Methodology and Quality Update

Latest Update on Methodology and Quality

09/07/2026

Statistical Presentation

Data description

Wholesale and retail trade statistics provide quarterly short-term data on the wholesale and retail trade sector and reflect the economic performance of establishments operating in this sector in Saudi Arabia.
It is a statistical product conducted to collect data on the following main characteristics:

• Operating revenues.
• Electronic commerce sales.
  Data is also used to estimates:
• Index and growth rates of compensation of employees.
• Index and growth rates of operating revenues.
• E-commerce sales index and growth rates.

 Classifications

The following classification is applied in the Wholesale and Retail Trade Statistics.
National Classification of Economic Activities (SSIC):
It is a statistical classification based on the International Standard Industrial Classification of All Economic Activities (ISIC4), and it is used to describe the productive activities of an establishment. 
The classifications are available on the GASTAT’s website: 
The National Classification for Economic Activities

 Statistical concepts and definitions

Terminologies and concepts of the Wholesale and Retail Trade Statistics publication:

• Wholesale trade:
  Resale of goods (without transformation) to retailers or to users for industrial or commercial purposes.
• Retail trade:
  Resale of goods (without transformation) to the public for personal or household consumption.
• Establishment:
  An establishment, or part of an establishment, with a fixed location, that carries out one or more economic activities under a single management and has, or can have, regular accounts. The owner of the establishment may be either a natural or a legal person.
• Main economic activity:
  The activity carried out by the establishment that accounts for the largest share of the total value of its production.
• Compensations of Employees:
  All amounts of wages, salaries, in-kind benefits, and social contributions payable to employees during the accounting period in return for work performed, whether in cash or in kind, before any deductions such as social insurance contributions, taxes, and similar items.
• Operating revenues:
  Cash revenues generated from the establishment’s main economic activity or other secondary activities, such as the sale and marketing of its products, the provision of services to consumers, or the trading of goods in general. It also includes daily operating receipts. These revenues comprise the total value of sales of manufactured products, in addition to other operating revenues not directly related to the establishment’s main economic activity but associated with its secondary activities.
  They include revenues from industrial services, secondary activities, the sale of production waste, and the rental of non-agricultural buildings and land, as well as the leasing of machinery and equipment, etc., and any other operating revenues, provided that their types are specified. etc., and any other operating revenues, provided that their types are specified.
• Electronic sales (electronic commerce):
  Commonly known as electronic commerce. It includes the buying and selling of products or services through electronic systems such as the internet or other computer networks.
  This business model relies on innovation, supply chain management, internet marketing, online transaction processing, electronic data interchange, warehouse management, and automated data collection systems.

Data sources

The primary data source for the Wholesale and Retail Trade Statistics is the Short-term Business Statistics Survey. 
The main variables targeted for dissemination in the Wholesale and Retail Trade Statistics are:

• Employee compensation
• Operating revenues.
• Electronic commerce sales.
• Motor vehicle sales.

Designing the data collection tool

The Wholesale and Retail Trade Statistics rely on the Short-term Business Statistics questionnaire, which was prepared and designed by specialists at the General Authority for Statistics (GASTAT). The data collection tool was designed in electronic formats (CAPI), (CATI), and (CAWI) to ensure ease of use by field researchers. International recommendations, standards, and definitions were taken into consideration in designing the tool. It was also shared with relevant entities to obtain their views and feedback. Furthermore, the questions were formulated in a specific scientific manner to standardize the wording of the questions.
The latest update to the questionnaire design was carried out in 2023.
The Short-term Business Survey questionnaire consists of several sections: 

• 101: Type of economic activity
• 102: Number of paid employees.
• 103: Number of unpaid employees.
• 104: Compensation of employees.
• 105: Operating revenues
• 106: Job vacancies
• 107: Operational expenses
• 108: E-commerce sales
• 109: Changes in fixed assets.

Review and validation rules:
Validation and consistency rules are incorporated into the questionnaire to ensure that the collected data is consistent, accurate, and logical. These rules were designed by establishing logical relationships between responses, questions, and various variables to assist the field researcher in directly detecting any errors during data entry.
To ensure the quality of the Short-term Business Statistics data, three types of validation and editing rules have been established, as follows:

• Navigation rules between sections and fields:
  Specific rules were programmed to regulate the automatic navigation between sections and fields based on the respondent’s inputs. There are two navigation rules.
• Error rules:
  These are rules that cannot be bypassed during the data entry process. The field researcher must correct the data by referring back to the respondent to verify its accuracy. There are four such rules.
• Warning rules:
  These are rules established to verify the accuracy of the data entered by the field researcher. The field researcher may override them after confirming the accuracy of the data. There are four such rules.

