Croatian Bureau of Statistics

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

Ilica 3, 10 000 Zagreb, Croatia

Statistics on Private non-profit R&D (PNPRD) measure research and experimental development (R&D) performed in the private non-profit sector, i.e. R&D expenditure and R&D personnel. In line with this objective the target population for the national R&D survey of the private non-profit sector should consist of all R&D performing units (including all R&D performers – occasional and continuous, known and unknown - in all branches and size classes) belonging to this sector.

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

• The distribution of principal economic activity and by product field is based on Statistical classification of economic activities in the European Community (NACE Rev. 2);
• The local units for the statistics are compiled at regional level according to NUTS 2 – Nomenclature of Territorial Units for Statistics;
• The distribution by socioeconomic objectives (SEO) is based on Nomenclature for the Analysis and Comparisons of Scientific Programmes and Budgets (NABS);
• The fields of research and development based on Classification and distribution by Fields of Research and Development (FORD).

See below.

According to the Frascati Manual, expenditure on extramural R&D (i.e. R&D performed outside the statistical unit) is not included in intramural R&D performance totals (FM, §4.12).

See below.

See below.

Formula is used, which is given as an example in the questionnaire:

3 persons working on R&D half-time (50%) during entire year = 3 x 0.5 = 1.5
2 persons working on R&D part-time (20%) during entire year = 2 x 0.2 = 0.4
1 person working on R&D full-time (100%) half a year = 1 x 0.5 = 0.5
2 persons working on R&D part-time (25%) during 8 months = 2 x (8/12) x 0.25 = 0.3

The statistical unit is the institutional unit as defined by Council Regulation (EEC) No 1993/696 of 15 March 1993.

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 of institutional units.

The objective of the European R&D statistics is to cover all intramural R&D activities. In line with this objective, the target population for the national R&D survey of the PNP Sector should consist of all R&D performing units (including known R&D performers or assumed to perform R&D). In practise however, countries in their R&D surveys might have difficulty in identifying R&D activities at the municipality level. 

R&D statistics cover national and regional data (aggregates for NUTS 1 and NUTS 2) accordind to Statistical Classification of Economic Activities in the European Community – NACE Rev. 2.1.

Calendar year 2021

Not requested.

Main R&D indicators are available according to 4 main indicators:

• Gross domestic expenditure in thousand of national currency (kuna)
• share of research and development (R&D) expenditures in GDP (%)
• R&D personnel (headcount and FTE)
• number of performing units

Calendar year 2021

See below.

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

- European Business Statistics Methodological Manual on R&D

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.

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.

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.

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, thus abiding by the Principle of Timeliness of the European Statistics Code of Practice, i.e. standard daily time set for the release.

R&D is conducted and disseminated annually at the end of October as First release and at the beggining of July as PC-Axis data base.

See below.

1) Y - Yes, N – No

See below.

1) Y – Yes, N - No 

R&D database in PC-Axis is available on CBS website. 

Not requested.

See below.

See below.

Not requested.

1) Y – Yes, N - No 

Methodological documents are published as a part of First Release and are available on the website of the Croatian Bureau of Statistics.

The meta-information available together with the data published in official First Release – part “Notes on methodology” are information about Data sources, comparability and short interpretation and analysis of results.

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. Furthermore, 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.

For the reference year 2021 we improved the survey coverage which enabled us to identify unknown R&D performing units. The sources we have used are explained in section 2.1. Data description. The analysis of the mentioned sources resulted in adding 7 units to the basic list of PNP reporting units, out of which 3 units reported R&D activities. Total PNP population was 17 units. 

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.

Share of PNP R&D expenditure in GERD (Gross Domestic Expenditure on R&D):

1) This question is optional. It refers to variables and breakdowns NOT asked by the Commission Implementing Regulation (EU) No 2020/1197 (neither as 'optional').

2) Y-start year

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.

That part of the difference between a population value and an estimate thereof, derived from a random sample, which is due to the fact that only a subset of the population is enumerated.

The main indicator used to measure sampling errors is the coefficient of variation (CV). 
Definition of coefficient of variation: 
CV= (Square root of the estimate of the sampling variance) / (Estimated value)

Coefficient of variation for Total R&D expenditure : Not applicable. No sampling is used.

Coefficient of variation for Total R&D personnel (FTE) : Not applicable. No sampling is used.

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.

a)       Extent of non-sampling errors: not applicable

b)       Measures taken to reduce the extent of non-sampling errors: not applicable

c)       Methods used in order to correct / adjust for such errors: not applicable

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.

There are no units accessible via the frame that do not belong to the target population.

Not requested.

