A data set of cross-nationally comparable microdata samples for 15 Economic Commission for Europe (ECE) countries (Bulgaria, Canada, Czech Republic, Estonia, Finland, Hungary, Italy, Latvia, Lithuania, Romania, Russia, Switzerland, Turkey, UK, USA) based on the 1990 national population and housing censuses in countries of Europe and North America to study the social and economic conditions of older persons. These samples have been designed to allow research on a wide range of issues related to aging, as well as on other social phenomena. A common set of nomenclatures and classifications, derived on the basis of a study of census data comparability in Europe and North America, was adopted as a standard for recoding. This series was formerly called Dynamics of Population Aging in ECE Countries. The recommendations regarding the design and size of the samples drawn from the 1990 round of censuses envisaged: (1) drawing individual-based samples of about one million persons; (2) progressive oversampling with age in order to ensure sufficient representation of various categories of older people; and (3) retaining information on all persons co-residing in the sampled individual''''s dwelling unit. Estonia, Latvia and Lithuania provided the entire population over age 50, while Finland sampled it with progressive over-sampling. Canada, Italy, Russia, Turkey, UK, and the US provided samples that had not been drawn specially for this project, and cover the entire population without over-sampling. Given its wide user base, the US 1990 PUMS was not recoded. Instead, PAU offers mapping modules, which recode the PUMS variables into the project''''s classifications, nomenclatures, and coding schemes. Because of the high sampling density, these data cover various small groups of older people; contain as much geographic detail as possible under each country''''s confidentiality requirements; include more extensive information on housing conditions than many other data sources; and provide information for a number of countries whose data were not accessible until recently. Data Availability: Eight of the fifteen participating countries have signed the standard data release agreement making their data available through NACDA/ICPSR (see links below). Hungary and Switzerland require a clearance to be obtained from their national statistical offices for the use of microdata, however the documents signed between the PAU and these countries include clauses stipulating that, in general, all scholars interested in social research will be granted access. Russia requested that certain provisions for archiving the microdata samples be removed from its data release arrangement. The PAU has an agreement with several British scholars to facilitate access to the 1991 UK data through collaborative arrangements. Statistics Canada and the Italian Institute of statistics (ISTAT) provide access to data from Canada and Italy, respectively. * Dates of Study: 1989-1992 * Study Features: International, Minority Oversamples * Sample Size: Approx. 1 million/country Links: * Bulgaria (1992), http://www.icpsr.umich.edu/icpsrweb/ICPSR/studies/02200 * Czech Republic (1991), http://www.icpsr.umich.edu/icpsrweb/ICPSR/studies/06857 * Estonia (1989), http://www.icpsr.umich.edu/icpsrweb/ICPSR/studies/06780 * Finland (1990), http://www.icpsr.umich.edu/icpsrweb/ICPSR/studies/06797 * Romania (1992), http://www.icpsr.umich.edu/icpsrweb/ICPSR/studies/06900 * Latvia (1989), http://www.icpsr.umich.edu/icpsrweb/ICPSR/studies/02572 * Lithuania (1989), http://www.icpsr.umich.edu/icpsrweb/ICPSR/studies/03952 * Turkey (1990), http://www.icpsr.umich.edu/icpsrweb/ICPSR/studies/03292 * U.S. (1990), http://www.icpsr.umich.edu/icpsrweb/ICPSR/studies/06219

Abstract

The Future of Business Survey is a new source of information on small and medium-sized enterprises (SMEs). Launched in February 2016, the monthly survey - a partnership between Facebook, OECD, and The World Bank - provides a timely pulse on the economic environment in which businesses operate and who those businesses are to help inform decision-making at all levels and to deliver insights that can help businesses grow. The Future of Business Survey provides a perspective from newer and long-standing digitalized businesses and provides a unique window into a new mobilized economy.

Policymakers, researchers and businesses share a common interest in the environment in which SMEs operate, as well their outlook on the future, not least because young and innovative SMEs in particular are often an important source of considerable economic and employment growth. Better insights and timely information about SMEs improve our understanding of economic trends, and can provide new insights that can further stimulate and help these businesses grow.

To help provide these insights, Facebook, OECD and The World Bank have collaborated to develop a monthly survey that attempts to improve our understanding of SMEs in a timely and forward-looking manner. The three organizations share a desire to create new ways to hear from businesses and help them succeed in the emerging digitally-connected economy. The shared goal is to help policymakers, researchers, and businesses better understand business sentiment, and to leverage a digital platform to provide a unique source of information to complement existing indicators.