Questionnaire test (cognitive test)

Cognitive testing was conducted on several questionnaire items. The interview sample consisted of a random sample of establishments distributed across the regions of Saudi Arabia.
During the cognitive testing process, the following evaluation pillars were taken into consideration: The overall concept of the question, clarity of question wording, clarity of terms used in the question, appropriateness of the response options, participants’ ability to answer the questions effectively, and the extent to which participants were willing to disclose their answers. This process resulted in a report summarizing the full findings of the cognitive test.

Statistical population

The statistical population of the Wholesale and Retail Trade Statistics survey consists of all economic establishments of various sizes: Micro, small, medium, and large establishments that engage in wholesale and retail trade activities, and the repair and maintenance of motor vehicles according to the ISIC4 classification, and are classified as commercial entities through operational licenses issued by government entities in Saudi Arabia.

Sample Design

The sample was designed using the stratified systematic random sampling method, whereby a systematic random sample of establishments was selected from each stratum of the approved sample design.
Stratification:
To increase the efficiency of the sample and improve its representation of the target population, establishments in the sampling frame were classified into homogeneous strata. In order to obtain more accurate results compared to the simple random sampling method of the same size, and to ensure an adequate number of establishments at publishable levels, a two-level stratification approach was applied as follows:
Stratification at the 2-digit level of economic activity (ISIC4).
Stratification by establishment size categories, which are:

• Micro enterprises:
  Establishments with 1 to 5 employees.
• Small enterprises:
  Establishments with 6 to 49 employees.
• Medium enterprises:
  Establishments with 50 to 249 employees.
• Large enterprises:
  Establishments with more than 249 employees.

Sample size:
The sample size was calculated at the first-level (division) of the economic activity classification (ISIC4) to ensure the production of reliable estimates at this level (publication level) as well as at the national level. Based on the request of the survey-owning department, it was decided to include all large establishments within the sample. 
Parameters used in estimating the sample size:

• The total number of establishments in the frame at the first level (division) of the economic activity classification (ISIC4).
• The mean and variance at the first level (division) of the economic activity classification (ISIC4) for estimating the average number of employees, based on data from the previous survey round (September 2023).
• The design effect at the first level (division) of the economic activity classification (ISIC4) for estimating the average number of employees, based on data from the previous survey round (September 2023).
• The response rate at the first level (division) of the economic activity classification (ISIC4) for estimating the average number of employees, based on data from the previous survey round (September 2023), with a specified acceptable minimum threshold.
• The allowable relative margin of error.
• A confidence level was used in estimating the average number of employees(1-α)=0.95.
  The sample size for each study domain at the fourth level of ISIC4 was determined using the following equation:
  
  Whereas:
• n_h : Sample size for each stratum h   (study domain).
• Deff_h : Estimated design effect for each stratum h  (study domain).
• resp_h : Estimated response rate for each stratum h   (study domain).
• S_h : Standard deviation for each stratum h  (study domain).
• α : Confidence level factor in estimating the indicator for each stratum h  (study domain).
• re_h : Allowed relative error in estimating the indicator for each stratum h  (study domain).
• : Average of the indicator for each stratum h  (study domain).
• Nh : Total establishments for each stratum  h (study domain) in the frame.

The result of the sample size calculation, using the previously mentioned equation, was distributed across the establishment size classes for each study domain. Large establishments within the same stratum were then excluded, as all large establishments were included in the sample with a 100% selection probability due to their importance. The remaining estimated sample size for each stratum was subsequently distributed across the three remaining size classes using power allocation.
This is followed by the final step of distributing the sample at the second level of the economic activity classification (ISIC4), using the Probability Proportional to Size (PPS) allocation method, as this approach reduces the variance of the weighting factors, thereby reducing the variance of the estimates and increasing the efficiency of the design. 
The calculations outlined above resulted in a total sample size of 12,575 establishments, distributed as shown in the tables below:
Table: Distribution of the survey sample at the first level (division) of the economic activity classification (ISIC4):
 

Statistical unit

The statistical unit in the Wholesale and Retail Trade Statistics is the establishment engaged in economic activities.

