1.1. Contact organisation
ISTAT – National Institute of Statistics
1.2. Contact organisation unit
Population register, demographic and living conditions statistics - DCA
1.3. Contact name
Restricted from publication1.4. Contact person function
Restricted from publication1.5. Contact mail address
ISTAT
Division for population register, demographic and living conditions statistics (DCA)
Viale Liegi 13- 00198 Rome- Italy
1.6. Contact email address
Restricted from publication1.7. Contact phone number
Restricted from publication1.8. Contact fax number
Restricted from publication2.1. Metadata last certified
22 December 20232.2. Metadata last posted
22 December 20232.3. Metadata last update
2 July 20243.1. Data description
The EU survey on the use of ICT in households and by individuals is an annual survey conducted since 2002. In Italy it has been conducted since 2002
In 2023, the survey collects data on the access to information and communication technologies (ICT), on the use of the internet, e-government, electronic identification (eID) and e-commerce, e-skills, as well as privacy and protection of personal data.
3.1.1. Survey name in national and English languages
National language: Indagine multiscopo "Aspetti della vita quotidiana"
English: Multipurpose survey on everyday life aspects
Questionnaire(s) in national language(s) and the translation in English are available in the Annexes below.
3.2. Classification system
The following common concepts and definitions apply under the Integrated European Social Statistics (IESS):
- the International Standard Classification of Education (ISCED) 2011 published in the following breakdowns: low (ISCED levels 0-2: no formal education, primary education or lower secondary education), medium (ISCED levels 3-4: upper secondary or post-secondary non-tertiary education) and high (ISCED levels 5-6: tertiary programmes which normally need a successful completion of ISCED 3 or 4, or second-stage tertiary education leading to an advanced research qualification);
- the International Standard Classification for Occupation ISCO-08 at the 2-digit level;
- the Classification of Economic Activities (NACE Rev.2-2008), at section level;
- the Common classification of territorial units for statistics (NUTS 1) – finer granularity of NUTS 2 is provided on optional basis by some Member States;
- the SCL – Geographical code list;
- information about household income is provided at lower level of detail.
Additional classifications used in the national questionnaire: Territory (Codes for municipalities, provinces and regions).
3.3. Coverage - sector
The ICT survey in households and by individuals covers those households having at least one member in the age group 16 to 74 years old. Internet access of households refers to the percentage of households that have an internet access, so that anyone in the household could use the internet.
3.3.1. Differences in scope at national level
None
3.4. Statistical concepts and definitions
The survey is collecting data of internet users, individuals who have used the internet in the three months prior to the survey.
This annual survey is used to benchmark ICT-driven developments, both by following developments for core variables over time and by looking in greater depth at other aspects at a specific point in time. While the survey initially concentrated on access and connectivity issues, its scope has subsequently been extended to cover a variety of subjects (for example, the use of internet, e-government, eID, and e-commerce, e-skills and privacy and protection of personal data) and socio-economic analysis (such as regional diversity, gender specificity, differences in age, education and the employment situation). The scope of the survey with respect to different technologies is also adapted so as to cover new product groups and means of delivering communication technologies to end-users.
For more details on the methodology applicable in each survey year, please consult the Compiler's Manual for the respective year (Methodological Manual - Information society statistics).
Deviations from standard ICT concepts: None
3.5. Statistical unit
Households and Individuals
3.6. Statistical population
In the ICT usage survey, the target population for the different statistical units is:
- individuals: all individuals aged 16 to 74;
- households: all (private) households with at least one member aged 16 to 74.
Target population composed of households and/or individuals:
- Number of households: 21 879 340 Universe
- Number of individuals: 43 538 623 Universe
3.6.1. Non-compulsory age groups
Non-compulsory age groups also included in the target population:
| No | Yes | Age scope | |
| Individuals younger than 16? | X | ||
| Individuals older than 74? | X | 75 - higher |
3.6.2. Population not covered by the data collection
| Non-target population (the difference between the total population and the target population) |
Households | Individuals |
| Approximate number of units outside the general scope of the survey (for example individuals younger than 16 or older than 74; households with all members over 74 years old). | 3 900 | 8 000 |
| Estimate of the resulting percentage of under-coverage (non-covered population compared to the total country), if applicable |
3.7. Reference area
The whole Italian territory (no region excluded) except Vatican and San Marino State
3.8. Coverage - Time
Year 2023
3.9. Base period
Not applicable
Percentages of ‘Households’ and Percentages of ‘Individuals’
For most questions the reference period is the last three months before the interview. Questions in the modules on e-government and eID refer to the 'last year' before the interview.