With more businesses leveraging online tools each day, the survey provides a lens into a new mobilized, digital economy and, in particular, insights on the actors: a relatively unmeasured community worthy of deeper consideration and considerable policy interest.

Geographic coverage

When the survey was initially launched in February 2016, it included 22 countries. When the survey was initially launched in February 2016, it included 22 countries. The Future of Business Survey is now conducted in over 90 countries in every region of the world.

Countries included in at least one wave: Albania Algeria American Samoa Andorra Angola Anguilla Antigua and Barbuda Argentina Aruba Australia Austria Azerbaijan Bahamas (the) Bangladesh Barbados Belarus Belgium Belize Benin Bolivia (Plurinational State of) Bonaire, Sint Eustatius and Saba Bosnia and Herzegovina Botswana Brazil Brunei Darussalam Bulgaria Burkina Faso Burundi Cabo Verde Cambodia Cameroon Canada Cayman Islands (the) Central African Republic (the) Chad Chile Colombia Congo (the) Curaçao Cyprus Czechia Côte d'Ivoire Denmark Djibouti Dominica Dominican Republic (the) Ecuador Egypt El Salvador Equatorial Guinea Estonia Eswatini Ethiopia Faroe Islands (the) Fiji Finland France French Polynesia Gabon Gambia (the) Germany Ghana Gibraltar Greece Grenada Guadeloupe Guam Guatemala Guernsey Guinea Guinea-Bissau Guyana Haiti Honduras Hong Kong Hungary Iceland India Indonesia Iraq Ireland Isle of Man Israel Italy Jamaica Japan Jersey Jordan Kenya Korea (the Republic of) Kuwait Lao People's Democratic Republic (the) Lebanon Lesotho Liberia Libya Liechtenstein Lithuania Luxembourg Malawi Malaysia Mali Malta Martinique Mauritania Mauritius Mayotte Mexico Monaco Montenegro Morocco Mozambique Myanmar Namibia Nepal Netherlands (the) New Caledonia New Zealand Nicaragua Niger (the) Nigeria North Macedonia Northern Mariana Islands (the) Norway Oman Pakistan Panama Papua New Guinea Paraguay Peru Philippines (the) Poland Portugal Qatar Romania Russian Federation (the) Rwanda Réunion Saint Kitts and Nevis Saint Lucia Saint Vincent and the Grenadines Samoa San Marino Sao Tome and Principe Saudi Arabia Senegal Serbia Seychelles Sierra Leone Singapore Sint Maarten (Dutch part) Slovakia Slovenia Solomon Islands South Africa Spain Sweden Switzerland Taiwan Tanzania, the United Republic of Thailand Timor-Leste Togo Tonga Trinidad and Tobago Tunisia Turkey Turks and Caicos Islands (the) Uganda United Arab Emirates (the) United Kingdom of Great Britain and Northern Ireland (the) United States of America (the) Uruguay Vanuatu Viet Nam Virgin Islands (British) Virgin Islands (U.S.) Zambia.

Analysis unit

The study describes small and medium-sized enterprises.

Universe

The target population consists of SMEs that have an active Facebook business Page and include both newer and longer-standing businesses, spanning across a variety of sectors. With more businesses leveraging online tools each day, the survey provides a lens into a new mobilized, digital economy and, in particular, insights on the actors: a relatively unmeasured community worthy of deeper consideration and considerable policy interest.

Kind of data

Sample survey data [ssd]

Sampling procedure

Twice a year in over 97 countries, the Facebook Survey Team sends the Future of Business to admins and owners of Facebook-designated small business pages. When we share data from this survey, we anonymize responses to all survey questions and only share country-level data publicly. To achieve better representation of the broader small business population, we also weight our results based on known characteristics of the Facebook Page admin population.

A random sample of firms, representing the target population in each country, is selected to respond to the Future of Business Survey each month.

Mode of data collection

Internet [int]

Research instrument

The survey includes questions about perceptions of current and future economic activity, challenges, business characteristics and strategy. Custom modules include questions related to regulation, access to finance, digital payments, and digital skills. The full questionnaire is available for download.

Response rate

Response rates to online surveys vary widely depending on a number of factors including survey length, region, strength of the relationship with invitees, incentive mechanisms, invite copy, interest of respondents in the topic and survey design.

