Croatian Bureau of Statistics

Structural Business Statistics, Innovations, Science, Technologies and Investments Department

Ilica 3, 10 000 Zagreb, Croatia

Statistics on Government Budget Allocations for R&D (GBARD) measure government support to research and development (R&D) activities, and thereby provide information about the priority governments give to different public R&D funding activities. This type of funder-based approach for reporting R&D involves identifying all the budget items that may support R&D activities and measuring or estimating their R&D content.

Main concepts and definitions used for the production of R&D statistics are given by the OECD (2015), Frascati Manual 2015: Guidelines for Collecting and Reporting Data on Research and Experimental Development, The Measurement of Scientific, Technological and Innovation Activities (FM 2015, Chapter 12), which is the internationally recognised standard methodology for collecting R&D statistics and by Eurostat’s European Business Statistics Methodological Manual on R&D Statistics (EBS Methodological Manual on R&D Statistics).

Since the beginning of 2021, the collection of R&D statistics is based on Commission Implementing Regulation (EU) No 2020/1197 of 30 July 2020.

The Regulation sets the framework for the collection of R&D statistics and specifies the main variables of interest and their breakdowns at predefined level of detail (Commission Implementing Regulation (EU) 2020/1197 of 30 July 2020 laying down technical specifications and arrangements pursuant to Regulation (EU) 2019/2152 of the European Parliament and of the Council on European business statistics repealing 10 legal acts in the field of business statistics (europa.eu)).

Statistics on science, technology and innovation were collected until the end of 2020 based on Commission Implementing Regulation (EU) No 2012/995 concerning the production and development of Community statistics on science and technology.

Distribution by socioeconomic objectives (SEO) is based on the Nomenclature for the Analysis and Comparisons of Scientific Programmes and Budgets (NABS) at one digit level.

See below.

GBARD statistics are assumed to report detailed data on all the government's budget items that may support R&D activities and to measure or estimate their R&D content. For the purposes of GBARD, the Government sector comprises (a) the central (federal) government, (b) regional (state) government and (c) local (municipal) government subsectors (FM2015, Chapter 12).

Not requested.

Statistical units are budgetary and extrabudgetary users of government budget.

See below.

The target population is the population for which inferences are made. The frame (or frames, as sometimes several frames are used) is a device that permits access to population units. The frame population is the set of population units, which can be accessed through the frame and the survey data really refer to this population.

GBARD statistics cover national data (aggregates for NUTS 1) accordind to Statistical Classification of Economic Activities in the European Community – NACE Rev. 2.1.

Calendar year 2021

Not requested.

Unit of measure is expenditure in thousand of national currency (kuna).

a) Calendar year: 2021.

b) Fiscal year:

    Start month:

    End month:

See below.

Since the beginning of 2021, GBARD statistics are based on Commission Implementing Regulation (EU) No 2020/1197 of 30 July 2020 laying down technical specifications and arrangements pursuant to Regulation (EU) 2019/2152 of the European Parliament and of the Council on European business statistics repealing 10 legal acts in the field of business statistics. The Regulation sets the framework for the collection of R&D statistics and specifies the main variables of interest and their breakdowns at predefined level of detail. GBARD statistics were based until the end of 2020 on the Commission Implementing Regulation (EU) No 2012/995 concerning the production and development of Community statistics on science and technology.

Production of national GBARD statistics is governed by the general national statistical legislation, The Official Statistics Act (NN 25/20) and the current annual implementation plan of statistical activities. 

The Official Statistics Act (NN No. 25/20) and Annual Implementation Plan of Statistical Activities of the Republic of Croatia for 2022 (NN No 42/22)

-          Frascati Manual 2015, Guidelines for Collecting and Reporting Data on Research and Experimental Development

-          EBS Methodological Manual on R&D Statistics

Not requested.

Confidentiality, being one of the process quality components, concerns the privacy of data providers (households, enterprises, administrations and other respondents), the confidentiality of the information they provide and the extent of its use for statistical purposes.

