1) classification - the division of many objects into groups according to similarity or difference in accordance with accepted characteristics;
2) imputation - the process of replacing missing, incorrect or inconsistent values with other values;
3) the weight of the index is a value that reflects the significance of each individual element in their total population;
4) metadata - data on statistical data, including data and other documentation describing objects in a formalized way;
5) weighing - a procedure used in index calculations to obtain summary indicators and ensuring the commensurability of different goods that are not directly amenable to summation;
6) official statistical information - statistical information generated by state statistics bodies in accordance with the Statistical Work Plan;
7) statistical information - aggregated data obtained in the process of processing primary statistical data and (or) administrative data;
8) a statistical indicator is a qualitative characteristic of socio-economic phenomena and processes in society, reflecting the essence of a phenomenon or process in specific conditions of place and time;
9) selection - individual items from the approved classifiers, nomenclatures and reference books used in the collection and processing of statistical data,
as well as the following terms and definitions in the meanings defined by the State standard of the Republic of Kazakhstan ST RK ISO 9000-2007 “Basic Provisions. Dictionary":
10) information - meaningful data;
11) validation - confirmation by presenting objective evidence that the requirements for a specific intended use or application have been met;
12) system - a set of interconnected and interacting elements;
13) effectiveness - the relationship between the achieved result and the resources used;
14) production environment - a set of conditions in which work is performed;
15) products - the result of the process;
16) procedure - an established method of carrying out an activity or process;
17) quality - the degree to which the set of inherent characteristics meets the requirements;
18) quality management - a part of quality management aimed at fulfilling quality requirements;
19) quality assurance - part of the quality management aimed at creating confidence that the quality requirements will be met;
20) process - a set of interconnected and interacting activities that transform inputs into outputs;
21) analysis - activities undertaken to establish the suitability, adequacy, effectiveness of the facility in question to achieve established goals;
22) efficiency - the degree of implementation of planned activities and achievement of planned results.
1) study of needs;
2) design of the production process;
3) the construction of the production process;
4) collection of primary statistics;
5) data processing;
6) data analysis;
7) dissemination of official statistical information;
8) assessment of the production cycle.
In this Standard Methodology, state statistics bodies adhere only to those processes and subprocesses that they apply in their activities in the formation of national and departmental statistical observations.
1) determining the needs of users involves the study and determination of relevant statistical information. This need is determined on the basis of a study of the practice of national and international organizations involved in the production of similar data and, in particular, methods of accounting for the special needs of users;
2) for a deep understanding of the needs of users in statistical information, including the timing of presentation, the purpose of its further use, it is necessary for the state body (hereinafter referred to as the state agency-developer) to conduct consultations with interested parties taking into account previously identified user needs;
3) based on the results of consultations, the state agency-developer develops statistical indicators containing the required information. These statistical indicators are subject to clarification with users on their compliance with the needs and quality characteristics. In determining the goals of generating a statistical indicator, it is necessary to take into account data confidentiality aspects and the availability of resources;
4) determination of the list of required data corresponding to the satisfaction of needs within the framework of the proposed process;
5) in order to establish the conformity of the data sources used to the needs of users, determine the conditions under which the data will be obtained, including any restrictions on their use, as well as check for duplication of indicators, the state body-developer checks the availability of data. It provides an assessment of the legal framework within which the collection and use of primary statistics will be carried out, as a result of which there may be a need to consider proposals for amending existing legislation or establishing new legislative frameworks;
6) a subprocess for the preparation of a business model documents the conclusions of other subprocesses of this stage in the form of a business model for obtaining approval for the implementation of a new or modified production of statistical information. This statistical information meets the requirements of the government agency-developer and includes the following elements:
a description of existing business processes with information on the implementation of the current production of statistical information, indicating deficiencies, as well as issues that need to be addressed; һ
Proposed promising solutions with a detailed indication of the development of business processes for the production of new or revised statistics;
an assessment of costs and benefits, as well as any other constraints.