Deviation from this assertion: None
5.1. Survey period
The data collection period is 9 January 2023 to 31 March 2023
6.1. Institutional Mandate - legal acts and other agreements
The legal basis for the 2023 EU survey on the use of ICT in households and by individuals is the Regulation (EU) 2019/1700 of the European Parliament and of the Council of 10 October 2019 establishing a common framework for European statistics relating to persons and households, based on data at individual level collected from samples (OJ L 261 I, 14.10.2019, p. 1), as implemented by the Commission Implementing Regulation (EU) 2022/1399 of 1 August 2022 specifying the technical items of the data set, establishing the technical formats for transmission of information and specifying the detailed arrangements and content of the quality reports on the organisation of a sample survey in the use of information and communication technologies domain for reference year 2023 in accordance with Regulation (EU) 2019/1700 of the European Parliament and of the Council (OJ L 213, 16.08.2022, pp. 13-56) and Commission Delegated Regulation (EU) 2022/2279 of 1 August 2022 supplementing Regulation (EU) 2019/1700 of the European Parliament and of the Council by specifying the number and titles of the variables for the use of information and communication technologies statistics domain for the reference year 2023.
Complementary national legislation constituting the legal basis for the survey on the use of ICT in households and by individuals:
Decree of the President of the Republic of 9 March 2022 approving the National Statistical Program 2020- 2022 and the related list of surveys with mandatory response for private entities (OJ General Series No 122 d of 26-05-2022 - S.O. No. n. 20) (in italian only)
Note: National Statistical Program 2023-2025 - is currently being formalized
6.2. Institutional Mandate - data sharing
Not applicable
7.1. Confidentiality - policy
The information collected, protected by statistical confidentiality (art. 9 Legislative Decree no. 322/1989) and subject to the regulations on the protection of personal data (Legislative Decree no. 196/2003). This information may be used, also for successive processing, by subjects of the Italian National Statistical System, exclusively for statistical purposes, and may be communicated for the purpose of scientific research according to the terms and by the procedures laid down in art. 7 of the Code of ethics for the processing of personal data performed in the context of the Italian National Statistical System (Annex A.3 of Legislative Decree no. 196/2003). The data will be disseminated in aggregate form so that it will not be possible to trace the data back to the individuals who provided them, ensuring the maximum privacy.
See for information in Italian: Normativa, privacy
7.2. Confidentiality - data treatment
Data are transmitted via Eurostat integrated environment for data transmission and delivered to a secure environment where they are treated.
8.1. Release calendar
The target is to release data on 20 of December 2023.
8.2. Release calendar access
The planned release dates are announced some weeks in advance on the ISTAT website.
8.3. Release policy - user access
ISTAT's dissemination policy, as well as other national statistical institutes, is inspired by principles of timeliness and transparency shared at international level and enunciated by supranational organizations such as the United Nations, the International Monetary Fund (IMF) and the European Commission.
Annual
10.1. Dissemination format - News release
Annual Citizens and Ict (in italian only)
10.2. Dissemination format - Publications
Noi Italia. 100 Statistics to understand the country we live (in italian only)
10.3. Dissemination format - online database
Data dissemination in the data wharehouse I.Stat theme "Culture, communication, tourism" subtheme "Internet: access and type of use": http://dati.istat.it/?lang=en&SubSessionId=f57f860d-2784-45ec-9e5b-67780152b746
10.3.1. Data tables - consultations
Not applicable
10.4. Dissemination format - microdata access
Information on microdata access are available at: Microdata
Files are released free of charge and in compliance with the principle of statistical secrecy and protection of personal data.
Four types of microdata will be released
- PUBLIC USE FILES, downloadable directly from the website;
- FILES FOR RESEARCH PURPOSES, issued to subjects belonging to universities or research bodies upon the presentation of a research project;
- FILES FOR SISTAN, accessible only by the statistical offices of the National Statistical System;
- FILES FOR THE LABORATORY, for Elementary Data Analysis (ADELE), where subjects belonging to universities or research bodies can access microdata files of all ISTAT surveys (without identification, sensitive and judicial data).
PUBLIC USE FILES
Public use of mIcro.STAT files are collections of elementary data downloaded directly and free of charge from the ISTAT website. To acquire such files it is necessary to register at the area of the ISTAT website dedicated to them and to accept the terms of use. Data are available in different formats (TXT, STATA, SAS, R).
FILES FOR RESEARCH PURPOSES
Files for research purposes are developed in relation to statistical surveys regarding individuals and households as well as enterprises, and are created specifically for the purposes of scientific research. These files are subject to particular statistical treatments that limit the identifiability of the respondent, while maintaining a high level of detailed information.
Files for research purposes may be requested exclusively by:
- subjects belonging to universities or research bodies and institutions to which the “Ethical code for the processing of statistical data outside Sistan” applies;
- other subjects with Eurostat requirements defined for the provision of microdata files in accordance with Commission Regulation (EC) no. 557/2013.
Files are available both in delimited or fixed structure and are also provided with the programs to import these files in STATA, SAS and R.