Note: Response rates are calculated as the number of respondents who completed the survey divided by the total number of SMEs invited.

Sampling error estimates

Any survey data is prone to several forms of error and biases that need to be considered to understand how closely the results reflect the intended population. In particular, the following components of the total survey error are noteworthy:

Sampling error is a natural characteristic of every survey based on samples and reflects the uncertainty in any survey result that is attributable to the fact that not the whole population is surveyed.

Other factors beyond sampling error that contribute to such potential differences are frame or coverage error (sampling frame of page owners does not include all relevant businesses but also may include individuals that don't represent businesses), and nonresponse error.

Note that the sample is meant to reflect the population of businesses on Facebook, not the population of small businesses in general. This group of digitized SMEs is itself a community worthy of deeper consideration and of considerable policy interest. However, care should be taken when extrapolating to the population of SMEs in general. Moreover, future work should evaluate the external validity of the sample. Particularly, respondents should be compared to the broader population of SMEs on Facebook, and the economy as a whole.

Graph and download economic data for Refugee Population by Country or Territory of Asylum for Small States (SMPOPREFGSST) from 1990 to 2023 about refugee, small, World, and population.

The coastal zones of Small Island States are hotspots of human habitation and economic endeavour. In the Pacific region, as elsewhere, there are large gaps in understandings of the exposure and vulnerability of people in coastal zones. The 22 Pacific Countries and Territories (PICTs) are poorly represented in global analyses of vulnerability to seaward risks. We combine several data sources to estimate populations to zones 1, 5 and 10 km from the coastline in each of the PICTs. Regional patterns in the proximity of Pacific people to the coast are dominated by Papua New Guinea. Overall, ca. half the population of the Pacific resides within 10 km of the coast but this jumps to 97% when Papua New Guinea is excluded. A quarter of Pacific people live within 1 km of the coast, but without PNG this increases to slightly more than half. Excluding PNG, 90% of Pacific Islanders live within 5 km of the coast. All of the population in the coral atoll nations of Tokelau and Tuvalu live within a km of the ocean. Results using two global datasets, the SEDAC-CIESIN Gridded Population of the World v4 (GPWv4) and the Oak Ridge National Laboratory Landscan differed: Landscan under-dispersed population, overestimating numbers in urban centres and underestimating population in rural areas and GPWv4 over-dispersed the population. In addition to errors introduced by the allocation models of the two methods, errors were introduced as artefacts of allocating households to 1 km x 1 km grid cell data (30 arc–seconds) to polygons. The limited utility of LandScan and GPWv4 in advancing this analysis may be overcome with more spatially resolved census data and the inclusion of elevation above sea level as an important dimension of vulnerability.

This workbook allows users to pull out data from 2011 Census Commissioned Table CT0561 (age by sex by country of birth) and visualises the data in a population pyramid.

This data was part of a release of 2011 Census tables that allow users to see the characteristics of small migrant populations. See this dataset for more characteristics.

The gridded population data used for calculating exposed populations is based on the population projections from the original SSPs (KC and Lutz, 2017) which were subsequently gridded (Jones and O’Neill, 2016). These gridded projections were aggregated to 0.5 ° spatial resolution and then scaled to match the latest available projections for population in line with the updated SSPs, v3.0 (KC et al., 2024). The scaling is done on a country basis for all countries included in the latest SSP projections. Countries, which are not included in these projections, remain unchanged. The scaling process is done on a country-level basis using the following step:

1. The total population for the original gridded data is calculated using the ISIMIP fractional country raster (Perrette, 2023), excluding border cells containing contributions from more than one country.
2. The population of the fractional border cells is subtracted from the total population of the SSP population projections and the required scalar to match the population from the gridded data to the SSP population projections is calculated.
3. This scalar is applied to all non-fractional cells.

While it is possible to calculate the scalar for each country including the proportion of the population in the fractional border cells, this would require the scalar to also be applied to that proportion of the population in the border cells to match the overall population number for each country. Applying different scalars to the population proportions for each country in the same cell would, however, change the ratios of the population in the fractional border cells and subsequently lead to skewed results when reapplying the fractional country raster to the scaled data for the aggregation to country level. For small countries, where more population lives in fractional border cells than in non-border cells, and for countries that only consist of border cells with contributions from more than one country, all cells were used in the scaling process.

It should be noted that some smaller countries cannot be scaled properly and that the latest SSP population projections do not contain values for all countries. Since there has been no release of updated gridded population projections yet, the gridded population data created using this approach still provide the closest match to the latest SSP population projections currently available.