1) provides for the design by the state agency-developer of the statistical information planned for release, including the development and preparation of tools necessary at the dissemination stage. Input resources in the design of statistical publications include metadata obtained from previous collections of statistical information;
2) determines the need for the preparation of metadata descriptions for the collected and retrieved variables and their classifications;
3) determine the methods and mechanisms that are most suitable for the collection of primary statistics. In fact, the work within this subprocess varies depending on the type of collection mechanisms. The subprocess includes designing collection mechanisms, sample questions and answers, as well as designing any formal agreements related to the provision of data, such as memoranda of understanding, and confirmation of the collection of primary statistics;
4) the design of the population and the sample is applied only to processes related to the collection of data based on the sample, for example, through statistical observations. The subprocess is used in the preparation of the sampling plan and the register used for this, and also sets the most suitable criteria and sampling methods. Sources for sampling are administrative and statistical registers, censuses, and information obtained from other sample surveys. If necessary, the government agency-developer combines the sources;
5) the design of processing and analysis offers a methodology for the processing of statistical information for its implementation at the stages of "Processing of primary statistical data" and "Data Analysis". It includes clarification of coding, editing, calculus, estimation, integration, confirmation and finalization methods in the aggregate data;
6) defines the production process, starting with the collection of primary statistical data and ending with the dissemination of official statistical information, providing a general overview of the processes required throughout the production cycle of statistical information, and also ensures the effectiveness of interaction without any gaps or redundancy. The subprocess tracks the analysis of the interaction of employees with systems, and also determines their responsibility.
1) the construction of a data collection mechanism describes the work on the construction of a data collection mechanism, which will be used at the stage of “Collection of primary statistics”. The collection is carried out using one or more methods of obtaining data, such as: personal or telephone surveys, paper, electronic or online questionnaires. The collection mechanism is created in accordance with the plans developed at the stage of “Designing the production process”. This subprocess also includes the preparation and testing of content, the functioning of appropriate tools, for example, checking questions in a statistical form;
2) the construction or strengthening of the components of the process includes the procedures and functions of the information panel, information services, transformations, work systems, services for working with respondents and metadata;
3) the construction or strengthening of dissemination components describes the work on building new and strengthening existing components and services necessary for the dissemination of official statistical information defined in the sub-process “Designing a statistical publication”. It includes all components and services for the dissemination of official statistical information, from those used to produce traditional paper publications, to those that provide web services, the production of open data;
4) the layout of production processes provides the layout of production processes, systems and transformations used in the framework of statistical production, from the collection of primary statistical data to the dissemination of official statistical information. The subprocess ensures the functioning of the practical production process created in the subprocess "Design of production systems and process";
5) testing of the production system represents testing of the assembled and completed services and related production processes, provides for the verification of their interactions, and also ensures the operability of the production solution as a well-coordinated set of processes;
6) testing a statistical business process describes the work of conducting field trials, the pilot use of a statistical business process. Subprocess leaves the possibility of making adjustments to mechanisms, systems or components;
7) the commissioning of the production system includes the commissioning of integrated and complete processes and services, including modified and newly created services, for use by industry departments.
1) the formation of the general population and the sample for a given process involves the coordination of samples between events of the same statistical process and between different processes that use a common basis or common register. Also, within the framework of this subprocess, work is underway to ensure quality and approve the population and the sample;
2) the organization of the collection of primary statistical data ensures the readiness of employees, processes and technologies to collect information in all planned modes and includes:
preparation for the collection;
training for collection staff (interviewers);
ensuring the availability of funds for the collection;
acquisition systems for requesting and receiving data;
ensuring the protection of data to be collected;
preparation of collection tools (printing of questionnaires, downloading of questionnaires and data to computers of meters).
For non-survey data sources, the subprocess includes ensuring the availability of processes, systems and privacy procedures to obtain and extract the necessary information from the source;
3) the collection of primary statistical data is carried out using various means for collecting information, includes:
raw data or aggregated data received from a source of information;
initial contact with respondents and any further follow-up activities.
Manual entry of information at the point of contact or monitoring of field work is also possible, depending on the source and method of collection;
4) the completion of the collection of primary statistical data provides for the loading of the collected primary statistical data into the appropriate electronic environment for further processing. Includes manual or automatic data loading.
