survey methodology Archives - GeoPoll https://www.geopoll.com/blog/tag/survey-methodology/ High quality research from emerging markets Wed, 18 Nov 2026 10:24:00 +0000 en-US hourly 1 https://wordpress.org/?v=7.1.5 https://www.geopoll.com/wp-content/uploads/2017/12/favicon-2.png survey methodology Archives - GeoPoll https://www.geopoll.com/blog/tag/survey-methodology/ 32 32 Baseline and Endline Surveys: How to Run Them Remotely Without Losing Comparability https://www.geopoll.com/blog/baseline-endline-surveys/ https://www.geopoll.com/blog/baseline-endline-surveys/#respond Sat, 14 Nov 2026 10:06:25 +0000 https://www.geopoll.com/?p=26120 A baseline survey is only as useful as the endline you compare it to. If the two waves measure different things, reach […]

The post Baseline and Endline Surveys: How to Run Them Remotely Without Losing Comparability appeared first on GeoPoll.

]]>
A baseline survey is only as useful as the endline you compare it to. If the two waves measure different things, reach different people, or use different modes without a plan, the change you report may be an artefact of the method rather than the program.

That risk has grown as more evaluations move to remote data collection. Phone, SMS, WhatsApp and web surveys make it possible to reach communities that field teams cannot easily visit, and to do it faster and at lower cost. They also add new ways for waves to drift apart.

This guide covers how to design baseline, midline and endline surveys that hold up when you compare them, with a focus on remote and mixed-mode data collection in emerging markets.

What baseline, midline and endline surveys are

The three waves measure the same indicators at different points in a program’s life.

Wave When it runs What it answers
Baseline Before the intervention starts, or as early as possible Where are participants starting from? What targets are realistic?
Midline Partway through implementation Is the program on track? What needs to change before it ends?
Endline At or after the program ends What changed, by how much, and for whom?

The baseline sets the reference point. Without it, an endline can describe conditions but cannot show change.

The midline is optional on short programs but valuable on long ones. It gives implementers a chance to adjust while there is still time and budget to act.

The endline closes the loop. On its own it shows a snapshot. Compared with the baseline, it shows movement. Compared with a comparison group, it helps show whether the program caused that movement.

Example: The Seed Marketing Report, produced by GeoPoll and Resourced under the Seed Marketing Insights & Adoption (SMIA) program, ran three waves of data collection with farmers in Kenya and Uganda, from a 2023 baseline to a 2025 endline. Because the same themes were measured at each wave, the study could track how seed sourcing, variety switching, purchasing barriers and marketing channels shifted over two years, rather than describing a single point in time.

1. Start with indicators you can measure the same way every time

Comparability starts at the questionnaire. Each indicator in your results framework needs a question, or a small set of questions, that will be asked identically at every wave.

  • Lock the wording. Changing a question between baseline and endline, even to improve it, breaks the comparison. If a baseline question was flawed, keep it and add the improved version alongside it.
  • Lock the answer options and scales. A 4-point scale at baseline and a 5-point scale at endline cannot be compared directly.
  • Lock the recall period. “In the last 7 days” and “in the last month” produce different numbers for the same behaviour.
  • Fix the translation. Use the same approved translation in every wave and every language. Back-translate once, then version-control it.
  • Keep question order stable. Earlier questions shape answers to later ones. Moving a block can shift results.
  • Use standard instruments where they exist. Validated tools such as the reduced Coping Strategies Index or the Food Consumption Score already have tested wording and make results comparable with other studies.

Write a short indicator reference sheet before baseline fieldwork. For each indicator, record the exact question text, the calculation, the population it applies to, and the target. The endline team, who may not be the baseline team, will rely on it.

2. Decide early: panel or repeated cross-section

The biggest sampling decision is whether you will interview the same people at endline or a fresh sample from the same population. Make it before baseline, because a panel design needs things a cross-section does not.

Factor Panel (same respondents) Repeated cross-section (new respondents)
Measures Change within individuals or households Change at population level
Statistical power Higher for the same sample size Lower; needs larger samples to detect the same change
Main risk Attrition between waves Sample composition shifts between waves
Needs at baseline Consent to recontact, multiple contact details, unique IDs A documented, repeatable sampling frame and method
Best for Beneficiary outcomes, livelihoods, behaviour change Population awareness, perceptions, coverage

A hybrid is common: recontact the baseline sample at endline, and top up with fresh respondents to replace those lost. Analyse the panel and the top-up separately before combining them.

Whichever you choose, size the sample for the endline, not the baseline. Work out the smallest change the evaluation must detect, then add a buffer for attrition or non-response. See our guide on how to determine sample size for the core calculation.

Document the sampling frame, stratification and selection method in enough detail that a different team could repeat it exactly. For a cross-section, the endline is only comparable if it draws from the same frame in the same way. Our explainer on sample frame and sample error covers what to record.

