21
• Accuracy of the data from surveys is routinely assessed.
Reports of the Census and Annual Survey of Industrial Production are prepared and published on the NBS website, taking into account sampling errors, biases, and non-response.
To maintain the accuracy of the data collected, several procedures are followed, such as supervision during data collection, manual editing of questionnaires, and outlier checks during data processing. Outliers are identified by comparing prices from the previous quarter and the same quarter of the previous year. In some cases, prices of the same commodity are compared, and phone calls are used to seek clarification from establishments.
The accuracy of the data is verified through direct phone calls to respondents if outliers or extreme values are identified. No outliers are automatically deleted without confirmation.
Enumerators are trained and reminded to ensure that the form is accurately filled out before leaving the establishment.
Data is monitored, and if it is missing for three consecutive months, the product is replaced with one of the same characteristics. For temporarily missing values, imputation method is sometimes used.
• Accuracy of administrative data and other secondary sources is routinely assessed.
In some cases, administrative data is used to assess the accuracy of data collected for PPI.
• Appropriate measures are taken to make the source data consistent with PPI concepts.
Misreporting or underreporting is analyzed directly through phone calls to respondents or by checking the consistency of prices from the previous quarter.
3.3 Statistical techniques
3.3.1 Data compilation employs sound statistical techniques to deal with data sources.
22
• Adjustments are made to source data when concepts followed in their compilation are not consistent with price statistics.
Excel spreadsheet is used for data entry and compilation procedures. Prices collected are monitored during data collection to minimize errors, and data validation is performed during processing, where outliers, missing prices, and other issues are identified.
Unusual values are identified during data processing, and verification is done through direct phone calls to the respondents. For the issue of non-response, an imputation method is applied.
• Appropriate measures are taken to validate the source data.
Procedures for data sources, coverage, definitions, classifications, and valuation follow international guidelines, such as the PPI Manual and UNIDO guidelines.
Grossing-up factors are calculated by activity to produce population estimates that represent uncovered (non-response) activities. For establishments with 10 or more employees, the grossing factor is one.
• Internationally accepted statistical methods are used to handle missing prices and the introduction of new products that are within the scope of the PPI.
For temporarily missing prices, imputation is done using quarter-to- quarter price changes. Missing prices for seasonal products are imputed using price relatives of the sub-group. New establishments producing the same products are used for the permanent unavailable products.
3.3.2 Other statistical procedures (e.g., data adjustments and transformations, and statistical analysis) employ sound statistical techniques.
• Proper statistical techniques are used to address specific issues of output measurement for PPI weights.
Gross output, as defined in the 2008 SNA, is used for the development of weights. Work in progress and finished products are considered during the census or survey and is obtained through an inventory check (opening balance and closing balance).
23
The cash are converted to accrual by allocating them to the period to which they relate in particular for certain data related to government activities such as taxes and subsidies on products, government arrears, government revenue data and government expenditure data as aligned with SNA 2008.
• Calculation of the elementary (item) level indices.
In elementary aggregates (unweighted), the PPI is computed using the geometric mean of price relatives (Jevons formula). Weights are then applied to obtain aggregates for the high-level indices.
• Aggregation of the higher-level indices.
The weight reference period is ASIP 2015, and the price reference period is 2018 quarter 4. Elementary price indices are aggregated to form higher-level indices using weights. The Laspeyres aggregation formula is used to compute these higher-level indices.
• Weight reference period.
Weights should be updated every five years. The current weight reference period is ASIP 2015, and it will be updated after the completion of the CIP 2023. The current PPI was linked back to 2013 using a linking factor.
3.4 Assessment and validation of intermediate data and statistical outputs
3.4.1 Intermediate results are validated against other information where applicable.
• Iintermediate results are validated against other independent data.
PPI data is not compared with comparable estimates from other sources such the national accounts statistics, export and import price indices.
3.4.2 Statistical discrepancies in intermediate data are assessed and investigated.
• Unusual index movements arising from potential problems in price data are investigated and made available to users.
There is no unusual index movements observed.
24
3.4.3 Statistical discrepancies and other potential indicators of problems in statistical outputs are investigated.
• Statistical discrepancies, if any, between PPI for economic activities and the PPI for products are investigated and made available to users.
The NBS releases the PPI for economic activities and not the PPI for products. However, before finalizing data processing, price data are reviewed to correct any discrepancies that arise in the PPI for economic activities.
3.5 Revision studies
3.5.1 Studies and analyses of revisions and/or updates are carried out and used internally to inform statistical processes (see also 4.3.3).
• Revision studies are undertaken on a regular basis.
Periodic weight updates in the PPI are essential to reflect current production and pricing patterns. The update is conducted every five years to incorporate changes in the economy.
After obtaining the new reference period and weights, the new PPI to be published need to be studied for five consecutive quarters to observe economic trends before they are made available for public use.
Errors or bias cannot be avoided in any survey, but they must be addressed to prevent them from distorting the true picture of the economy. In the case of nonresponse, the imputation method is applied to estimate missing data. For sampling errors, every five years, activities and products are reviewed to ensure representativeness, thereby reducing bias.
• Measures are undertaken to incorporate the findings from revision and/or update studies in data compilation.
Observations gained from past data revisions are used to improve and adjust both the initial data and the methods employed for future data collection. These observations help analyze errors, biases, or inefficiencies in the data collection process encountered in the past, allowing them to be identified and corrected. This ensures that future
25
data is more accurate and better reflects the true picture of economic trends.