The NATCOOP project set out to study how nature shapes the preferences and incentives of economic agents and how this in turn affects common-pool resource management. Imagine a group of fishermen targeting a species that requires a lot of teamwork to harvest. Do these fishers become more social over time compared to fishers that work in a more solitary manner? If so, does this have implications for how the fishery should be managed? To study this, the NATCOOP team travelled to Chile and Tanzania and collected data using surveys and economic experiments. These two very different countries have a large population of small-scale fishermen, and both host several distinct types of fisheries. Over the course of five field trips, the project team surveyed more than 2500 fishermen with each field trip contributing to the main research question by measuring fishermen’s preferences for cooperation and risk. Additionally, each fieldtrip aimed to answer another smaller research question that was either focused on risk taking or cooperation behavior in the fisheries. The data from both surveys and experiments are now publicly available and can be freely studied by other researchers, resource managers, or interested citizens. Overall, the NATCOOP dataset contains participants’ responses to a plethora of survey questions and their actions during incentivized economic experiments. It is available in both the .dta and .csv format, and its use is recommended with statistical software such as R or Stata. For those unaccustomed with statistical analysis, we included a video tutorial on how to use the data set in the open-source program R.

Accuracy of population density estimates.

Variables The data file of standard Small Area Statistics contains information about: age and sex of the population, country of birth, 1 year and 5 year migration within and into a local authority, transport to work, economic activity, employment, socio-economic composition, social class, household composition, availability of cars and their garaging, housing tenure, dwellings, household amenities, occupation density, housing size and type and related topics (total of 381 variables). One-stage stratified or systematic random sample = 10% of population Face-to-face interview

Census data reveals that population density varies noticeably from area to area. Small area census data do a better job depicting where the crowded neighborhoods are. In this map, the yellow areas of highest density range from 30,000 to 150,000 persons per square kilometer. In those areas, if the people were spread out evenly across the area, there would be just 4 to 9 meters between them. Very high density areas exceed 7,000 persons per square kilometer. High density areas exceed 5,200 persons per square kilometer. The last categories break at 3,330 persons per square kilometer, and 1,500 persons per square kilometer.This dataset is comprised of multiple sources. All of the demographic data are from Michael Bauer Research with the exception of the following countries:Australia: Esri Australia and MapData ServicesCanada: Esri Canada and EnvironicsFrance: Esri FranceGermany: Esri Germany and NexigaIndia: Esri India and IndicusJapan: Esri JapanSouth Korea: Esri Korea and OPENmateSpain: Esri España and AISUnited States: Esri Demographics

The Small Area Estimates of Poverty and Inequality dataset consists of consumption-based

poverty, inequality and related measures for subnational administrative units in approximately twenty countries throughout Africa,

Asia, Europe, North America, and South America. These measures are derived on a country-level basis from a combination of census and

survey data using small area estimates techniques. The collection of data have been compiled, integrated and standardized from the

original data providers into a unified spatially referenced and globally consistent dataset. The data products include shapefiles

(vector data), tabular datasets (csv format), and centroids (csv file with latitude and longitude of a geographic unit and associated

poverty estimates). Additionally, a data catalog (xls format) containing detailed information and documentation is provided. This

dataset is produced by the Columbia University Center for International Earth Science Information Network (CIESIN) in collaboration

with a number of external data providers.

🇬🇧 United Kingdom English This workbook allows users to pull out data from 2011 Census Commissioned Table CT0561 (age by sex by country of birth) and visualises the data in a population pyramid. This data was part of a release of 2011 Census tables that allow users to see the characteristics of small migrant populations. See this dataset for more characteristics.

