What is A Sample Frame?

The sample frame is the specific source of respondents that is used to draw the sample from. This could be a map from which specific areas are outlined, a list of registered voters, a phonebook, or another source which specifically defines who will and will not be included in the sample. The sample frame should be representative of the sample universe, which is the broader definition of the sample makeup. For example, if a researcher is looking to study attitudes of students at a specific university, the definitions may look like the below:

• Sample Universe: Current students at University X
• Sample Frame: List of all 10,000 currently enrolled students provided by the admissions office
• Sample: 400 randomly selected students from the list of enrolled students who participate in the research study.

In a general population study, the sample frame may be ‘all households in Country A,’ from which a researcher can randomly select which households take part in a study.

Sampling Error or Non-Sampling Error

When speaking about a sample frame and it’s representatively of the overall population being studied, we must also consider who is not included in the sample frame. Often those who did not participate in a research study are just as important to consider as those who were represented, as without them, key items may be skewed or missed. There are a few types of sampling error, also referred to as non-sampling error:

• Coverage Error: When a sampling frame does not sufficiently cover the population required for a study there is a coverage error. For example, if a national survey is being conducted by telephone and the sample frame is taken from a phonebook, but not all households are listed in the phonebook. A telephone or internet survey will also exclude those who do not use telephones or the internet.
• Nonresponse Error: This error describes those who were contacted for a survey but were unable to or did not want to participate. This could include those who are selected for a telephone or in-person interview and do not pick up the phone or answer their door, or those who answer but refuse to participate.
• Interviewer Error: This error occurs when an interviewer incorrectly records a response for a participant of a study. This is a form of interviewer bias that can be introduced in telephone and in-person interviews. This bias could be due to voice tone or other characteristics and may influence a respondent’s likelihood to participation or their actual answers. For example, GeoPoll has found that females may be more comfortable answering questions from female interviewers.
• Processing Error: This error refers to the technical processing of a study’s data points and errors that occur as data is collected with the use of a technology platform, or during data entry as well as data coding, cleaning, and editing.
• Response Error: This error describes those who participate in a study that either intentionally or accidentally provide inaccurate responses to a study’s questions. This can occur for a variety of reasons related to the comprehension and memory of a study’s participants. Additionally, response error can occur due to social desirability bias that can be introduced into a study when a participant answers in a way they believe would be more acceptable and accurate to their conceptualization of a study’s objective or in a way that abides by social norms. Social desirability has the potential to be introduced into any study, but if often apparent in studies covering sensitive or taboo topics for a particular society.

The above errors can be mitigated through careful sample frame selection and testing of various modes to reduce non-sampling errors. For interview-administered surveys, rigorous training of interviewers is needed to help reduce the influence of biases. For self-administered surveys, understanding local context while in the design stage is important to be able to formulate questions that can be understood clearly and accepted as valid areas of inquiry by the population of interest.

GeoPoll Sample Frames

The creation of a sampling frame for GeoPoll projects depends on client needs, project specifications, and other factors including survey mode. While sampling frames are unique for each project, there are a few common sampling frames that we use which are outlined below.

• Mobile subscribers within a certain country: GeoPoll primarily conducts research through mobile-based methodologies including voice calls and SMS messages. Due to this, sample frames for our studies are often those who have access to a mobile device within each country. GeoPoll reaches mobile subscribers in two primary ways: Partnerships with mobile network operators which enable us to call or send messages to their opted-in subscribers, and Random Digit Dialing (RDD). Using an intelligent RDD process, GeoPoll is able to randomly generate valid phone numbers that match the format of those in each country.
• Census data: GeoPoll also relies on census data and census estimates both to inform nationally representative demographic breakdowns and to create sample frames when conducting in-person research. The availability of up-to-date census data varies by country and requires a researcher to understand what information from reputable sources is available. One resource that can be used to look at each country’s local bureau of statistics and at the U.S. Census Bureau’s International Data Base.
• Aid Beneficiaries: When working with international development clients, GeoPoll is able to survey aid beneficiaries if given their contact information. This requires organizations to provide GeoPoll with a list of beneficiaries’ phone numbers or other contact information.