3. Choose modes for every wave, not just the first

The same question can produce different answers depending on how it is asked. Respondents tend to give more socially acceptable answers to a live interviewer than to a self-completed SMS or web survey. Long answer lists behave differently when read aloud than when shown on a screen. These are mode effects, and they can look like program impact.

The safest design uses the same mode, or the same mix of modes, at every wave. When that is not possible, plan for it.

  • Match the mode to the instrument. SMS suits short instruments with simple answer options. CATI handles longer questionnaires, complex skip logic and sensitive topics. Mobile web and WhatsApp suit image-based questions and smartphone users. In-person interviews (CAPI) reach offline populations.
  • Keep the mode mix stable. If baseline was 70% CATI and 30% in person, aim for a similar split at endline, and record the mode for every interview so you can control for it in analysis.
  • Run a bridge study when you must switch. If baseline was in person and endline must be remote, interview a subsample in both modes. The difference gives you an estimate of the mode effect to adjust for.
  • Design for the hardest mode. If any wave may run by phone, write the baseline questionnaire so it works when read aloud. Short stems and few answer options transfer best.

For a fuller comparison of modes, see CAPI, CATI and CAWI research methods. If you are considering AI-led phone interviews for later waves, our practitioner’s guide to AI enumeration explains why a bridge study matters.

4. Plan retention at baseline, not at endline

In a panel design, the people you lose between waves are rarely random. Those who move, change numbers or stop responding often differ from those who stay. High attrition can bias endline results even when the remaining sample looks large enough.

Most retention work happens at baseline:

  • Get consent to recontact. Explain that you will call again, roughly when, and why.
  • Collect more than one contact. A second phone number, a household member’s number, or a community contact gives you a fallback when the main number fails.
  • Assign a stable respondent ID. Link every wave to it, not to a phone number that may change.
  • Stay in touch between waves. A short check-in or midline keeps contact details current and respondents familiar with the study.
  • Use consistent, timely incentives. Small airtime or mobile money rewards paid on completion support participation across waves. Pay them the same way each time.
  • Plan the endline contact protocol. Set the number of call attempts, the times of day and the fallback contacts in advance, and apply them evenly.

At endline, compare the baseline profile of respondents you retained with those you lost. If they differ on key indicators, report it and consider weighting to correct for it. Our explainer on nonresponse bias covers the options.

Example: For UNICEF’s High-Frequency Survey in Thailand, GeoPoll completed 2,583 CATI interviews in the first round, reaching respondents through verified random digit dialling. Every respondent consented at round one to be recontacted for the second round, which gave the follow-up wave a ready, nationally representative pool to work from.

5. Add a comparison group if you need to show attribution

A baseline-to-endline change shows that something moved. It does not show that the program moved it. Prices, weather, elections and other programs all change outcomes too.

If the evaluation must show attribution, you need a comparison group surveyed at the same waves, with the same questionnaire and the same mode.

  • Randomised control groups give the strongest evidence but must be built into program design from the start.
  • Matched comparison areas or households are a practical alternative when randomisation is not possible. Match on baseline characteristics that predict the outcome.
  • Difference-in-differences compares the change in the program group with the change in the comparison group. It needs baseline data for both.

Remote data collection lowers the cost of surveying a comparison group, because you do not need field teams in additional locations. That makes attribution more affordable on programs that would otherwise skip it.

Example: When Farm Radio International commissioned GeoPoll to measure the impact of its radio programming on banana farmers in Uganda, the SMS survey covered both listeners and non-listeners in the target districts. Among listeners, 83% said they had adopted practices promoted on the program. But listeners and non-listeners reported adopting new practices at similar rates overall (85% and 88%). Without the non-listener group, the adoption figure alone would have overstated the program’s distinct effect.

If a comparison group is not feasible, say so in the evaluation design. Then strengthen the analysis with contribution evidence: midline data, qualitative interviews with participants, and context data on what else changed.

Baseline checklist: before you field

Use this list to confirm the baseline will support a credible endline.

  • Every indicator has fixed question wording, answer options and recall period
  • An indicator reference sheet records question text, calculation and target
  • Translations are approved, back-translated and version-controlled
  • Panel or cross-section design is decided and documented
  • Sample size is calculated for the change the endline must detect, plus an attrition buffer
  • Sampling frame, strata and selection method are written down in full
  • Mode or mode mix is chosen with later waves in mind, and recorded per interview
  • Consent to recontact, backup contacts and stable respondent IDs are collected (panel designs)
  • Incentive type, amount and payment method are set for all waves
  • A comparison group is included, or its absence is justified
  • The questionnaire has been piloted in every language and mode
  • Raw data, codebook and cleaning scripts will be stored where the endline team can find them

How GeoPoll supports baseline and endline surveys

GeoPoll has run multi-wave surveys for development and humanitarian partners for more than a decade. During the West Africa Ebola response, we ran thirteen rounds of nationally stratified surveys in Liberia and Sierra Leone for the USAID Bureau for Africa and FHI360, with 1,000 completes per country per round. More recently, the Seed Marketing Report tracked farmers in Kenya and Uganda from baseline to endline across three waves. Both depended on the principles in this guide: stable instruments, documented sampling and consistent modes across rounds.