Data collection

Survey data collection:
Data for the Wholesale and Retail Trade Statistics are collected through the Short-term Business Statistics Survey using Computer-Assisted Telephone Interviewing (CATI), Computer-Assisted Web Interviewing (CAWI), or Computer-Assisted Personal Interviewing (CAPI).
These data are stored in GASTAT’s databases after undergoing validation and review processes in accordance with approved statistical methods and recognized quality standards. The data source is contacted whenever errors are detected or observations are identified in the data. The data are also examined to ensure consistency, completeness, and logical coherence, as well as to verify the absence of duplicate records.

Data collection frequency 

The data collection process for the Wholesale and Retail Trade Statistics is carried out on a quarterly basis.

Reference area

The Wholesale and Retail Trade Statistics cover all thirteen administrative regions in Saudi Arabia.

Reference period (time reference)

The reference period for the variables or dataset is as follows:
The data of the Wholesale and Retail Trade Statistics is based on the quarter preceding the data collection period.

Base period

The base year used is 2023.

Measurement unit

Some indicators are calculated as rates (e.g., Compensation of employees' index and growth rate).

Time coverage

Data are available for the period 2016–2026.

Publication frequency

The results of the Wholesale and Retail Trade Statistics are disseminated quarterly in accordance with the approved statistical plan.

Statistical processing

Error detection

Rigorous procedures are implemented to detect errors in the data collected during the survey and stored in the data lake. This is achieved through the automation of the data collection tool and the implementation of the necessary controls and validation procedures for managing the entered data, thereby ensuring quality, accuracy, and consistency. In addition, quality indicators, such as the survey response rate, are measured to support the assessment of data quality.
All data is regularly entered into the data collection system upon receipt. The specialized team ensures that the data is entered correctly and accurately. The data are checked for completeness and reviewed to ensure that they have been correctly incorporated into the system.
Treatment of outliers:
Outliers or out-of-range values are identified using standardized validation rules and approved statistical methods.

Data integration and matching from multiple sources 

Data extracted from administrative sources is used in conjunction with survey data to produce the final indicators.

Imputation and calibration

Compensation (for non-response cases or incomplete datasets): 
The approach used for imputation in the Wholesale and Retail Trade Statistics Survey, whether for establishments with complete non-response or for missing data on specific variables. Follow-up interviews may be conducted to obtain missing data from respondents or to address cases of non-response. Subsequently, missing data and non-response cases are handled in accordance with a scientific methodology for producing estimates, taking into account several factors, including historical data series, monthly growth rates by economic activity, acceptable thresholds for missing data, and estimates based on stratum-level data.
Formulas used:
Average monthly employee compensation in the establishment =

Average compensation of employees in the stratum =

Compensation of employees for the target quarter = Compensation of employees for the previous quarter × Compensation growth rate in the stratum for the target quarter

Average monthly revenue per employee in the establishment =

Average operating revenue in the stratum =

Operating revenue for the target quarter = Operating revenue for the previous quarter × Operating revenue growth rate in the stratum for the target quarter

Weighting:
The basic sample weights are calculated based on the strata used in the sample design and allocation. The selection probability of establishment i in stratum h is denoted by π_hi  . Accordingly, the weight of the establishment selected in the sample is calculated as follows:

Non-response weight adjustment:
Weight adjustment is applied to compensate for non-response or missing data and to ensure adequate sample representation. This adjustment is carried out after data collection and processing, once response statuses have been identified, according to the following equation: 

Denotes the non-response adjusted weight in the stratum (or adjustment class), where the adjustment factor for each stratum (or adjustment class) is calculated as follows:

Where R represents the responses, and NR represents the non-responses.

Seasonal adjustments

Not applicable, as the Wholesale and Retail Trade Statistics is conducted on a quarterly basis.

Adjustment of preliminary results 

Preliminary statistical outputs are reviewed and updated after the completion of data processing to correct identified errors or improve accuracy based on internal reviews. The data are updated within 90 days of the publication of the preliminary results, and any differences between the preliminary and final results are documented and communicated to users.