To access microdata it is necessary that the requesting body is recognized as a research entity by the Comstat (Committee for Directing and Co-ordinating Statistical Information) on the basis of established criteria (Article 5-ter paragraph 1, letter a) of the legislative decree 14 March 2013, no. 33) or is included into the list of research entities recognized by Eurostat (Regulation (EU) No. 557/2013).
The researchers of an institution included in the list of recognized organizations may submit, for a preliminary assessment, the research proposal for the request for access to MFR files to: rilasciomicrodati@istat.it.
FILES FOR SISTAN
Requests for elementary data by Sistan departments
Directive no. 9 issued by Comstat (Committee for Directing and Co-ordinating Statistical Information), “Criteria and procedures concerning the communication of personal data within the National Statistical System”, brings Sistan fully into line with legislation concerning the protection of personal data (Legislative Decree 196/03 and ethical code of conduct). The directive deals with the transmission of previously collected personal data to a statistic bureau or agency or any other party in the System (in this specific case ISTAT) which requests them for statistical purposes.
Such requests may be made for the purpose of:
- the implementation of the National Statistical Programme (PSN);
- the execution of statistical data processes in connection with the institutional activities or local area of competence of the requesting party. In this case, a brief description of the project must be provided.
The transmission of personal data with information containing unique identification data must be limited to exceptional cases in which it is absolutely and strictly necessary (in which it is impossible to achieve established objectives without information for identification). The signer of the request assumes full responsibility with regard to the applicability of this condition.
In order to acquire information or microdata files the requesting party (Director of the Statistics Department or data controller/supervisor for public Bodies and Boards providing statistical information) must register at the Cont@ct center. Once registration has been completed, or for users already registered, the request must be formulated by selecting, in the Cont@ct centre the area: “Dati elementari per uffici Sistan” (Elementary data for Sistan departments) and filling in the online form.
FILES FOR THE LABORATORY
The Laboratory for Elementary Data Analysis (ADELE) is a “safe” environment in which researchers from universities or research institutions or bodies to which the Code of conduct and professional practice applying to processing of personal data for statistical and scientific purposes applies (Annex A.4, Legislative Decree no. 196 of 30th June 2003) may conduct statistical analyses that require the use of elementary data, where information already available with other tools is not sufficient (I.Stat data warehouse, publications, data tables, databases, microdata files, custom processing).
Within the Laboratory, data security and statistical confidentiality are guaranteed by the control of both the working methods and the results of the analyzes conducted by the users.
Once the processing is complete, the output is evaluated in terms of statistical confidentiality by the experts of the ADELE Laboratory. Only results that positively comply with the Rules for the release of results can be issued. Please note that starting from March 2016 the release rules for structural equation models and factor analysis have been specified and since June 2016 also for analysis in main components and correspondence analysis.
Access to the ADELE Laboratory is free.
10.5. Dissemination format - other
Not applicable
10.5.1. Metadata - consultations
Not applicable
10.6. Documentation on methodology
It is possible to find Survey description in ISTAT information system on quality of statistical production processes https://siqual.istat.it/SIQual/visualizza.do?id=0058000
10.6.1. Metadata completeness - rate
100%
10.7. Quality management - documentation
The following methods are used to improve quality:
Prevention, monitoring and evaluation of total non-response: initiatives to encourage participation in the survey;
Treatment of incorrect or incomplete responses: training and supervision of operators and verification of procedures; Interviewer training corrective methods to reduce the effects of incorrect or incomplete responses;
Validation of data: Coherence control with data from other surveys (Census of population, LFS) or other sources (Annual Report); Coherence control with previous data of the same survey.
11.1. Quality assurance
- Initiatives to encourage participation in the survey. A few days before the interview, a letter is sent to the sampled households, signed by the President of ISTAT, in which the survey is presented. Furthermore all the people included in the sample could ask for information on the survey by calling a free telephone number (working from Monday to Friday from 9 a.m. to 1 p.m. and from 2 to 7 p.m.).
- Training and supervision of operators and verification of procedures
- A monitoring web system was implemented to allow a daily control of interviewer performance. The ISTAT personnel controlled daily the updating of the monitoring web system. The interviewers had to fill out daily the Monitoring Form to keep track of all contacts and interviews: number of contacts, provisional or final outcome of the interview, duration, date and time of the interview; non-response and reason for non-response; difficulty in contacts; etc. To ensure high-quality of the interviewers performance, the supervisors analyzed the quality indicators in order to take timely action in case of critical situations.
- Validation of data: consistency check with data from other surveys (Census, LFS) or other sources (Annual Report). Consistency check with previous data from the same survey.
For further information: Classifications and Tools
11.2. Quality management - assessment
The comprehensive monitoring system that involves the interviewers, the referent person of the municipalities, the regional offices and the central staff of ISTAT allowed to prevent and reduce non-response and/or measurement errors. The access to the online quality indicators from all persons involved in the monitoring, enabled us to follow daily the survey in its various aspects: the progress of the survey, the lack of participation and the reasons for not participating, the method of completion of the questionnaires, etc., allowing us to quickly identify and resolve critical situations highlighted by the system.