A property of data indicating the extent to which their unauthorised disclosure could be prejudicial or harmful to the interest of the source or other relevant parties.

a)       Confidentiality protection required by law:

Statistical data collected in this survey, according to the National Statistics Act (NN, 25/20.) is confidential and its purpose is restricted exclusively to statistical usage (with exception of registered researchers under specified conditions). Authorized interviewers are obligated to respect these restrictions. The results will be published in a cumulative form which prevents displaying data on individuals.

b)       Confidentiality commitments of survey staff:

According to Code of practice of European Statistics, all employees upon employment are informed of the rules and duties pertaining to confidential information and its treatment and are obliged sign statistical confidentiality statement.

The following rules are used to identify sensitive cells in tabular data:

•              Threshold rule: The cell is considered sensitive if the cell frequency is less than a pre-specified threshold value. In practice this means if data in certain cell in the table relates to less than a pre-specified number of reporting units, the cell is primary sensitive.

•              Dominance rule: The cell is considered sensitive if the value of 1 largest contributor in the cell exceeds a pre-specified percentage of total value for that cell.

When a data cell in a table is suppressed by dropping its value based on a primary cell suppression rule, the value of that cell can still be calculated if the table provides totals. Secondary cell suppression is therefore needed to avoid such disclosures. Those values under primary and secondary protection are therefore suppressed for use. 

Data are published in aggregated form which does not allow identification of the reporting unit. All collected data are confidential and are used only for statistical purposes.

Release policy and release calendar are available and publicly accessible on CBS website.

Release calendar is publicly accessible.

According to the Release Date announced in the Publishing Programme and in the Calendar of Statistical Data Issues, publications of the Croatian Bureau of Statistics are released at 11:00 a.m. precisely, in electronic format, thus abiding by the Principle of Timeliness of the European Statistics Code of Practice, i.e. standard daily time set for the release.

GBARD is conducted and disseminated annually at the end of December as First release.

See below.

1) Y - Yes, N – No

See below.

1) Y – Yes, N - No 

Currently we do not have an on-line databases for GBARD. However, we are planning to create and publish PC-Axis database.

Not requested.

See below.

See below.

Not requested.

1) Y – Yes, N - No 

GBARD methodology is described in First Release in electronic version avaialble on the web site of the CBS. In the First Release ZTI-2022-2-2 "Government budget allocations for R&D, 2021-2022", there are parts containing information about data sources, coverage and comparability, definitions and explanations and short interpretation and analysis of results, within part "Notes on methodology".

Not requested.

See below.

Croatian Bureau of Statistics uses the model of total quality management which comprises European Code of Practice. In order to ensure this, a quality system has been established. The CBS regularly submits quality reports according to the templates prescribed for each area of statistics by the corresponding organizational unit of Eurostat. A template was developed based on the ESMS, ESQRS and SIMS structures. In order to produce complete reports on quality, considering all quality indicators, the CBS has prepared a Manual for the calculation of quality indicators. Quality reports for individual statistical surveys are available on the website of the CBS.

The POMI quality database offers many opportunities as well as DESAP questionnaire for doing self-assessment.
As already mentioned before the developed tools like POMI quality and application database in combination with the GSBPM give the opportunity for each statistical survey to be improved if necessary.
An independent Internal Audit unit conducts internal audits in the CBS, gives professional opinion and has an advisory role for improving CBS business operation, estimate systems, processes and the internal controlling system based on the risk management, carries out internal audits in accordance with the best professional practice and internal audit standards in line with the International standards on internal auditing and the Ethics Code of the Internal Auditors.