For baseline, midline and endline work, we offer:

  • Multi-mode data collection: SMS, CATI, mobile web, WhatsApp, the GeoPoll app and in-person CAPI, combined by design and recorded per interview.
  • Our own respondent panels and call centres in Africa, Asia and Latin America, so samples can be recontacted across waves.
  • Survey design support, from indicator mapping and questionnaire review to sampling plans that hold up at endline.
  • Translation and localisation in the languages respondents actually use.
  • Mobile airtime and mobile money incentives paid on completion.
  • Comparison group fieldwork in the same waves and modes as the program group.

Planning an evaluation or responding to a baseline RFP? Contact the GeoPoll team to discuss design, feasibility and timelines.

Frequently asked questions

What is the difference between a baseline survey and an endline survey?

A baseline survey measures conditions before a program starts. An endline survey measures the same indicators when the program ends. Comparing the two shows how much changed over the life of the program.

Can a baseline survey be done remotely?

Yes, as long as the target population can be reached by phone or online and the questionnaire is designed for the mode. Remote baselines are common for short instruments and in areas that are hard for field teams to access. Where some groups are offline, mix remote and in-person modes and keep that mix stable across waves.

Should I interview the same people at baseline and endline?

Interview the same people (a panel) if you need to measure change in individuals or households. Use a new sample from the same population (a repeated cross-section) if you need population-level estimates. Panels give more statistical power but require a retention plan from baseline.

What if the baseline was done in person and the endline must be remote?

Run a bridge study. Interview a subsample both in person and remotely, estimate the mode effect, and adjust for it in analysis. Report the switch and the adjustment in the evaluation.

How large should a baseline sample be?

Size it for the endline. Start from the smallest change the evaluation must detect, calculate the sample needed to detect it, and add a buffer for attrition or non-response.

The post Baseline and Endline Surveys: How to Run Them Remotely Without Losing Comparability appeared first on GeoPoll.

]]>
https://www.geopoll.com/blog/baseline-endline-surveys/feed/ 0
Computer-Assisted Personal Interviewing (CAPI) Surveys: A Guide https://www.geopoll.com/blog/capi-surveys-guide/ Fri, 22 Apr 2022 13:32:40 +0000 https://www.geopoll.com/?p=19343 Computer-Assisted Personal Interviewing (CAPI) survey methodology refers to survey data collection by in-person (face-to-face) interviewers using devices such as computers, smartphones, and […]

The post Computer-Assisted Personal Interviewing (CAPI) Surveys: A Guide appeared first on GeoPoll.

]]>
Computer-Assisted Personal Interviewing (CAPI) survey methodology refers to survey data collection by in-person (face-to-face) interviewers using devices such as computers, smartphones, and tablets to administer the questionnaire and capture the answers. CATI surveys are structured interviews, flowing as dialogues between two people and guided by predefined questionnaires loaded and driven by a computer device.

COMPUTER ASSISTED PERSONAL INTERVEW capi

CAPI methodology is best suited for complex investigations involving long and detailed questionnaires. The interviewer can help explain intricate questions, demonstrate how to fill in the questionnaire, and ensure the appropriate display of videos or other forms of stimuli.

In this article, we walk through the Computer-Assisted Personal Interviewing (CAPI) methodology, its benefits, and the steps needed to execute CAPI surveys.

Types of CAPI Surveys

Computer-Assisted Personal Interviewing surveys can be categorized into two types determined by how the sampling is handled.

  • Named CAPI surveys – where the researchers know the respondents beforehand and can make appointments to conduct the study. An example would be interviewing managers of companies or medical professionals in a city. It is possible to feed the CAPI system with a database of participants. The researcher can preload known respondent information. At GeoPoll, we call this CAPI and CATI feature Sample Management.
  • Anonymous CAPI surveys – conducted randomly, for example, on a street where the researchers do not know the respondents and may need to screen them by observation and using profiling questions.