description of the data cleaning process and its preparation for analysis;
consists of subprocesses dedicated to the verification, cleaning and conversion of input data for the purpose of analysis and dissemination as official statistical information:
1) data integration is based on a combination of the results of the process “Collection of primary statistics”. Input data come from various external and internal sources and are the result of various collection methods. The result is a set of linked data. After integration, depending on the protection requirements, the data can be anonymized (deprived of identifiers such as name and address) in order to protect confidentiality;
2) classification and coding are carried out automatically (or manually), performed by assigning digital codes to text responses in accordance with a predefined classification system;
3) the verification and validation subprocess allows checking data for possible detection of potential problems, errors and discrepancies, such as sharply deviating values, lack of answers to the question and erroneous coding;
4) editing and imputation means adding new values using a variety of methods if the data are recognized inaccurate, missing and unreliable. Specific steps:
definition of adding and changing data;
selection of the used editing method;
Adding or changing data values
adding new data values to the data set and designating them as changed;
production of metadata through the editing and imputation process;
5) as part of the formation of new derived variables and statistical units, the data are calculated for the variables and statistical units that were not clearly allocated at the collection stage, but are necessary for the production of the desired data. This subprocess forms new derived variables by applying arithmetic formulas to one or more variables that are already present in the data set, or by applying various model hypotheses;
6) the calculation of the weight of the index creates weighting factors for individual data arrays according to the statistical methodology created in the framework of the subprocess “Design of processing and analysis”;
7) the calculation of aggregates involves the summation of data from accounts that have common certain characteristics, as well as the determination of average indicators and indicators of dispersion, weighing;
1) the preparation of preliminary statistical information is carried out by converting the data into statistical information. The subprocess involves the creation of additional indicators, such as indices, trends or seasonally adjusted time series, as well as registration of qualitative characteristics;
2) validation includes work aimed at determining the compliance of the collection and generation of information with the previously presented requirements for the expected results;
3) the interpretation and clarification of statistical information creates the basis for the correct interpretation of official statistics;
4) the application of measures to counter identification ensures compliance with confidentiality rules when disseminating statistical information. The degree and method of counteraction to identification varies depending on various types of statistical indicators;
5) the completion of the formation of statistical information ensures verification of its compliance with the set goal, the required level of quality and readiness for use.
1) updating statistical production systems provides for a final check for metadata and readiness for dissemination. Carry out the updating of systems in which data and metadata are stored, ready for distribution purposes:
formatting data and metadata, ready for entering into the output statistical information databases;
loading data and metadata into aggregate metrics databases;
linking data with relevant metadata;
2) production of official statistical information in pre-designed forms (publications, tables, interactive graphs, etc.);
3) the management of the dissemination of official statistical information ensures the availability of all components for the dissemination of official statistical information, including meeting deadlines for publication. Provides briefings for specific groups of users, such as the press, as well as the introduction of any prohibitions on the disclosure of statistical information before its publication. In addition, it includes the delivery of statistical publications to subscribers. Seizures of published official statistical information are also part of this subprocess;
4) the popularization of official statistical information in order to facilitate its dissemination to the general public. It includes the use of user relationship management tools to provide more focused work with potential users, as well as the use of mechanisms such as websites, social networks, electronic mailings, etc. to facilitate the process of reporting statistical information to users;
1) the collection of information for the assessment is carried out in various forms, including user comments and suggestions, process metadata, metric data of systems, as well as employee suggestions;
2) the assessment is carried out by analyzing and summarizing the information. The resulting report notes any quality problems, and also contains recommendations on possible changes regarding any process or subprocess;
3) the government agency-developer brings all the necessary legislative powers to develop, coordinate and approve an action plan based on the evaluation report.
application
to the Typical methodology for the description of the process
production of statistical information
government bodies
Description of the production process of official statistical information
|
Processes and sub-processes for the production of official statistical information |
|
|
1) determination of user needs 2) consultation and confirmation of needs 3) setting goals for the formation of a statistical indicator 4) determination of the list of required data 5) check for data availability 6) preparation of a business model |
|
|
1) design of statistical publication 2) designing variable descriptions 3) data collection design 4) designing the population and sample 5) design processing and analysis 6) design of production systems and process |
|
|
1) building a data collection mechanism 2) building or strengthening process components 3) building or strengthening distribution components 4) layout of production processes 5) production system testing 6) testing a statistical business process 7) commissioning of the production system |
|
|
1) the formation of the population and the sample 2) organization of the collection of primary statistics 3) conducting the collection of primary statistics 4) completion of the collection of primary statistics |
|
|
1) data integration 2) classification and coding 3) verification and validation 4) editing and imputation 5) the formation of new derived variables and statistical units 6) calculation of the weight of the index 7) calculation of units 8) completion of data generation
|
Table continuation
|
|
1) preparation of preliminary statistical information 2) validation 3) interpretation and explanation of statistical information 4) application of measures to counter identification 5) completion of the formation of statistical information |
|
|
1) updating production systems of statistical information 2) production of official statistical information 3) managing the dissemination of official statistical information 4) popularization of official statistical information 5) user support management |
|
|
1) Gather information for evaluation 2) Assessment 3) Harmonization of an action plan |