Since year 2016 we are continuously making efforts to increase the quality of the survey. For the year 2016 we have done a number of improvements in the statistical production process which caused break in series. The methodology of the survey has been revised in accordance with the Frascati Manual 2015, definitions have been changed and certain methodological concepts have been broken down in more detail in the questionnaire. Fut+rthermore, the process of data collection and processing has been improved. The data collection instrument is an electronic questionnaire in Excel with embeded controls and notes on methodology. Additional controls have been introduced with regard to the collection of primary data, which, along with repeated contacting of reporting units, had the effect of reducing the non-response rate for certain items. The switch to electronic data collection improved data processing, data editing and tablulation.

Overal assessment of national GBARD methodology is of good quality. Considering the specific structure of government budget, which makes it impossible to list data necessary for calculating GBARD by socio-economic objectives, data are collected directly from government institutions, direct beneficiaries of government budget. We keep close cooperation with the Ministry of Science and Education, which is our main reporting unit, and we throughly analyse all of the items reported in the questionnaire.

See below.

1)       Users' class codification

1- Institutions:
• European level: Commission (DGs, Secretariat General), Council, European Parliament, ECB, other European agencies etc.
• in Member States, at the national or regional level: Ministries of Economy or Finance, other ministries (for sectoral comparisons), National Statistical Institutes and other statistical agencies (norms, training, etc.), and
• International organisations: OECD, UN, IMF, ILO, etc.

2- Social actors: Employers’ associations, trade unions, lobbies, among others, at the European, national or regional level.

3- Media: International or regional media – specialized or for the general public – interested both in figures and analyses or comments. The media are the main channels of statistics to the general public.

4- Researchers and students (Researchers and students need statistics, analyses, ad hoc services, access to specific data.)

5- Enterprises or businesses (Either for their own market analysis, their marketing strategy (large enterprises) or because they offer consultancy services)

6- Other (User class defined for national purposes, different from the previous classes.)

To evaluate if users' needs have been satisfied, the best way is to use user satisfaction surveys.

See below.

The survey covers all mandatory and optional variables laid down in Commission Regulation (EC) No 995/2012 of 26 October 2012 implementing Decision No 1608/2003/EC of the European Parliament and of the Council concerning the production and development of Community statistics on science and technology. All mandatory and voluntary variables were collected. All statistics produced on R&D are available.

Completeness is assessed via comparison of the data delivered against the requirements of Commission Implementing Regulation (EU) No 2020/1197.

1)  Criteria: Obligatory data (provisional budget and final budget). Only 'Very Good' = 100% and 'Very Poor' <100% apply.

2)  Criteria: Optional data (final budget). 'Very Good' = 100%; 'Good' = >75%;'Satisfactory' 50 to 75%%; 'Poor' 25 to 50%; 'Very Poor' 0 to 25%.

See below.

1) Availability of the data: N: No, data are not available, Y: Yes, data are available + start year.

2) Time of compilation: T is assumed to represent the end of reference period, x expresses the number of months after (positive) or before (negative) T when data is compiled

1) Availability of the data: N: No, data are not available, Y: Yes, data are available + start year.

2) Time of compilation: T is assumed to represent the end of reference period, x expresses the number of months after (positive) or before (negative) T when data is compiled

1) Stage: P - provisional, F - final. 

2) Availability of the data: No, data are not available, Y: Yes, data are available + start year.

3) Time of compilation: T is assumed to represent the end of reference period, x expresses the number of months after (positive) or before (negative) T when data is compiled

Accuracy in the statistical sense denotes the closeness of computations or estimates to the exact or true values. Statistics are not equal with the true values because of variability (the statistics change from implementation to implementation of the survey due to random effects) and bias (the average of the possible values of the statistics from implementation to implementation is not equal to the true value due to systematic effects).

Several types of statistical errors occur during the survey process. The following typology of errors has been adopted:

1. Sampling errors. These only affect sample surveys. They are due to the fact that only a subset of the population, usually randomly selected, is enumerated.

2. Non-sampling errors. Non-sampling errors affect sample surveys and complete enumerations alike and comprise:

a) Coverage errors,

b) Measurement errors,

c) Non response errors and

d) Processing errors.