At European level, the recommended use of the annual Eurostat model questionnaire aims at improving comparability of the results among the countries that conduct the survey on ICT usage by household. Moreover, the Methodological Manual provides guidelines and clarifications for the implementation of the surveys in the Member States.
12.1. Relevance - User Needs
ISTAT uses working groups for the preparation of the National Statistical Program (PSN). The working group in which is included the ICT survey is responsible for meeting to analyze the supply and demand for statistical information for the PSN. The participants are from other public institutions or from private sector.
12.2. Relevance - User Satisfaction
Not available
12.3. Completeness
All of the variables required for transmission 2023 have been included in the microdata.
12.3.1. Data completeness - rate
100%
13.1. Accuracy - overall
The main sources of error of the estimates are sampling errors, nonresponse errors (unit and item) and measurement errors.
As regards the first ones, they were assessed with the standard error (SE) estimation; this is a measure of precision of the survey estimates. SE was estimated from the sample data through the linearization formula of the sampling variance (Re-genesees software) of the main estimates.
Non-sampling errors are errors in survey estimates which cannot be attributed to sampling fluctuations. Such errors can either be coverage errors, measurement errors, non-response errors, processing errors or model assumption errors.
Non-sampling errors are basically of 4 types:1) Coverage errors: errors due to divergences existing between the target population and the sampling frame; 2) Measurement errors: errors that occur at the time of data collection. There are a number of sources for these errors such as the survey instrument, the information system, the interviewer and the mode of collection; 3) Processing errors: errors in post-data-collection processes such as data entry, keying, editing and weighting; 4) Non-response errors: errors due to an unsuccessful attempt to obtain the desired information from an eligible unit. Two main types of non-response errors are considered: Unit non-response - refers to absence of information of the whole units (households and/or persons) selected into the sample; Item non-response - refers to the situation where a sample unit has been successfully enumerated, but not all required information has been obtained.
Non-response errors due to unit non-response were monitored by indicators in order to prevent and reduce them. This was reached with actions made before the data collection started (interviewing technique to avoid refusals, letters to households) and after data collection, by using calibration estimators (this is also partially useful to compensate for under-coverage errors). Measurement errors and item nonresponse errors, which were monitored by indicators and reports, were corrected by control and editing procedures. Double data entry of a sample of record was used. Deterministic and stochastic imputations were used as previously described.
Coverage errors are errors that express the quantitative divergence between the sampling frame population and the target population due to, for example, remoteness, age, multiple entries; coverage of different sub-populations. The use of the Master Sample of Census from 2022 could reduce the risk of coverage errors because the list was previously corrected and controlled for Census.
13.2. Sampling error
As regard sampling errors, they were assessed with the standard error (SE) estimation, that is a measure of precision of the survey estimates. Standard errors are calculated using the Taylor linearization technique. The software used to calculate standard errors is ReGenesees (software produced by Istat https://www.istat.it/en/methods-and-tools/methods-and-it-tools/process/processing-tools/regenesees).
The coefficient of variation is given by the square root of the variance of the estimator out of its expected value. It is estimated by the ratio of the square root of the estimated sampling variance to the estimated value of the variable of interest. See document annexed below.
References in the literature: Deville J.C., Sarndal C.E. (1992) Calibration Estimators in Survey Sampling, Journal of the American Statistical Association, vol. 87, pp. 376-382 Woodruff, R. S. (1971), A Simple Method for Approximating the Variance of a Complicated Estimate, Journal of the American Statistical Association, vol. 66, pp. 411-414
The sampling error reflects the fact that only a particular sample was surveyed rather than the entire population. It is estimated by the standard error and can be expressed by the square root of the estimate of the sampling variance . The estimation of the sampling variance should ideally take into account the sampling design (e.g. the stratification).
13.2.1. Sampling error - indicators
Precision estimates for the question "Individuals having ordered goods or services for private use over the internet in the last 12 months" (individuals who ticked 'Within the last 3 months' or 'Between 3 months and a year ago' in in the question “When did you last buy or order goods or services for private use over the internet?”):
Number of respondents (absolute value for ‘Yes’ answers): 15 495
Estimated proportion (in %): 51.1
Standard error (in percentage points): 0.24
Details of the breakdowns are available in document INFOSOC_HHNSI_A_2023_IT in the Annexes below.
13.3. Non-sampling error
See more details on non-sampling error below.
13.3.1. Coverage error
The sampling frame populations are:
- LAC (Liste Anagrafiche Comunali) - Register of households resident in municipalities updated at the 01 January 2020 for municipalities with less than 1,000 inhabitants;
- Master Sample of CENSUS 2022 - List of municipalities and households used for the permanent Census for municipalities with more than 1,000 inhabitants.
