questionnaire, there might be a slight bias as persons having low computer skills might have been negatively selected (although a paper version has been proposed too)
• the questionnaire was considered to be very long by respondents
• despite the effort we put into clarifying these questions and adopting a step-by-step-approach, many seem to have had difficulties with questions about HATLEVEL, JOBISCO and LOCNACE
• the difference between formal, non-formal and informal still seems to be very difficult to grasp for many respondents
• instruction hours and cost of activities also seem to be difficult for respondents; these variables should be used with caution
• as the survey was conducted using a web-based questionnaire, respondents may have encountered other problems without giving us any feedback

Main Users:

• Policy makers at European and national level
• Social actors, international organisations
• Media

Their main needs are

(X ) Access to information on learning possibilities and guidance
(X ) Participation in education and training by type, characteristics of the activity (field, distance learning, etc.)
(X ) Reason, use and outcomes of FED and NFE
(X ) Share of job-related or employer-sponsored NFE
(X ) Volume of instruction hours for FED and NFE
(X ) Cost of learning for NFE
(X ) Obstacles to participation in education and training
(X ) Self-reported language skills

There are no measures available at national level to analyse user satisfaction.

Data covers all requested variables as in the AES legislation.

Not applicable.

Overall accuracy should be good. Indicators for which a precision threshold is provided in the AES legislation are of good quality.

The sampling frame used for AES 2022 is the National Population Register (Répertoire National des Personnes Physiques).

The initial sample size was 8000 individuals, of which we received a final 4820 usable responses, which fulfils the precision requirements.

Respondents represent well the population in terms of sex, age and education level.

Overall accuracy should be good.

The sampling error for 2022 AES is considered fairly low.

See table 13.2.1 “Sampling errors - indicators for 2022 AES key statistics” in annex “LU - QR tables 2022 AES (excel)”.

Non-sampling errors are covered by items 13.3.1 - 13.3.5 below.

The sample was drawn from the population register on 29/08/2022.

See table 13.3.1.1 “Over-coverage - rate” in annex “LU - QR tables 2022 AES (excel)”.

Not applicable.

Measurement errors may occur if actual respondents do not correspond to the persons sampled. Birth dates and sex given in the questionnaire have been compared to information from the sampling frame in order to ensure that the right person has been responding, but we cannot guarantee that no person has filled in the questionnaire as a proxy for the person sampled, as the survey was conducted via a web questionnaire.

Other measurement errors may occur if questions or possible answers are not understood by the respondent. The questionnaire had been made available in the three national languages (French, German and Luxemburgish) as well as in English, and when deemed necessary, the questions from the Eurostat model questionnaire had been adapted to national circumstances in terminology and examples provided. Despite all these efforts, it cannot be ruled out that some respondents did not understand a question or the choice of answers provided. For difficult variables such as HATLEVEL, ISCO and NACE codes, respondents were asked to classify themselves in a list and in parallel to describe their diploma, occupation and sector of activity in writing. In many cases, we had to recode the variable because codes selected did not fit the description, which shows a lack of understanding of the respondent.

Unfortunately, due to budget constraints we did not have the means to run a test survey before the actual survey.

See items 13.3.3.1 - 13.3.3.2 below.

See table 13.3.3.1 “Unit non-response - rate” in annex “LU - QR tables 2022 AES (excel)”.

See table 13.3.3.2 “Item non-response rate” in annex “LU - QR tables 2022 AES (excel)”.

The data collection method was a web questionnaire. The web questionnaire included data filters and checks in order to minimize incoherence in data.

Some variables (HATLEVEL, LOCNACE and JOBISCO) were collected in parallel in two ways: respondents had to choose a value in a list and / or answer the question in an open text field. The variables were recoded afterwards on a case by case basis if the textual answers were not in line with the chosen value in the list or if only textual answers were given.

There has been no imputation of missing values except for some missing mother tongues, imputed on the basis of country of birth and country of birth of the parents.

Not applicable.

Reference period is the twelve months before the interview.

Interviews took place between 26/09/2022 and 28/02/2023.

Approximately 6 months.

4th quarter 2023

4th quarter 2023

See table 14.2 “Project phases - dates” in annex “LU - QR tables 2022 AES (excel)”.

Not applicable.

See table 15.1 “Deviations from 2022 AES concepts and definitions” in annex “LU - QR tables 2022 AES (excel)”.

Two additional variables related to COVID-19 were collected. 

Not applicable.

See table 15.2 “Comparability - over time” in annex “LU - QR tables 2022 AES (excel)”.

Not applicable.

See table 15.3 “Coherence - cross-domain” in annex “LU - QR tables 2022 AES (excel)”.

Not applicable.

Not applicable.

AES results for a given data collection round are based on the same microdata and results are calculated using the same estimation methods, therefore the data are internally coherent.

Not available.

Not applicable.

Not applicable.

Not applicable.

A simple random sample (of 8000 individuals) has been drawn directly from the population register ("Répertoire National des Personnes Physiques").

See also table 18.1 “Source data” in annex “LU - QR tables 2022 AES (excel)”.

Every 6 years.

See also table 18.1 “Source data” in annex “LU - QR tables 2022 AES (excel)”.

Data has been submitted through a web questionnaire.

The questionnaire contained precise descriptions of each variable, internal controls on most variables and coherence control between different variables, allowing to minimize the errors.

Received data was furthermore checked for consistency within the dataset by STATEC and EUROSTAT.

Weighting factors for individuals (RESPWEIGHT) and for non-formal learning activities (NFEACTWEIGHT_5 and NFEACTWEIGHT_2) are calculated according to the rules laid down in the AES Manual.

The individuals’ weighting factors are based on three variables: age (10 categories), sex (2 categories) and educational attainment level (3 categories), which together define 60 cells (of which some might be empty).

The final weighting factor for the individuals in each cell is equal to the number of persons in the population for that specific cell (N) divided by the number of respondents in that cell (n). (Source for the population data : [lfsa_pgaed])

See table 18.5.1 “Imputation - rate” in annex “LU - QR tables 2022 AES (excel)”.

Not applicable.

Not applicable.

None.