Determining the appropriate sample frame and other sample criteria for any one project is a complex process that cannot be represented in full here, however, we hope we have given you some insight into how GeoPoll approaches sampling. To learn more about GeoPoll’s processes please contact us here.

The post Sample Frame and Sample Error appeared first on GeoPoll.

This poses a direct threat to the fourth most populous country in the world by eroding public trust in institutions and the electoral processes, as well as increasing extremism and creating an environment of intolerance in one of the most diverse countries in Southeast Asia. The problem of misinformation and fake news became even more apparent in the post-election violence that followed the reelection of President Joko Widodo on April 17, 2019 which was flared by numerous inaccurate and false news stories surrounding the election results that were shared on social media.

In order to quantify Indonesia’s adult population access to traditional media and social media, as well as their exposure to misinformation and fake news, the University of Notre Dame in collaboration with GeoPoll, designed a comprehensive baseline survey instrument. From March 27 – April 24, 2019, GeoPoll’s team of interviewers in Jakarta, Indonesia, implemented a computer-assisted telephone interview (CATI) for 1,000 successful interviews. The results of the study can be found here in the detailed case study write-up. To conduct a project like this of your own, contact GeoPoll today.

The post Case Study: Misinformation in Indonesia appeared first on GeoPoll.

In order to learn more about how the private sector could help increase the proportion of people in Kenya who know their HIV status, Population Services International (PSI) and Population Services Kenya (PS Kenya), with support from the Children’s Investment Fund Foundation (CIFF), launched an HIV self-test demonstration project in Nairobi and Mombasa. HIV self-tests are tests that individuals can perform and interpret themselves at a private location of their choosing, and have been shown to be highly acceptable and accurate in a wide variety of populations and settings. To increase demand for HIV self-test kits, which were new to the Kenyan market, and to better understand customer satisfaction with self-testing services, PSI and PS Kenya needed to find a way to connect with consumers directly. Fortunately, GeoPoll, a ICT company that specializes in connecting organizations with people in sub-Saharan Africa, was able to make such a connection possible.

Test Kits and Methodology 

During the demonstration project, both oral-fluid and blood-based self-test kits were sold in select private-sector health facilities and pharmacies in Nairobi and Mombasa. From August 31, 2018 through March 29, 2019, GeoPoll facilitated a study for PSI to assess Kenyans’ use of and satisfaction with HIV self-test kits.  The study included two SMS-based surveys on product satisfaction of the self-test kit and post-test medical care and attitudes. Unlike traditional SMS surveys, respondents opted-in to the surveys using shortcodes found in each self-test kit purchased.

After working closely with PSI to develop the questionnaires for the product satisfaction and post-test survey, GeoPoll developed thousands of unique six-digit codes to be used as an access code to the SMS surveys. A small flyer within each HIV self-test kit provided instructions to the purchaser of the kit to send an SMS message to GeoPoll’s universal shortcode in Kenya with the keyword “HIVST”. Directly after sending a SMS message with the keyword HIVST, the sender was asked to enter a unique six-digit code found in their respective self-test kit. GeoPoll’s system verified if the code matched the codes distributed with each self-test kit. If the codes matched, the sender automatically received the product satisfaction survey. Two weeks later, the same mobile number that completed the product satisfaction survey and consented to the survey received the post-test survey via SMS.

Analysis and Results

The product satisfaction survey questions assessed the individual’s purchasing and usage experience with the self-test kit. Additionally, this survey collected demographic and behavioral data on participants, including if they had ever tested for HIV previously, which type of HIV self-test kit (blood or oral fluid) they had used, where they sought test-use information, and if they would recommend HIV self-testing to friends or family members. The post-test survey evaluated if the respondent accessed confirmatory testing and/or medical treatment following their self-test, and if their post-test experience was satisfactory.