Those sampling frames might contain errors for information such as addresses (due for instance to recent change of the address), wrong inclusions (recent emigration) and missed inclusions (recent immigration).
Coverage errors could be also due to the time lag between last update of the sampling frame and the time of the actual sampling (few months for LAC, one year for CENSUS 2021).
The use of the Master Sample of Census 2022 reduces the risk of coverage errors because the list was previously corrected and controlled for Census.
13.3.1.1. Over-coverage - rate
Not applicable
13.3.1.2. Common units - proportion
Not requested in the ICT survey.
13.3.2. Measurement error
1) Measurement errors:
The main measurement errors occurred during data collection were related to the use of the PAPI technique. In particular, the use of paper made difficult to manage some filters and errors on codification of variables.
2) Questionnaire design and testing:
The ICT HH questionnaire is based on the design of the questionnaire recommended by Eurostat. The module on ICT usage in households and by individuals is embedded in the annual multipurpose survey “Aspects of Daily life” integrating some sections with a few other questions useful at national level and every year ISTAT experts in the preparation of questionnaires work on the optimization of the questionnaire and testing of the CAWI and CAPI questionnaire.
3) Interviewer training:
Interviewers are recruited by the Statistical Offices of the Municipalities complying with the requirements provided by the National Statistical Institute (ISTAT). Some interviewers had experience in previous social surveys (they are registered in a register of interviewers that includes quality indicators on their performance) and others were trained for the first time. The personnel of the regional offices of ISTAT trained both the municipal contact persons for the survey and the interviewers. The staff of multipurpose survey “Aspects of Daily life”, trained the colleagues of the ISTAT regional offices, who have a long experience in carrying out sample surveys and in coordinating the activities of the interviewers.
The training of the interviewers was generally face to face in a classroom, but in these last two years because of the Covid-19 pandemic, the training has been done online. The training documents were: slides, questionnaires and guidelines. Interviewers received a login and a password to access the web monitoring system of the survey, the slides, the questionnaires and the manual with the guidelines. The guidelines explained how to contact the household for the interviews; how to behave to ensure the cooperation and the participation to the survey of the members of the household; how to carry out the interview; the rules to comply with for proxies and privacy issues; detailed information for each variable of the questionnaire.
4) Proxy interview rates: 6.13%
13.3.3. Non response error
Information about non-respondents: The distribution by sex and age of non-respondents did not have high bias compared to the respondent one.
13.3.3.1. Unit non-response - rate
The unit non-response rate is the ratio of the number of in-scope non-respondents (= number of rejected interviews) to the number of eligible elements selected from the sampling frame.
Unit non-response rate for
- Households: 24%
- Individuals (aged 16-74): 24%
13.3.3.1.1. Unit non-response – sample sizes
| Number of households | Number of individuals | |||
| (aged 16-74) | (< 16) | (> 74) | ||
| Gross sample [A] The number of households/individuals initially selected from the sampling frame (if not applicable, indicate why below the table) |
24 871 | 48 874 | ||
| Ineligible: out-of-scope [B] For example, when a selected household is not in the target population because all members are over 75 years old or when no dwelling exists at the selected address, or a selected individual has died between the reference data of the sampling frame at the moment of the interview. |
4 215 | 8 283 | ||
| Number of eligible elements [C] Gross sample size corrected of the ineligible cases |
20 656 | 40 591 | ||
| Net sample size or final sample [D] The net sample size (or final sample) corresponds to the number of households/individuals that can be used in the final database. |
15 708 | 30 868 | ||
| Unit response rate [E] = [D] / [C] The unit response rate is the ratio of the number of in-scope respondents (= the number of achieved interviews or the net sample size) to the number of eligible elements selected from the sampling frame. |
76 | 76 | ||
Comments, if any:
13.3.3.1.2. Unit non-response – methods, minimization and substitution
1) Methods used for dealing with unit non-response:
The procedure used to construct the final weights to be assigned to the corresponding sample units, is generally divided into the following phases:
- the direct weights are calculated as reciprocal of the probability of inclusion of the units in the sample;
- the correction factors for total non-response are calculated by the inverse of the response rate in appropriate subsets of units;
- the base weights, or weights correct for total non-response, are obtained multiplying the direct weights by the non-response factors;
- the calibration correction factors are computed to satisfy at regional level the condition of equality between the known totals of some auxiliary variables and the corresponding sample estimates;
- the final weights are calculated by the product of the base weights and the correction factors obtained in step 3.
2) Methods used for minimizing unit non-response:
- Advance notification in form of letters
- Free phone number to contact and ask for information.
- Assurances provided to the households by the interviewer and ISTAT staff regarding the confidentiality of information and the protection of privacy.