- Serviceability
4.1 Periodicity and timeliness
4.1.1 Periodicity follows dissemination standards.
• The periodicity of the statistics follows the IMF data dissemination standards (Special Data Dissemination Standard (SDDS) or General Data Dissemination System (GDDS)).
The PPI is compiled in quarterly basis, following the IMF's data dissemination standards: the Special Data Dissemination Standard (SDDS) and the General Data Dissemination System (GDDS).
4.1.2 Timeliness follows dissemination standards.
• The timeliness of statistical series follows the IMF data dissemination standards (SDDS or GDDS).
The PPI is disseminated within two months after the end of the quarter following the IMF data dissemination standards (SDDS or GDDS).
4.2 Consistency
4.2.1 Statistics are consistent within the dataset.
• Statistical series is internally consistent.
The Producer Price Index (PPI) is consistent as it follows 2004 PPI manual and other international recommendations guidelines. Producer prices are collected from the same selected establishments and commodities which covers all four industries sub sector by recoding the average prices of the quarter.
The price relatives of the selected commodities on each four-digit level of ISIC are computed. The first level of aggregation is the class 4-digit ISIC; these indices are the un-weighted Elementary Aggregate (EA) and are being compiled using the Jevons geometric mean aggregation formula which refers to Geometric Mean of the price relatives. The Elementary Aggregates indices are then being progressively combined to higher levels within the index structure using the Laspeyres formula.
26
4.2.2 Statistics are consistent or reconcilable over a reasonable period of time.
• The statistical series is consistent over time.
For any significant changes in PPI trends (such sudden increase or decrease in prices, production or other indicators), the release provides analysis to help users understand the reason behind these changes.
4.2.3 Statistics are consistent or reconcilable with those obtained through other data sources and/or statistical framework.
• The statistics are consistent or reconcilable with other statistical frameworks.
The PPI are aligned with other key economic indicators e.g Consumer Price Index, Gross Domestic Product. This ensures that the PPI and related data provide an accurate picture of economic trends.
4.3 Revision policy and practice
4.3.1 Revisions and/or updates follow a regular and transparent schedule.
• The practice of revisions (e.g., from provisional estimates, for weight updates, for changes in methodology) follows a predictable pattern of which users of statistics are informed.
The revision is done after five (5) years to incorporate changes in the economy.
The revision cycle is influenced by when the necessary data from comprehensive survey becomes unavailable for updating or revision.
• The agency has adopted a clear and consistent revision policy.
The Bureau undertakes revision, though there is no clear and consistent revision policy that is in place.
4.3.2 Preliminary and/or revised/ updated data are clearly identified.
• Users are informed about the preliminary nature of the data.
There is no dissemination for preliminary of PPI data.
• Users are informed about the revised nature of the data.
27
Once PPI data are disseminated, they are not subjected to any revision or updates.
4.3.3 Studies and analyses of revisions and/or updates are made public.
• Users are informed of the results and studies of the revisions and/or updates to the statistics.
Weight revision and data revision is done but users are not informed. Analysis of differences between the revised data and preliminary data is not done but expected to be done after Census of Industrial Production (CIP) 2023.
- Accessibility
5.1 Data accessibility
5.1.1 Statistics are presented in a way that facilitates proper interpretation and meaningful comparisons (layout and clarity of text, tables, and charts).
• The presentation of the statistics data is commensurate with users’ needs.
The PPI release is published on a quarterly basis and includes a table displaying indices by sub-sectors and major groups, along with a line graph that presents the overall indices. This format helps readers and analysts interpret the data and draw conclusions more easily.
Although the dataset for the PPI is available at the 4-digit level, as defined in ISIC Rev. 4, the release is published at the 2-digit level and in major groups of the ISIC Rev. 4.
The PPI release contains details for the current period, including comparisons between the current quarter and the previous quarter's index. Additionally, quarterly indices are disseminated with time series data to assess trends over time, comparing quarter to quarter and year on year.
5.1.2 Dissemination media and format are adequate.
• Statistics are disseminated in formats to suit users’ needs.
The quarterly PPI release is disseminated in electronic copies (PDF format) and provides details at the 2-digit level and in major groups
28
of ISIC Rev. 4 and can be accessed through the NBS website. Detailed current statistics and longer time series are available to the Bureau upon request for free.
5.1.3 Statistics are released on a preannounced schedule.
• Statistics are released on the preannounced schedule.
The NBS release calendar indicates the dates when the PPI will be available. The PPI is made available according to the pre-announced schedule.
5.1.4
Statistics are made available to all users at the same time.
• The statistics are made available to all users at the same time.
The public is informed about the statistics being released and the procedure to access them through NBS website. The Index is available on the NBS website without any delays or preferential treatment. The statistics are made available to all users at the same time.
5.1.5
Statistics not routinely disseminated are made available upon request.
• Statistics not routinely disseminated are made available to users upon request.
Users can obtain additional information free of charge by submitting a request to the Statistician General.
5.2 Metadata accessibility
5.2.1 Documentation on concepts, scope, classifications, basis of recording, data sources, and statistical techniques is available, and differences from internationally accepted standards, guidelines, or good practices are annotated.
• The metadata give adequate information about the meaning of the data and about the methodology used to collect and process them.
The PPI release includes a brief summary of concepts and definitions, the methodology used, and the classification procedures for obtaining the index.
The PPI compilation adheres to accepted standards, guidelines, and best practices. It follows the PPI Manual and other relevant industrial guidelines.