Model assumption errors should be treated under the heading of the respective error they are trying to reduce.

1)  Ranking of the type(s) of errors that result in over/under-estimation, from the most important source of error (1) to the least important source of error (5) In the event that errors of a particular type do not exist, is used the sign ‘-‘.

2)  The perceived direction of the ‘overall’ error using the signs “+” for over estimation, “-” for under estimation and “+/-” when assumption of the direction of the error cannot be made for GBARD.

1) High level of coverage (At least all national or federal ministries and the ministries and agencies responsible for R&D funding at state or regional level). High rate of response (>90%) in data collection. All figures broken down by NABS.  

2) If at least one out of the three criteria described above would not be fully met.

3) In the event that the rate of response would be lower than 80% even by meeting the two remaining criteria.

4) In the event that the average rate of response would be lower than 70% and at least one of the two remaining criteria would not be met.

5) If all the three criteria described above are not met.

Not requested.

Not requested.

Non-sampling errors occur in all phases of a survey. They add to the sampling errors (if present) and contribute to decreasing overall accuracy. It is important to assess their relative weight in the total error and devote appropriate resources for their control and assessment.

Coverage errors are due to divergences between the target population and the frame population. The frame population is the set of target population members that has a chance to be selected into the survey sample. It is a listing of all items in the population from which the sample is drawn that contains contact details as well as sufficient information to perform stratification and sampling.

a)       Description/assessment of coverage errors:

b)      Measures taken to reduce their effect:

There are no over-coverage errors in the survey.

Not requested.

Measurement errors occur during data collection and generate bias by recording values different than the true ones. The survey questionnaire used for data collection may have led to the recording of wrong values.

a)       Description/assessment of measurement errors:

b)      Measures taken to reduce their effect:

Non response errors: occur when a survey failed to collect data on all survey variables from all the population units designated for data collection in a sample or complete enumeration.

a) Problems in obtaining data from targeted information providers: All units responded.

b) Measures taken to reduce their effect: Not applicable.

c) Effect of non-response errors on the produced statistics: Not applicable.

Unit non-response rate is 0%.

Not requested.

Between data collection and the beginning of statistical analysis, data must undergo a certain processing: coding, data entry, data editing, imputation, etc. Errors introduced at these stages are called processing errors. Data editing identifies inconsistencies or errors in the data.

a)       Data processing and editing processes: Data entry errors are minimize by means of consistency controls on key aggregates added to the survey questionnaire (in Excel form) and by means of processing software by visual checking.

b)      Description of errors: So far no processing errors have been identified.

c)       Measures taken to reduce their effect:

Model assumption errors occur when the assumptions made for the estimation of parameters, models, the testing of statistical hypotheses, etc., are violated. As a result, the quality of the resulting statistics is affected (e.g. degrees of confidence might be inflated).

Description/assessment: not aplicable

Timeliness and punctuality refer to time and dates, but in a different manner: the timeliness of statistics reflects the length of time between their availability and the event or phenomenon they describe. Punctuality refers to the time lag between the release date of the data and the target date on which they should have been delivered, with reference to dates announced in the official release calendar.

Date of first release of national data: T+6

Date of first release of national data: T+12

Punctuality refers to the time lag between the release date of data and the target date on which they were scheduled for release as announced officially.

Punctuality of time schedule of data release = (Actual date of the data release) - (Scheduled date of the data release)

See below.

Not requested.

The following table lists a number of key survey concepts and conceptual issues; it gives reference to the Commission Regulation No 2020/1197, Frascati manual and the EBS Methodological Manual on R&D Statistics paragraphs with recommendations about these concepts / issues.

GBARD encompass all spending allocations met from sources of government revenue foreseen within the budget, such as taxation. Spending allocations by extra-budgetary government entities are within the scope only to the extent that their funds are allocated through the budgetary process (FM2015 §12.9). The following table lists a number of key methodological issues, which may affect the international comparability of national GBARD statistics.