3) Substitution permitted:
If a household member is absent will be requested within the time period of the survey; only if this is not really possible then another household member will be interviewed. Proxy interviews are also allowed, in case of obvious difficulties of the component to respond (disability, special distress, illness).In case of proxy answers, the following guidelines are adopted.
if it is a couple with or without children, it is preferable to ask the questions to the woman of the couple
if it is a single parent with children it is preferable to ask the questions to the parent in other situations another adult in the household who can provide the information
4) Substitution rate (in %): about 9%
13.3.3.2. Item non-response - rate
Items with low response rates (observed rates in %):
- Socio-demographic background EU target variables: None.
- Household-based ICT related EU target variables: None.
- Individuals' based ICT related EU target variables:
- TIME: Interview duration 60%
13.3.4. Processing error
Data entry is performed by a private company contracted by ISTAT. A format, reporting for each variable the admitted values and warnings (outliers), was prepared by ISTAT to ensure that all variables were correctly filled out throughout a software used for data entry by the private company.
Check of the coherence between the electronic dataset and the paper questionnaire was carried out by controlling the files after the data entry: coding errors (e.g. municipality codes), data entry errors (e.g. a one digit number instead of a two digit number), data out of possible range or incoherence of data (e.g. the age calculated by the date of birth and the age in years, the marital status not coherent with other information like the year of the marriage, or the other information concerning the family).
Check and deterministic correction of all variable were done in order to correct incoherent values and errors. The validation rules were implemented in SAS programs for all the modules.
Imputations were applied to respect all the ICT validation rules and treatment of errors concerning the 1) Not admitted values; 2) Outliers; 3) Missing values; 4) Incoherent values among variables in the same module or in different modules.
The core social variables (age, sex, legal marital status, de facto marital status, type of household) and level of education, labour status, were checked in order to correct incoherent values and impute missing values.
Other National datasets (surveys or administrative registers) concerning the same dimensions /questions or phenomena were used to validate/compare the variables.
13.3.5. Model assumption error
Not requested for ICT Survey
14.1. Timeliness
Date of data dissemination at national level:
20 December 2023
14.1.1. Time lag - first result
Restricted from publication14.1.2. Time lag - final result
Restricted from publication14.2. Punctuality
Data have been submitted to Eurostat 4 october 2023
14.2.1. Punctuality - delivery and publication
delivered on time.
15.1. Comparability - geographical
There is no problem of comparability across the country’s regions.
15.1.1. Asymmetry for mirror flow statistics - coefficient
Not relevant
15.2. Comparability - over time
Possible limitations in the use of data for comparisons over time: Not relevant
15.2.1. Length of comparable time series
The length of comparable time series depends on the module and variable considered within each of the modules of the survey.
15.3. Coherence - cross domain
Not applicable
15.3.1. Coherence - sub annual and annual statistics
Not applicable
15.3.2. Coherence - National Accounts
Not applicable
15.4. Coherence - internal
All statistics are coherent within the dataset”
15.4.1. Survey questionnaire – mandatory questions
MANDATORY questions in the Eurostat model questionnaire 2023:
Table 15.4.1. of document INFOSOC_HHNSI_A_2023_IT in the Annexes lists the questions included in the national questionnaire for which the coverage of subjects and characteristics differs from of Annex 2 of the Commission Delegated Regulation (EU) 2022/2279 of 1 August 2022.
15.4.2. Survey questionnaire – optional questions
Adoption of OPTIONAL questions and items in the Eurostat model questionnaire 2023:
Table 15.4.2. of document INFOSOC_HHNSI_A_2023_IT in the Annexes lists the optional questions from the annual Eurostat model questionnaire 2023 included in the national questionnaire and their coverage for age groups beyond the standard scope.
15.4.3. Survey questionnaire – additional questions at national level
Additional questions introduced in the national questionnaire in 2023: None
15.4.4. Survey questionnaire – deviations
Effects of deviations from the routing used in the Eurostat model questionnaire: No deviations from Eurostat’s routing otherwise
17.1. Data revision - policy
A revision of the sampling weight calculation system is being currently under evaluation in order with the aim of using the recent availability of Permanent Census data on the number of households and type.
17.2. Data revision - practice
Nowadays there are no revisions to report”
17.2.1. Data revision - average size
Not relevant
18.1. Source data
The source of the raw data is described with more details in the paragraphs below.
18.1.1. Sampling frame
For municipalities with 1,000 inhabitants or more: Master Sample of CENSUS - List of municipalities and households used for the permanent Census;
For municipalities with less than 1,000 inhabitants: LAC (Liste Anagrafiche Comunali) - Register of households resident in municipalities.
Survey vehicle: The module on ICT usage in households and by individuals is embedded in the annual multipurpose survey “Aspects of Daily life” that is the main survey of ISTAT’s integrated system of multi-purpose social surveys. This annual survey is the supporting and normalising element of the whole social informative framework. It collects a set of data concerning individuals, households and events which affords to construct and analyse the citizen’s demand, besides comparing it with services supply, already surveyed by ISTAT.
Survey participation: Participation in this survey is mandatory because it is part of the National Statistical Plan.