Used Resources

Quality dimensions

Suitability 

A criterion that indicates the extent to which the product meets users’ needs.

User needs 

Internal users of the Wholesale and Retail Trade Statistics data within GASTAT:

• National accounts.

Several external users and beneficiaries make extensive use of the Wholesale and Retail Trade Statistics, including:

• Government entities.
• Regional and international organizations.
• Research institutions.
• Media.
• Individuals.

Key variables used by external users:
 

Completeness 

The data are complete, and the indicators have been designed to provide comprehensive coverage of all targeted activities. Detailed indicators are provided according to the National Classification of Economic Activities (SSIC) at the second level, ensuring a comprehensive and integrated representation of all relevant economic activities.
    Accuracy and reliability 
A measure of the extent to which calculations or estimates are close to the true values that reflect reality.

Overall accuracy 

• Data quality is enhanced through the selection of researchers based on a set of practical and objective criteria related to the nature of the work, as well as their qualifications and training.
• Alert, validation, and correction rules are applied during the data collection process through the electronic questionnaire of the Wholesale and Retail Trade Statistics to enhance data quality.
• The data is examined against previous years to identify any significant changes.
• The internal consistency of the data is checked before it is finalized.
• The links between variables are checked, and coherence between different data series is confirmed.

Timeliness and punctuality 

Timeliness: A standard that indicates the length of time between the availability of information and the occurrence of the event.
Punctuality: It reflects the time lag between the data publication date and the target date when publication actually occurs.

Timeliness 

GASTAT applies the Special Data Dissemination Standard (SDDS) issued by the International Monetary Fund (IMF). According to this standard, all statistical agencies are required to publish data on a quarterly basis, with a time lag not exceeding one quarter (90 days) after the end of the reference period. If the data are from different sources, they may be published at different frequencies.

Punctuality 

Publication takes place in accordance with the release dates specified in the published statistical calendar for the Wholesale and Retail Trade Statistics on GASTAT’s website.
The data are made available at the scheduled time, as specified in the statistical calendar. If publication is delayed, the reasons for the delay will be provided.

Coherence and comparability

A standard that refers to the necessity of internal and temporal consistency of statistics, their logical coherence, and their comparability and integration across different regions and sources.

Comparability - geographical

Statistical data related to the Wholesale and Retail Trade Statistics are fully comparable geographically within Saudi Arabia, as well as at the regional and international levels.

Comparability - over time

 The survey was first conducted in 2016 as an annual survey. In 2018 and 2019, its frequency was changed to a quarterly basis. It was then temporarily suspended for development purposes. 
In the first quarter of 2023, the survey was relaunched following transformation and development efforts. It was integrated with the Short-term Business Statistics Survey in terms of the questionnaire, sample, and data collection methodology, and data collection activities resumed in accordance with the updated methodology.

Coherence- Cross-domain

The data are consistent, as consistency was verified across the different classification levels in accordance with ISIC4. It was confirmed that the data classified at the first level (Short-term Business Statistics Survey) are consistent with the detailed data available at the second level (Wholesale and Retail Trade Statistics Survey). These procedures ensure consistency and coherence across classification levels, thereby enhancing the reliability of the data and the quality of the resulting analysis, and ensuring that the results are free from contradictions.

Coherence- Sub-annual and annual statistics 

Not applicable, as the Wholesale and Retail Trade Statistics are published on a quarterly basis, and no monthly or annual publications are issued. 

Coherence- National Accounts 

The Wholesale and Retail Trade Statistics are integrated with national accounts requirements through the adoption of statistical classifications. The results of the publication are used as key inputs for compiling Gross Domestic Product (GDP) within the national accounts framework. Continuous coordination with national accounts statistics ensures consistency between the publication's results and macroeconomic indicators.

Coherence- Internal 

The Wholesale and Retail Trade Statistics are integrated with national accounts requirements through the adoption of statistical classifications. The results of the publication are used as key inputs for compiling Gross Domestic Product (GDP) within the national accounts framework. Continuous coordination with national accounts statistics ensures consistency between the publication's results and macroeconomic indicators.

Accessibility and clarity

It refers to the extent to which users can access data, the availability of detailed and aggregated data, and the availability of the Methodology and Quality Report.