See below.

See below.

1)       Breaks years are years for which data are not fully comparable to the previous period.

Government financed GERD covers only R&D performed on national terrirory, and GBARD also includes payments to foreign performers.
Government financed GERD covers R&D financed by all levels of government, while GBARD covers only central government.
GERD includes all sources of funding of R&D conducted on national territory, while GBARD covers only R&D financed by government (inluding abroad).
GBARD covers money allocated in a given year, but government financed GERD shows actual spending because money can be spent by performer in a year later than it was allocated by the funder.

Not requested.

Not requested.

This part compares GBARD statistics from the provisional and final budget for the reference year.

The assessment of costs associated with a statistical product is a rather complicated task since there must exist a mechanism for appointing portions of shared costs (for instance shared IT resources and dissemination channels) and overheads (office space, utility bills etc). The assessment must become detailed and clear enough so that international comparisons among agencies of different structures are feasible. 

1)       The shares of the figures given in the first column that are accounted for by payments to private firms or other Government agencies.

1)        T = the time required to provide the information, including time spent assembling information prior to completing a form or taking part in interview and the time taken up by any subsequent contacts after receipt of the questionnaire (‘Re-contact time’)

Not requested.

Not requested.

Not requested.

a)       Provisional data: 

Data are collected from budgetary and extra-budgetary users of the Government Budget. The Ministry of Science and Education provided data in the Annual Report on the Government Budget Appropriations or Outlays for the R&D Activity ‒ PIIR-1 form, while other government bodies provided data in the Annual Report on the Government Budget Appropriations or Outlays for the R&D Activity ‒ PIIR-2 form.

b)      Final data:

Data are collected from budgetary and extra-budgetary users of the Government Budget. The Ministry of Science and Education provided data in the Annual Report on the Government Budget Appropriations or Outlays for the R&D Activity ‒ PIIR-1 form, while other government bodies provided data in the Annual Report on the Government Budget Appropriations or Outlays for the R&D Activity ‒ PIIR-2 form. 

c)       General University Funds (GUF):

Data from General University Funds (GUF) are collected from all reporting units. Some of them do have resources and some not. The Ministry of Science and Education which provide data in the Annual Report on the Government Budget Appropriations or Outlays for the R&D Activity ‒ PIIR-1 form, often use R&D coefficients for distributing total resources.   

Data is collected annually.

See below.

1) Time of data collection (T+x): T is assumed to represent the end of reference period. x expresses the number of months after (positive) or before (negative) T when data is collected.

General University Funds (GUF) is calculated as an estimation estimated by coefficients collected by R&D survey. The Ministry of Science and Education fills in the total amount od General University Funds (GUF) in the questionnaire PIIR-1. Expenditures for individual fields of science in the GUF category are calculated on the basis of the coefficients obtained from R&D survey.

As already stated above, the statistical survey on budget allocations for research and development, includes budgetary and extra-budgetary users of the state budget in the Republic of Croatia, i.e. all bodies that financed during 2020 and planned to finance R&D activity in 2021. 

First step is  to download from the web the address book of budgetary and extra-budgetary users of the state budget (Register of budgetary and extra-budgetary users). The register of budgetary and extra-budgetary users is established and maintained by the Ministry of Finance for the purposes of determining the scope of budgetary and extra-budgetary users of the general budget. Update it in such a way that 'heads' are taken and a report is sent to them. For example The Ministry of Culture and Media should send a consolidated report for all institutions that are part of it (state archives, archaeological museums, castles, galleries, museums...). It is necessary to carefully check which units to include, because some are not allowed to provide data (e.g. SOA, Information Systems Security Institute), and some are part of the reporting unit from which we received the data. It should be checked whether they have been included (e.g. the State Institute for Radiological and Nuclear Safety, which should be included in the Ministry of Internal Affairs report).

See below.

No data imputation is performed.

See below.

Not requested.

Not requested.