18.1.2. Sampling design
The sample is selected from the Master sample of the permanent census and from LAC (Liste Anagrafiche Comunali).
The sampling design is a probability design. The sample is systematic selected with probabilities proportional-to-size. Around 230 primary sampling units are self-representing, defined according to a threshold which is function of the sampling fraction at NUTS2 level and the minimum number of sampling households for municipality. Households are second stage sampling units and are selected for each municipality from the theoretical sample of master sample with equal probabilities.
All individuals in the selected household are interviewed
18.1.3. Net effective sample size
Restricted from publication18.2. Frequency of data collection
Annual
18.3. Data collection
1) Methods used to gather data:
Mix mode 51.2% Paper assisted personal interview (PAPI)) and self-administered paper questionnaire. 48.8% Computer assisted web interview (CAWI)
2) Short description of the survey method:
The information is collected through a mixed technique, which uses an online questionnaire that is filled in by respondents (CAWI technique, Computer-Assisted Web Interviewing) or a direct interview with electronic questionnaire administered by an interviewer (CAPI technique, Computer-Assisted Personal Interviewing) and self-administered paper questionnaire.
3) Variables completed from an external source:
In instances where there was no response on some demographic variables (sex, year of birth, citizenship), information was completed by Register of households resident in municipalities.
18.4. Data validation
The procedures used for checking and validating the source data are :
- Internal consistency of data analysis
- Time series comparison
- Acquisition of information on data processing, controls and/or corrections
- Comparison with external sources (statistical registers, other sources)
- Validation standards provided by Eurostat.
18.5. Data compilation
Data entry is performed by a private company contracted by ISTAT. A format, reporting for each variable the admitted values and warnings (outliers), was prepared by ISTAT to ensure that all variables were correctly filled out throughout a software used for data entry by the private company.
Check of the coherence between the electronic dataset and the paper questionnaire was carried out by controlling the files after the data entry: coding errors (e.g. municipality codes), data entry errors (e.g. a one digit number instead of a two digit number), data out of possible range or incoherence of data (e.g. the age calculated by the date of birth and the age in years, the marital status not coherent with other information like the year of the marriage, or the other information concerning the family).
Check and deterministic correction of all variable were done in order to correct incoherent values and errors. Validation rules were implemented in SAS programs for all the modules.
Imputations were applied to respect all validation rules and treatment of errors concerning the 1) Not admitted values; 2) Outliers; 3) Missing values; 4) Incoherent values among variables in the same module or in different modules. The core social variables (age, sex, legal marital status, de facto marital status, type of household) and level of education, labour status, were checked in order to correct incoherent values and impute missing values. Other National datasets (surveys or administrative registers) concerning the same dimensions /questions or phenomena were used to validate/compare the variables.
Data are checked and corrected following to different approaches: deterministic imputation based on if then conditions to ensure internal coherence of data (plan of check) and probabilistic imputation to deal with partial non response (Fellegi-Holt methodology or nearest-neighbour imputation).
Calibration estimator are used the corrections to the design weights
18.5.1. Imputation - rate
For the target indicator "Individuals having ordered goods or services for private use over the internet in the last 12 months" (individuals who ticked 'Within the last 3 months' or 'Between 3 months and a year ago' in the question “When did you last buy or order goods or services for private use over the internet?”:
Imputation rate (% of observations): 1.9%
Imputation rate (share of estimate): 1.8%
18.5.2. Use of imputation methods
Methods used to impute item non-response: Random imputation
18.5.3. Grossing-up procedures
Grossing up procedures have been applied to:
The estimates produced by the survey are absolute and relative frequencies, referring to the households and to persons or estimates of quantitative variables. The principle on which each sample estimation method is based is that the units belonging to the sample represent also the units of the population that are not included in the sample. This principle is achieved by attributing a sample unit to a weight that indicates the number of units of the population represented by the unit itself. For example, if a sample analysis is assigned a weight of 30, this indicates that the units are not included in the sample. The weights are obtained by means of a calibration estimator.
Description of the weighting procedures:
The procedure used to construct the final weights to be assigned to the corresponding sample units, is generally divided into the following phases:
- the direct weights are calculated as reciprocal of the probability of inclusion of the units in the sample;
- the calibration correction factors are computed to satisfy at regional level the condition of equality between the known totals of some auxiliary variables and the corresponding sample estimates;
- the final weights are calculated by the product of the base weights and the correction factors obtained in step 2.
18.6. Adjustment
Not relevant
18.6.1. Seasonal adjustment
Not relevant
The EU survey on the use of ICT in households and by individuals is an annual survey conducted since 2002. In Italy it has been conducted since 2002
In 2023, the survey collects data on the access to information and communication technologies (ICT), on the use of the internet, e-government, electronic identification (eID) and e-commerce, e-skills, as well as privacy and protection of personal data.
The survey is collecting data of internet users, individuals who have used the internet in the three months prior to the survey.