Measurement errors occur during data collection and generate bias by recording values different than the true ones (e.g. difficulty to distinguish intramural from extramural R&D Expenditure). The survey questionnaire used for data collection may have led to the recording of wrong values, or there may be respondent or interviewer bias.

a)       Description/assessment of measurement errors:

b)      Measures taken to reduce their effect:

Non-response occurs 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.

There are two elements of non-response:

-Unit non-response which occurs when no data (or so little as to be unusable) are collected on a designated population unit.

-Item non-response which occurs when data only on some, but not all survey variables are collected on a designated population unit.

The extent of response (and accordingly of non response) is also measured with response rates. 

The main interest is to judge if the response from the target population was satisfactory by computing the un-weighted response rate.

Definition: Eligible are the survey units which indeed belong to the target population. Frame imperfections always leave the possibility that some units may not belong to the target population. Moreover, when there is no contact with certain units and no other way to establish their eligibility they are characterised as ‘unknown eligibility units’.

Un-weighted Unit Non- Response Rate = 1 - (Number of units with a response) / (Total number of eligible and unknown eligibility units in the survey) 

Total number of units in the survey: 17

Number of units with a response in the survey: 7

Unit non-response rate (Un-weighted): 58,8%

There are no units which have not responded to a particular item. During post-field control of received questionnaires the reporting units are subsequently contacted due to blank or poorly answered questions. This is the reason there are no unanswered variables and that the data collected are of very good quality.

Data were collected by electronic questionnaire in Excel. After the data collection and control of each questionnaire, Excel files were imported as txt files in Survey Processor Application for further computer logical and mathematical control. Coding was not performed because the Excel questionnaire contained drop-down lists for NABS, industrial orientation and fields of science.

Since 2016, for the data collection we use electronic questionnaires in Excel. The questionnaire is designed in a way that respondents only have to enter data for specific categories and the built-in formulas calculate totals and subtotals. The questionnaire also has built-in logical control of the major categories in different tables (for example, the number of researchers has to be the same in all tables). The number of errors in the questionnaires has decreased drastically due to these built-in warnings and controls, which has caused the drastical decrease of errors in the phase of computer editing. Procedure used to correct errors or missing values was re-contact with information provider.

Not requested.

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.

Time lag between the end of reference period and the release date of the results:
Indicator: (Release date of provisional/ first results) - (Date of reference for the data)

a) End of reference period: 31.12.2021.

b) Date of first release of national data: 31.10.2022.

c) Lag (days): T+10

a) End of reference period: 31.12.2021.

b) Date of first release of national data: 31.10.2022.

c) Lag (days): T+10

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.

R&D statistics is fully conducted and produced according to the Frascati methodology.

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

The following table lists a number of key methodological issues, which may affect the international comparability of national R&D statistics. The table gives the references in the Frascati manual, where related recommendations are made. Countries are asked to report on the existence of any deviations from existing recommendations and comment upon.

See below.

See below.

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

Data in the even years are produced in the same way as in the odd years.

See below.

Not requested.

SNA classification was used for the reference year 2019 for institutional sector of units in the target population.

R&D data were used by our colleagues in the National Accounts for the calculation of regional investments.

See below.

This part compares key R&D variables as preliminary and final data.

(1)    Calculate the average remuneration (cost) of individuals belonging to the internal R&D personnel, excluding those who are only formally ‘employees’ (university students, grant holders, etc.).

(2)    Calculate the average remuneration (cost) of individuals belonging to the external R&D personnel (FTEs/other current R&D costs for external R&D personnel).

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.

Several separate activities are used for the collection of raw data or pre-compiled administrative data and statistics related to R&D. For simplicity, we call them surveys irrespective of whether they are sample surveys, censuses, collections of administrative data/pre-compiled statistics. This section presents the names of the surveys by sector of performance as well as methodological information for each survey. Depending on the type of survey and sector of performance, only the sections corresponding to that survey and sector are filled in.

Data is collected annually.

See below.

Source data are checked by means of visual control (checking if all requested data are filled in, checking for logical or numerical inconsistencies - within a single table and several tables of the questionnaire). In case of incomplete, illogical or incorrect answers, we contact the respondents. Reported data are then compared with previous cycles, and in case of larger discrepancies we contact the respondents in order to verify the reported data. We compare data on employed personnel and R&D expenditures with data in the statistical business register. Even though Excel questionnaires have built-in controls to decrease data entry errors, each report is additionally checked in Survey Processor application. Aggregated data are checked again for inconsistencies and outliers.

See below.

Imputation is the method of creating plausible (but artificial) substitute values for all those missing.
Definition:
Imputation rate (for the variable x) % = (Number of imputed records for the variable x) / (Total number of possible records for x)*100

Not requested.

Not requested.

No comments.