Both of these surveys helped PSI better understand consumer experiences with private sector HIV self-tests, where users seek test use information, and whether and where they access post-test care. Moreover, it provided information on how satisfied they were with their test kit purchase, use, and post-test experiences, and how likely they would be to recommend the test kits to others. Because HIV self-tests were new to Kenya, and were designed to be used by consumers in private, it was vital that PSI work to understand user experiences and post-test behavior. By utilizing SMS surveys as a tool to measure these data points, the individuals that purchased and used the self-test kits were able to provide their opinion securely and confidentially on their experience and results of their respective tests.

The findings from the surveys showed that consumer satisfaction with private sector HIV self-testing was incredibly high, and that most users would recommend self-testing to a friend or a loved one. Given that over 80% of the participants were also willing to self-report their HIVST results, and that attrition between the initial and follow-up surveys was very low, this study also provides an interesting proof-of-concept for a low-cost, private approach to monitoring linkage-to-care following self-testing (which can be challenging for self-care medical technologies more broadly). To conduct a similar survey of your own, contact GeoPoll today to get started.

The post HIV Self-Test Kits in Kenya: A GeoPoll Facilitated Study appeared first on GeoPoll.

GeoPoll believes in TMCS’s mission of strengthening Tanzania’s media ecosystem by building the capacity of media outlets through training and technical assistance. The partnership with TMCS for the training allowed GeoPoll to assist in driving the mission forward. In order to do our part, GeoPoll provided the trainees with nationally representative audience measurement data tailored to specific program indicators. The data was used as a tool for training the attending media stakeholders on practical ways to use audience measurement data to improve the quality of community radio programming, increase listenership, and generate additional advertising revenue.

Leading the training was GeoPoll media data analytics expert Akinyi Okulo, who serves at the current Senior Client Services Manager of Media; supported by Athman Sungura, Regional Sales Lead of East Africa, and Tavian MacKinnon, Senior Manager of Social Sector.

The Training: Using Data to Develop & Attract Advertisers

GeoPoll’s day-long training combined theoretical learning with real audience measurement data and SMS perception data on major radio advertisers in Tanzania.

Akinyi began training by presenting the audience measurement data to the approximately 28 representatives from the 18 community-based radio station in attendance. The measurement data provided a comprehensive overview of the methodology and the data collected in February 2019. Community-based radio station representatives examined the results of the audience measurement data for stations Safari FM, Arusha One FM, and Chai FM, then explained how they adjusted their programming to reach more listeners as a lesson learned from the June 2018 training, Data-Driven Decisions Making – Radio Media.

Next, GeoPoll presented data from a GeoPoll SMS survey on Tanzanians’ perceptions of leading radio advertisements in the country. This survey was nationally representative at the region, age, and, gender demographics as well as reflective of awareness and appeal of major advertisements. This data survey was a used in order for the community radio stations to practice drawing conclusions from data in order to understand what types of advertisements are most appealing to Tanzanians. The exercise was guided by the training lead, Akyini, and completed on a local level, meaning participants examined data from the provinces where their radio stations operate—which encouraged the development of a targeted advertisement approach.

Training participants were then asked to collectively discuss how to improve their appeal to major advertisers and conceptualize how GeoPoll’s provided data could be used to capture and monetize potential advertisers. The training was very well-received and representatives from the community radio stations in attendance expressed a newly developed understanding of why such data is important to improving the sustainability of their respective stations.

Beyond this training session, GeoPoll will continue to work on teaching how to build the sustainability of the targeted community radio ecosystem. The series on using data for decision-making to improve listenership and the business of community-based radio stations is not over yet. GeoPoll will hold bi-annual trainings on data collected under Boresha Habari/TMCS to further acclimate community-based radio stations on how data can be used effectively for growth and sustainability.

As leaders in data collection throughout Africa, GeoPoll’s Audience Measurement data is highly respected by media agencies. Our trainings can be customized to the needs of any team seeking to learn how to analyze data for thoughtful decision making in media as well as other industries. Contact us to learn more about our trainings or data collection capabilities today.