Office for National Statistics’ national and subnational mid-year population estimates for England and Wales for a selection of administrative and census areas by age (in 5 year age brackets) for 2012 to 2020. The data is source is from ONS Population Estimates. Find out more about this dataset here.This data is issued at (BGC) Generalised (20m) boundary type for:Country,Region,Upper Tier Local Authority (2021),Lower Tier Local Authority (2021),Middle Super Output Area (2011), andLower Super Output Area (2011).If you require the data at full resolution boundaries, or if you are interested in the range of statistical data that Esri UK make available in ArcGIS Online please enquire at content@esriuk.com.The Office for National Statistics (ONS) produces annual estimates of the resident population of England and Wales at 30 June every year. The most authoritative population estimates come from the census, which takes place every 10 years in the UK. Population estimates from a census are updated each year to produce mid-year population estimates (MYEs), which are broken down by local authority, sex and age. More detailed information on the methods used to generate the mid-year population estimates can be found here.For further information on the usefulness of the data and guidance on small area geographies please see here.The currency of this data is 2021.MethodologyThe total and 5-year breakdown population counts are reproduced directly from the source data. The age range estimates have been calculated from the published estimates by single year of age. The percentages are calculated using the gender specific (total, female or male) total population count as a denominator except in the case of the male and female total population where the total population is used to give female and male proportions.This dataset will be updated annually, in two releases.Creator: Office for National Statistics. Aggregated age groupings and percentages calculated by Esri UK._The data services available from this page are derived from the National Data Service. The NDS delivers thousands of open national statistical indicators for the UK as data-as-a-service. Data are sourced from major providers such as the Office for National Statistics, Public Health England and Police UK and made available for your area at standard geographies such as counties, districts and wards and census output areas. This premium service can be consumed as online web services or on-premise for use throughout the ArcGIS system.Read more about the NDS.

The population of Latin America and the Caribbean increased from 175 million in 1950 to 515 million in 2000. Where did this growth occur? What is the magnitude of change in different places? How can we visualize the geographic dimensions of population change in Latin America and the Caribbean? We compiled census and other public domain information to analyze both temporal and geographic changes in population in the region. Our database includes population totals for over 18,300 administrative districts within Latin America and the Caribbean. Tabular census data was linked to an administrative division map of the region and handled in a geographic information system. We transformed vector population maps to raster surfaces to make the digital maps comparable with other commonly available geographic information. Validation and error-checking analyses were carried out to compare the database with other sources of population information. The digital population maps created in this project have been put in the public domain and can be downloaded from our website. The Latin America and Caribbean map is part of a larger multi-institutional effort to map population in developing countries. This is the third version of the Latin American and Caribbean population database and it contains new data from the 2000 round of censuses and new and improved accessibility surfaces for creating the raster maps.

Summary statistics for villages in the national sample.

Small population statistics giving key characteristics of people in specific small population groups such as individual ethnic groups, or those with a specific country of birth - for local authorities above a disclosure control threshold.

Context

This is a dataset of the most highly populated city (if applicable) in a form easy to join with the COVID19 Global Forecasting (Week 1) dataset. You can see how to use it in this kernel

Content

There are four columns. The first two correspond to the columns from the original COVID19 Global Forecasting (Week 1) dataset. The other two is the highest population density, at city level, for the given country/state. Note that some countries are very small and in those cases the population density reflects the entire country. Since the original dataset has a few cruise ships as well, I've added them there.

Acknowledgements

Thanks a lot to Kaggle for this competition that gave me the opportunity to look closely at some data and understand this problem better.

Inspiration

Summary: I believe that the square root of the population density should relate to the logistic growth factor of the SIR model. I think the SEIR model isn't applicable due to any intervention being too late for a fast-spreading virus like this, especially in places with dense populations.

After playing with the data provided in COVID19 Global Forecasting (Week 1) (and everything else online or media) a bit, one thing becomes clear. They have nothing to do with epidemiology. They reflect sociopolitical characteristics of a country/state and, more specifically, the reactivity and attitude towards testing.

The testing method used (PCR tests) means that what we measure could potentially be a proxy for the number of people infected during the last 3 weeks, i.e the growth (with lag). It's not how many people have been infected and recovered. Antibody or serology tests would measure that, and by using them, we could go back to normality faster... but those will arrive too late. Way earlier, China will have experimentally shown that it's safe to go back to normal as soon as your number of newly infected per day is close to zero.

https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F197482%2F429e0fdd7f1ce86eba882857ac7a735e%2Fcovid-summary.png?generation=1585072438685236&alt=media" alt="">

My view, as a person living in NYC, about this virus, is that by the time governments react to media pressure, to lockdown or even test, it's too late. In dense areas, everyone susceptible has already amble opportunities to be infected. Especially for a virus with 5-14 days lag between infections and symptoms, a period during which hosts spread it all over on subway, the conditions are hopeless. Active populations have already been exposed, mostly asymptomatic and recovered. Sensitive/older populations are more self-isolated/careful in affluent societies (maybe this isn't the case in North Italy). As the virus finishes exploring the active population, it starts penetrating the more isolated ones. At this point in time, the first fatalities happen. Then testing starts. Then the media and the lockdown. Lockdown seems overly effective because it coincides with the tail of the disease spread. It helps slow down the virus exploring the long-tail of sensitive population, and we should all contribute by doing it, but it doesn't cause the end of the disease. If it did, then as soon as people were back in the streets (see China), there would be repeated outbreaks.