Press releases

The announcements for each publication are available on the statistical calendar as mentioned in 10.1. The press releases can be viewed on the website of GASTAT on the link: 
Press release

Publications

GASTAT issues the Wholesale and Retail Trade Statistics publications and reports regularly in accordance with a pre-approved dissemination plan, and they are published on the Authority’s website. GASTAT is committed to publishing its results in a manner that serves all users. Publications are made available in various formats and include statistical tables, charts of data and indicators, the Methodology and Quality Report, and the questionnaires used, in both Arabic and English.
The results of the Wholesale and Retail Trade Statistics are available on:
Wholesale and Retail Trade Statistics

Online database

The data is published on the statistical database:
GASTAT (stats.gov.sa)

Microdata accessibility

Accurate data is unit-level disaggregated data obtained from multiple sources such as sample statistical surveys, general population and housing censuses, and administrative systems, providing detailed information about the characteristics of individuals, families, business entities, and geographical areas, supporting the construction and development of statistical indicators and scientific research.
Different types of microdata files are available to meet diverse information needs.

• Public use: 
  ‌‌It consists of sets of records containing information on individuals, households, or business entities anonymized in such a way that the respondent cannot be identified either directly, such as by name, address, contact number, identity number, etc., or indirectly (by combining different – especially rare – characteristics of respondents), such as age, occupation, education, etc.
• Scientific use:
  These datasets are created in accordance with specific methodologies at the request of data users to produce datasets with defined characteristics for use in strategic studies, decision-making, and scientific research. The datasets may relate to individuals, households, or enterprises, while ensuring that they contain no direct identifiers and are subject to confidentiality protection controls.
  Qualified users who meet the standards and procedures of confidentiality protection can access the files of scientific use of accurate data through the platform "ITAHA" of the General Authority for Statistics, while the most sensitive data for use is shared by visiting the accurate data laboratory within a secure environment managed by the Authority.

References and standards

Methodological Manual for European Short-term Business Statistics (2021 Edition):
The methodological manual of European short-term business statistics
System of National Accounts 2008:
System of National Accounts

Quality assurance

GASTAT is committed to adhering to the following principles: Impartiality; user-oriented statistical products; quality of processes and outputs; effectiveness of statistical operations; and reduced respondent burden. 
Data are validated through quality assurance procedures and controls implemented at various stages of the statistical process, including: data entry, data collection, and other final controls.

Quality assessment

GASTAT conducts all statistical activities in accordance with the National Version of the Generic Statistical Business Process Model (GSBPM). During the comprehensive evaluation phase, which is the final phase of the GSBPM, information collected throughout each phase and sub-process is used to prepare an evaluation report that summarizes all quality-related challenges associated with each statistical process. The report serves as an input for continuous improvement and development initiatives.

Confidentiality

Confidentiality - Policy

According to Royal Decree No. 23 dated 07/12/1379, data must always be kept confidential and must be used by GASTAT for statistical purposes only.
Therefore, the data is protected in the data servers of GASTAT.

Confidentiality - Data Treatment

Data of SMEs survey are presented in right tables in order to summarize, understand, as well as extract their results. Moreover, to compare them with other data, and to obtain statistical significance about the selected study population. However, referring to such data indicated in tables is much easier than going back to check the original questionnaire that may include some data like: names and addresses of individuals, and names of data providers, which violates data confidentiality of statistical data.
“Anonymity of data” is one of the most important procedures. To keep data confidential,

GASTAT removed information on individual persons, households, or business entities in such a way that the respondent cannot be identified either directly, such as by name, address, contact number, identity number, etc., or indirectly by combining different, especially rare, characteristics of respondents, such as age, occupation, education, etc.

Dissemination policy

Statistical calendar

The Wholesale and Retail Trade Statistics are included in the statistical calendar.
Statistical Calendar

User access

One of GASTAT’s objectives is to better meet users’ needs. Therefore, the results of the Wholesale and Retail Trade Statistics publication are made available immediately upon publication.
GASTAT also receives users’ questions and inquiries regarding the publication and its results through various communication channels, such as:

• GASTAT’s official website:  www.stats.gov.sa
• GASTAT’s official email address:  info@stats.gov.sa
• Official visits to GASTAT’s official head office in Riyadh or one of its branches in Saudi Arabia.
• Official letters.
• Statistical telephone: (199009).