This annual survey is used to benchmark ICT-driven developments, both by following developments for core variables over time and by looking in greater depth at other aspects at a specific point in time. While the survey initially concentrated on access and connectivity issues, its scope has subsequently been extended to cover a variety of subjects (for example, the use of internet, e-government, eID, and e-commerce, e-skills and privacy and protection of personal data) and socio-economic analysis (such as regional diversity, gender specificity, differences in age, education and the employment situation). The scope of the survey with respect to different technologies is also adapted so as to cover new product groups and means of delivering communication technologies to end-users.
For more details on the methodology applicable in each survey year, please consult the Compiler's Manual for the respective year (Methodological Manual - Information society statistics).
Deviations from standard ICT concepts: None
Households and Individuals
In the ICT usage survey, the target population for the different statistical units is:
- individuals: all individuals aged 16 to 74;
- households: all (private) households with at least one member aged 16 to 74.
Target population composed of households and/or individuals:
- Number of households: 21 879 340 Universe
- Number of individuals: 43 538 623 Universe
The whole Italian territory (no region excluded) except Vatican and San Marino State
For most questions the reference period is the last three months before the interview. Questions in the modules on e-government and eID refer to the 'last year' before the interview.
Deviation from this assertion: None
The main sources of error of the estimates are sampling errors, nonresponse errors (unit and item) and measurement errors.
As regards the first ones, they were assessed with the standard error (SE) estimation; this is a measure of precision of the survey estimates. SE was estimated from the sample data through the linearization formula of the sampling variance (Re-genesees software) of the main estimates.
Non-sampling errors are errors in survey estimates which cannot be attributed to sampling fluctuations. Such errors can either be coverage errors, measurement errors, non-response errors, processing errors or model assumption errors.
Non-sampling errors are basically of 4 types:1) Coverage errors: errors due to divergences existing between the target population and the sampling frame; 2) Measurement errors: errors that occur at the time of data collection. There are a number of sources for these errors such as the survey instrument, the information system, the interviewer and the mode of collection; 3) Processing errors: errors in post-data-collection processes such as data entry, keying, editing and weighting; 4) Non-response errors: errors due to an unsuccessful attempt to obtain the desired information from an eligible unit. Two main types of non-response errors are considered: Unit non-response - refers to absence of information of the whole units (households and/or persons) selected into the sample; Item non-response - refers to the situation where a sample unit has been successfully enumerated, but not all required information has been obtained.
Non-response errors due to unit non-response were monitored by indicators in order to prevent and reduce them. This was reached with actions made before the data collection started (interviewing technique to avoid refusals, letters to households) and after data collection, by using calibration estimators (this is also partially useful to compensate for under-coverage errors). Measurement errors and item nonresponse errors, which were monitored by indicators and reports, were corrected by control and editing procedures. Double data entry of a sample of record was used. Deterministic and stochastic imputations were used as previously described.
Coverage errors are errors that express the quantitative divergence between the sampling frame population and the target population due to, for example, remoteness, age, multiple entries; coverage of different sub-populations. The use of the Master Sample of Census from 2022 could reduce the risk of coverage errors because the list was previously corrected and controlled for Census.
Percentages of ‘Households’ and Percentages of ‘Individuals’
Data entry is performed by a private company contracted by ISTAT. A format, reporting for each variable the admitted values and warnings (outliers), was prepared by ISTAT to ensure that all variables were correctly filled out throughout a software used for data entry by the private company.
Check of the coherence between the electronic dataset and the paper questionnaire was carried out by controlling the files after the data entry: coding errors (e.g. municipality codes), data entry errors (e.g. a one digit number instead of a two digit number), data out of possible range or incoherence of data (e.g. the age calculated by the date of birth and the age in years, the marital status not coherent with other information like the year of the marriage, or the other information concerning the family).
Check and deterministic correction of all variable were done in order to correct incoherent values and errors. Validation rules were implemented in SAS programs for all the modules.
Imputations were applied to respect all validation rules and treatment of errors concerning the 1) Not admitted values; 2) Outliers; 3) Missing values; 4) Incoherent values among variables in the same module or in different modules. The core social variables (age, sex, legal marital status, de facto marital status, type of household) and level of education, labour status, were checked in order to correct incoherent values and impute missing values. Other National datasets (surveys or administrative registers) concerning the same dimensions /questions or phenomena were used to validate/compare the variables.
Data are checked and corrected following to different approaches: deterministic imputation based on if then conditions to ensure internal coherence of data (plan of check) and probabilistic imputation to deal with partial non response (Fellegi-Holt methodology or nearest-neighbour imputation).
Calibration estimator are used the corrections to the design weights
The source of the raw data is described with more details in the paragraphs below.
Annual
Date of data dissemination at national level:
20 December 2023
There is no problem of comparability across the country’s regions.
Possible limitations in the use of data for comparisons over time: Not relevant