Smart politicians will test a lot because it will make their condition look worse. It helps them demand more resources. At the same time, they will have a low rate of fatalities due to large denominator. They can take credit for managing well a disproportionally major crisis - in contrast to people who didn't test.

We were lucky this time. We, Westerners, have woken up to the potential of a pandemic. I'm sure we will give further resources for prevention. Additionally, we will be more open-minded, helping politicians to have more direct responses. We will also require them to be more responsible in their messages and reactions.

The Data Sheet lists all geopolitical entities with populations of 150,000 or more and all members of the UN. These include sovereign states, dependencies, overseas departments, and some territories whose status or boundaries may be undetermined or in dispute. Regional population totals are independently rounded and include small countries or areas not shown. Regional and world rates and percentages are weighted averages of countries for which data are available; regional averages are shown when data or estimates are available for at least three-quarters of the region's population. Variables include population, birth and death rate, rate of natural increase, population "doubling time", estimated population for 2010 and 2025, infant mortality rate, total fertility rate, population under age 15/over age 65, life expectancy at birth, urban population, contraceptive use, per capita GNP, and government view of current birth rate. NOTE: This file is a compilation of demographic data from various sources. The data values are the same as those published in PRB's World Data Sheet, but this file also contains some underlying population figures used to calculate the rates and percentages.

Abstract

Different countries have different health outcomes that are in part due to the way respective health systems perform. Regardless of the type of health system, individuals will have health and non-health expectations in terms of how the institution responds to their needs. In many countries, however, health systems do not perform effectively and this is in part due to lack of information on health system performance, and on the different service providers.

The aim of the WHO World Health Survey is to provide empirical data to the national health information systems so that there is a better monitoring of health of the people, responsiveness of health systems and measurement of health-related parameters.

The overall aims of the survey is to examine the way populations report their health, understand how people value health states, measure the performance of health systems in relation to responsiveness and gather information on modes and extents of payment for health encounters through a nationally representative population based community survey. In addition, it addresses various areas such as health care expenditures, adult mortality, birth history, various risk factors, assessment of main chronic health conditions and the coverage of health interventions, in specific additional modules.

The objectives of the survey programme are to: 1. develop a means of providing valid, reliable and comparable information, at low cost, to supplement the information provided by routine health information systems. 2. build the evidence base necessary for policy-makers to monitor if health systems are achieving the desired goals, and to assess if additional investment in health is achieving the desired outcomes. 3. provide policy-makers with the evidence they need to adjust their policies, strategies and programmes as necessary.

Geographic coverage

The survey sampling frame must cover 100% of the country's eligible population, meaning that the entire national territory must be included. This does not mean that every province or territory need be represented in the survey sample but, rather, that all must have a chance (known probability) of being included in the survey sample.

There may be exceptional circumstances that preclude 100% national coverage. Certain areas in certain countries may be impossible to include due to reasons such as accessibility or conflict. All such exceptions must be discussed with WHO sampling experts. If any region must be excluded, it must constitute a coherent area, such as a particular province or region. For example if ¾ of region D in country X is not accessible due to war, the entire region D will be excluded from analysis.

Analysis unit

Households and individuals

Universe

The WHS will include all male and female adults (18 years of age and older) who are not out of the country during the survey period. It should be noted that this includes the population who may be institutionalized for health reasons at the time of the survey: all persons who would have fit the definition of household member at the time of their institutionalisation are included in the eligible population.

If the randomly selected individual is institutionalized short-term (e.g. a 3-day stay at a hospital) the interviewer must return to the household when the individual will have come back to interview him/her. If the randomly selected individual is institutionalized long term (e.g. has been in a nursing home the last 8 years), the interviewer must travel to that institution to interview him/her.

The target population includes any adult, male or female age 18 or over living in private households. Populations in group quarters, on military reservations, or in other non-household living arrangements will not be eligible for the study. People who are in an institution due to a health condition (such as a hospital, hospice, nursing home, home for the aged, etc.) at the time of the visit to the household are interviewed either in the institution or upon their return to their household if this is within a period of two weeks from the first visit to the household.