The post Using Data to Develop & Attract Advertisers: GeoPoll Lead Training Recap appeared first on GeoPoll.

The survey targeted medium and large businesses in Liberia that paid and filed relevant business taxes. The overall goal of the survey was to better understand the perceptions and experiences that Liberia’s business taxpayers had filing and paying taxes with the Liberian Revenue Authority. Before the survey was full implemented in September 2017, GeoPoll performed a series of tests via text message (SMS) to better understand the target sample.

Selecting Survey Modes

Once GeoPoll understood the complexities and sensitivities of the study as well as the limited sample size of business taxpayers, GeoPoll initially recommended to the use of Computer Assisted Telephone Interviews (CATI) as the mode for the project. However, after a number of discussions with DAI RG3 team members, the team agreed that GeoPoll would test the survey via SMS to gain insight if response rates increased after changing key factors with implementation of the survey, despite the complex and sensitive nature of the survey’s subject matter.

Beginning in July 2017, GeoPoll tested a SMS survey with 39 questions with advanced conditional logic and routing of respondents. The sample GeoPoll utilized initially consisted of 1,756 business taxpayers in Liberia, with an additional 120 eligible respondents being added after several DAI RG3 programmatic events that invited taxpayers. The majority of these sample members had been previously contacted by GeoPoll through informative one-way messages, but were not pre-notified directly regarding the survey nor had the majority of the sample previously take a SMS survey on GeoPoll’s platform. These factors were an important characteristic of the sample, since prior engagement and pre-notification of a survey are all empirically proven to increase response rates, especially if pre-notification of a survey occurs within the same mode.

For approximately a month and a half, from July until the conclusion at the end of August, GeoPoll tested:

• The frequency of reminder messages to respondents as well as sending the initial survey invitation message different times throughout the day and different days of the week.
• Increased airtime incentive amounts from five USD to 10 USD. GeoPoll offers a small airtime incentive for all of its surveys, but this amount is normally significantly less than five USD.
• Different wording of the Opt-in messages to garner more attention from potential respondents.
• Additionally, towards the end of testing, DAI RG3 staff made direct calls to a portion of the respondents in the sample to ask them to take the survey they received via SMS.

Testing Results

The SMS testing confirmed GeoPoll’s original suggestion that SMS would not be a functional mode for a study with a very limited sample and a sensitive topic. Due to the specific targeting of this survey, GeoPoll saw much lower response rates than seen with other SMS survey projects. Although nearly 60 sample members initially engaged with the opt-in message, only four completed the survey entirely. These results allowed GeoPoll and the DAI RG3 Team to make the collective decision to switch entirely to CATI for the full implementation.

The Survey

In the final stage of the project, GeoPoll utilized a sample of approximately 3,000 medium and large business tax payers in Liberia to conduct a 41 question CATI survey, achieving 506 completed surveys. CATI is a survey method by which data is collected by an interviewer through calling phone numbers to reach respondents, asking them questions from a computerized script and recording the data electronically on a computer. CATI software is customizable and allows for researchers to control the flow of a survey based on a respondent’s answers to questions, as well as information already known about the respondent. The benefits of this mode include:

• Interviewers allow for in depth probing to complex/difficult questions.
• Interviewers are able to gauge respondent understanding of questions, and probe for clarification if needed, and ensure appropriate responses are given.
• The mode reaches populations that are not as accessible using other modes.

These benefits made CATI an ideal mode for conducting a very targeted survey on a complex and sensitive topic such as filing taxes.

Impact Assessed

An initial assessment of the data displays that business taxpayers in Liberia believe that many of filing processes are burdensome, although the majority of respondents noted that it only took one or two hours to file their respective returns. However, the majority of respondents had problems filing their business taxes due to the tax s system being down or because the wait at the Liberian Revenue Authority was too long. DAI’s RG3 program and GeoPoll will continue to analyze the data and results yielded from this unique study.

The post Testing Survey Modes to Collect Taxpayer Data in Liberia appeared first on GeoPoll.