The Adult Education Survey (AES) covers adults’ participation in education and training (formal - FED, non-formal - NFE and informal learning - INF). The 2016 AES focuses on people aged 25-64. 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 2016 AES legislation (http://ec.europa.eu/eurostat/web/education-and-training/legislation) and the 2016 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 2016 AES implementation manual (http://ec.europa.eu/eurostat/web/education-and-training/methodology).

Sampling design of the AES survey is a one stage stratified random sampling, with the strata defined by the combination of the modalities of the following planned domains: territorial unit (the North-West, the North–East, the Centre and the South with the Islands), municipality typology, gender, and age class. A fixed number of individuals is selected in each stratum without replacement and with equal probabilities. The optimal number of units to be selected in each stratum is defined as a solution of a linear integer problem (Bethel, 1989).

In particular, the minimum sample size in each stratum is determined in order to ensure that the variance of sampling estimates of the target variable in each domain of interest does not exceed a given threshold, in terms of coefficient of variation. The target variables used for optimising the sample allocation are ‘not in education or training, ‘in formal education’, ‘in non-formal education and training’, whose mean and variance are estimated in each stratum by data collected from the previous survey. The optimal allocation has been obtained by constraining the precision of the estimates of these target variables to a maximum CV of 9 % per estimation domain for the first and the second variables, and a maximum CV of 15 % for the third one respectively.

In this way, an overall sample size of 18 500 individuals has been the result of Bethel’s algorithm. The corresponding optimal sample size at the level of each territorial unit has been then distributed into the 22 Italian administrative regions (representing hence unplanned domains of estimation), according to a proportional criterion.

The sample weights that refer to the entire reference population have been calibrated with respect to the total Italian population (national and regional) of the second semester of 2017 (deduced from the LFS).
During calibration, the following regional constraints have been taken into account:

• Occupational condition perceived, professional position, type of municipality, gender, age class, education.

The distance function used for calibration is the truncated logarithmic.

See also table 3.1 in annex 'IT - ESQRS tables 2016 AES (excel)'.

See table 3.3 in annex 'IT - ESQRS tables 2016 AES (excel)'.

See also the national questionnaire below.

CATI technique was used for data collection during the interview (an outsourcing of data entry). Coherence and compatibility rules were incorporated into the data acquisition software. Any discrepancy or partial non-response has been solved during the interview and accordingly there was no process of data check and correction in the post-collection phase.

Regarding the final validation, coherence control with data from other surveys (LFS) or sources was done, as well as checks against previous AES data.

Increase in the number of individuals in the sample to arrive at providing representative estimates at the regional level. Estimates at regional level are important to allow policies on the territory to increase the participation of individuals in training. In addition, regional estimates affect several academic users.

See table 5.1 in annex 'IT - ESQRS tables 2016 AES (excel)'.

The 2016 AES can be assessed as being successful regarding the overall accuracy due to using the appropriate statistical methods for minimizing the errors (e.g. measurement errors, coverage errors, processing errors, calibration)

A computer procedure developed by the Institute is currently used to calculate the sampling errors.

See table 6.2a in annex 'IT - ESQRS tables 2016 AES (excel)'.

See table 6.2.1 in annex 'IT - ESQRS tables 2016 AES (excel)'.

See table 6.3.1.1 in annex 'IT - ESQRS tables 2016 AES (excel)'.

National comparability:

The sample design allows the comparison of results by italian regions.

International comparability:

Commission Regulation (EU) No 1175/2014 establishes the obligation of the survey in all countries of the European Union, thus ensuring the comparability of information on adult education.

See also table 8.1 in annex 'IT - ESQRS tables 2016 AES (excel)'.

Not applicable.

Data collection staff: 40 interviewers full-time for data collection via the CATI survey and one supervisor.

The average time for answering the questionnaire was 10 minutes.