Kind of data

Sample survey data [ssd]

Sampling procedure

SAMPLING GUIDELINES FOR WHS

Surveys in the WHS program must employ a probability sampling design. This means that every single individual in the sampling frame has a known and non-zero chance of being selected into the survey sample. While a Single Stage Random Sample is ideal if feasible, it is recognized that most sites will carry out Multi-stage Cluster Sampling.

The WHS sampling frame should cover 100% of the eligible population in the surveyed country. This means that every eligible person in the country has a chance of being included in the survey sample. It also means that particular ethnic groups or geographical areas may not be excluded from the sampling frame.

The sample size of the WHS in each country is 5000 persons (exceptions considered on a by-country basis). An adequate number of persons must be drawn from the sampling frame to account for an estimated amount of non-response (refusal to participate, empty houses etc.). The highest estimate of potential non-response and empty households should be used to ensure that the desired sample size is reached at the end of the survey period. This is very important because if, at the end of data collection, the required sample size of 5000 has not been reached additional persons must be selected randomly into the survey sample from the sampling frame. This is both costly and technically complicated (if this situation is to occur, consult WHO sampling experts for assistance), and best avoided by proper planning before data collection begins.

All steps of sampling, including justification for stratification, cluster sizes, probabilities of selection, weights at each stage of selection, and the computer program used for randomization must be communicated to WHO

STRATIFICATION

Stratification is the process by which the population is divided into subgroups. Sampling will then be conducted separately in each subgroup. Strata or subgroups are chosen because evidence is available that they are related to the outcome (e.g. health, responsiveness, mortality, coverage etc.). The strata chosen will vary by country and reflect local conditions. Some examples of factors that can be stratified on are geography (e.g. North, Central, South), level of urbanization (e.g. urban, rural), socio-economic zones, provinces (especially if health administration is primarily under the jurisdiction of provincial authorities), or presence of health facility in area. Strata to be used must be identified by each country and the reasons for selection explicitly justified.

Stratification is strongly recommended at the first stage of sampling. Once the strata have been chosen and justified, all stages of selection will be conducted separately in each stratum. We recommend stratifying on 3-5 factors. It is optimum to have half as many strata (note the difference between stratifying variables, which may be such variables as gender, socio-economic status, province/region etc. and strata, which are the combination of variable categories, for example Male, High socio-economic status, Xingtao Province would be a stratum).

Strata should be as homogenous as possible within and as heterogeneous as possible between. This means that strata should be formulated in such a way that individuals belonging to a stratum should be as similar to each other with respect to key variables as possible and as different as possible from individuals belonging to a different stratum. This maximises the efficiency of stratification in reducing sampling variance.

MULTI-STAGE CLUSTER SELECTION

A cluster is a naturally occurring unit or grouping within the population (e.g. enumeration areas, cities, universities, provinces, hospitals etc.); it is a unit for which the administrative level has clear, nonoverlapping boundaries. Cluster sampling is useful because it avoids having to compile exhaustive lists of every single person in the population. Clusters should be as heterogeneous as possible within and as homogenous as possible between (note that this is the opposite criterion as that for strata). Clusters should be as small as possible (i.e. large administrative units such as Provinces or States are not good clusters) but not so small as to be homogenous.

In cluster sampling, a number of clusters are randomly selected from a list of clusters. Then, either all members of the chosen cluster or a random selection from among them are included in the sample. Multistage sampling is an extension of cluster sampling where a hierarchy of clusters are chosen going from larger to smaller.

In order to carry out multi-stage sampling, one needs to know only the population sizes of the sampling units. For the smallest sampling unit above the elementary unit however, a complete list of all elementary units (households) is needed; in order to be able to randomly select among all households in the TSU, a list of all those households is required. This information may be available from the most recent population census. If the last census was >3 years ago or the information furnished by it was of poor quality or unreliable, the survey staff will have the task of enumerating all households in the smallest randomly selected sampling unit. It is very important to budget for this step if it is necessary and ensure that all households are properly enumerated in order that a representative sample is obtained.

It is always best to have as many clusters in the PSU as possible. The reason for this is that the fewer the number of respondents in each PSU, the lower will be the clustering effect which

Abstract

The Future of Business Survey is a new source of information on small and medium-sized enterprises (SMEs). Launched in February 2016, the monthly survey - a partnership between Facebook, OECD, and The World Bank - provides a timely pulse on the economic environment in which businesses operate and who those businesses are to help inform decision-making at all levels and to deliver insights that can help businesses grow. The Future of Business Survey provides a perspective from newer and long-standing digitalized businesses and provides a unique window into a new mobilized economy.

Policymakers, researchers and businesses share a common interest in the environment in which SMEs operate, as well their outlook on the future, not least because young and innovative SMEs in particular are often an important source of considerable economic and employment growth. Better insights and timely information about SMEs improve our understanding of economic trends, and can provide new insights that can further stimulate and help these businesses grow.

To help provide these insights, Facebook, OECD and The World Bank have collaborated to develop a monthly survey that attempts to improve our understanding of SMEs in a timely and forward-looking manner. The three organizations share a desire to create new ways to hear from businesses and help them succeed in the emerging digitally-connected economy. The shared goal is to help policymakers, researchers, and businesses better understand business sentiment, and to leverage a digital platform to provide a unique source of information to complement existing indicators.

With more businesses leveraging online tools each day, the survey provides a lens into a new mobilized, digital economy and, in particular, insights on the actors: a relatively unmeasured community worthy of deeper consideration and considerable policy interest.

Geographic coverage

When the survey was initially launched in February 2016, it included 22 countries. When the survey was initially launched in February 2016, it included 22 countries. The Future of Business Survey is now conducted in over 90 countries in every region of the world.

Analysis unit

The study describes small and medium-sized enterprises.

Universe

The target population consists of SMEs that have an active Facebook business Page and include both newer and longer-standing businesses, spanning across a variety of sectors. With more businesses leveraging online tools each day, the survey provides a lens into a new mobilized, digital economy and, in particular, insights on the actors: a relatively unmeasured community worthy of deeper consideration and considerable policy interest.

Kind of data

Sample survey data [ssd]

Sampling procedure

Twice a year in over 97 countries, the Facebook Survey Team sends the Future of Business to admins and owners of Facebook-designated small business pages. When we share data from this survey, we anonymize responses to all survey questions and only share country-level data publicly. To achieve better representation of the broader small business population, we also weight our results based on known characteristics of the Facebook Page admin population.

A random sample of firms, representing the target population in each country, is selected to respond to the Future of Business Survey each month.

Mode of data collection

Internet [int]

Research instrument

The survey includes questions about perceptions of current and future economic activity, challenges, business characteristics and strategy. Custom modules include questions related to regulation, access to finance, digital payments, and digital skills. The full questionnaire is available for download.

The questionnaire was pretested by the target audience, as well as experts from the area of research interest. Additionally, steps were taken to translate the survey in order to reduce sensitivities to cultural response bias: - Respondents were given the option to respond to the survey in any of fifteen languages native to the countries in which it was conducted. - Translations were done only by native speakers, with two rounds of additional online checks in the context of the survey environment. - Translators were provided with context material for this survey (e.g., the Facebook for Business website) in order to understand the context of the survey. They were also instructed to take the English survey at least two times before starting with the translations. - Translations were discussed in a group in order to ensure a common understanding of questions and items. - The tone (formal vs. informal) of the survey was based on cultural conventions, e.g., Facebook usually uses an informal tone, while in cultures such as the Japanese this is very uncommon and thus a formal tone was used there.

Response rate

Response rates to online surveys vary widely depending on a number of factors including survey length, region, strength of the relationship with invitees, incentive mechanisms, invite copy, interest of respondents in the topic and survey design.

Note: Response rates are calculated as the number of respondents who completed the survey divided by the total number of SMEs invited.

Sampling error estimates

Any survey data is prone to several forms of error and biases that need to be considered to understand how closely the results reflect the intended population. In particular, the following components of the total survey error are noteworthy:

Sampling error is a natural characteristic of every survey based on samples and reflects the uncertainty in any survey result that is attributable to the fact that not the whole population is surveyed.

Other factors beyond sampling error that contribute to such potential differences are frame or coverage error (sampling frame of page owners does not include all relevant businesses but also may include individuals that don't represent businesses), and nonresponse error.

Note that the sample is meant to reflect the population of businesses on Facebook, not the population of small businesses in general. This group of digitized SMEs is itself a community worthy of deeper consideration and of considerable policy interest. However, care should be taken when extrapolating to the population of SMEs in general. Moreover, future work should evaluate the external validity of the sample. Particularly, respondents should be compared to the broader population of SMEs on Facebook, and the economy as a whole.