Benefits of CAPI Surveys Over Traditional Paper Surveys

  • Guidance – CAPI facilitates logic checks, skip patterns, and validations during the interview to make the survey more efficient and improve data quality.
  • Efficiency – CAPI saves time and resources in subsequent steps of data cleaning and data entry.
  • Real-time monitoring – CAPI is an excellent tool to monitor enumerators in real-time or later during validity checks. It is possible to automatically record each interview’s start time, end time, and GPS location, making it easy for supervisors to cross-check the processes and manage teams.
  • Real-time results – Data collected through CAPI surveys is immediately relayed for real-time analysis and processing.
  • Quality of data – Validation and quality control of CAPI surveys can be done when filling out the survey, and it eliminates human error during data entry. Sessions can also be recorded for validation.
  • Rich media – During a CAPI survey, the enumerators can take photos, record audio, and take videos to complement the study.
  • Personification – CAPI allows direct contact with the interviewee, which helps complete the questionnaire, both in terms of administering stimulus and offering explanations if necessary. Personal contact makes the interview fluid and warm and may result in greater collaboration from the respondent than in remote surveys.

CAPI face to face surveys

Steps and Considerations for Planning and Executing a Successful CAPI Project

As with all types of surveys, planning and executing a CAPI survey is dependent on several factors, including the research objective, environmental influences, complexity, and the availability of other methodologies, among others. Below, we look at generic steps to consider based on our experience and standard CAPI processes:

  1. Objectives and methodology choice – Determine the project objectives and factors that justify using CAPI over other methodologies. Consider the time and cost of the fieldwork, its scope, and its limitations.
  2. Map the project – Design a work schedule to execute the research project, from ideation to data collection, to analysis and reporting.
  3. Software selection – Evaluate and choose the best CAPI platform and apps to use. At GeoPoll, we have developed an ecosystem for CAPI surveys that includes the Interviewer App tailored to emerging markets and backed by our data processors for data validation, analysis, and reporting.
  4. Hardware selection – Evaluate and select the computer equipment or mobile devices used for the data collection. It is advisable to use devices with internet connections for a real-time relay of data and portability for convenience. GeoPoll uses smartphones and tablets.
  5. Personnel recruitment and training – Several factors go into selecting personnel to perform the CAPI survey in the field (interviewers or agents). There are language and cultural nuances to consider, education levels, knowledge of the subject matter, and more. The team also needs to be trained well on how to conduct effective surveys, how to use the selected apps and devices, and how to flow through the specific survey they will be administering.
  6. Pilot testing – A lot can go wrong in any research project. It is therefore imperative for researchers to meticulously pilot test the survey with the interviewers and devices in the field. This process can then be used to adjust the questionnaires, provide post-exposure training, adjust the verbatim, and correct any errors detected.
  7. Fieldwork – After a successful pilot, the actual data collection can commence. If applicable, arrange appointments with respondents or get the interviewers on the ground, making sure that the data collection app and devices are being used and working as planned. Monitor the survey process, detect and correct errors on the go, measure the length of the interviews (LOI), and track the productivity of the team. The GeoPoll Interviewer App includes all these functionalities.
  8. Data consolidation and validation – Data is only as good as its integrity. Whether real-time or after the data collection process, it is crucial to perform quality checks and ensure that everything checks out.
  9. Data analysis – The data collected and cleaned from the CAPI survey can then be tabulated and analyzed, and the open-ended questions coded according to the research question and objectives.
  10. Final report and delivery of results

Conduct Mobile-Based In-person Surveys Anywhere in the World

GeoPoll administers face-to-face surveys through our own Computer-Assisted Personal Interviewing (CAPI) mobile application, which is specifically built for use in emerging markets and includes features such as offline capabilities, remote progress tracking, and interviewer metrics. We can conduct face-to-face interviews via CAPI in almost any country in the world and have experience in responding quickly to fast-moving situations. Please contact us to discuss your CAPI project needs.

The post Computer-Assisted Personal Interviewing (CAPI) Surveys: A Guide appeared first on GeoPoll.

]]>
How to Determine Sample Size for a Research Study https://www.geopoll.com/blog/sample-size-research/ Wed, 07 Apr 2021 00:49:50 +0000 https://www-new.geopoll.com/?p=17776   Sample size is a research term used for defining the number of individuals included in a research study to represent a […]

The post How to Determine Sample Size for a Research Study appeared first on GeoPoll.

]]>
 

sample size research
Sample size is a research term used for defining the number of individuals included in a research study to represent a population. The sample size references the total number of respondents included in a study, and the number is often broken down into sub-groups by demographics such as age, gender, and location so that the total sample achieves represents the entire population. Determining the appropriate sample size is one of the most important factors in statistical analysis. If the sample size is too small, it will not yield valid results or adequately represent the realities of the population being studied. On the other hand, while larger sample sizes yield smaller margins of error and are more representative, a sample size that is too large may significantly increase the cost and time taken to conduct the research.

This article will discuss considerations to put in place when determining your sample size and how to calculate the sample size.

Confidence Interval and Confidence Level

As we have noted before, when selecting a sample there are multiple factors that can impact the reliability and validity of results, including sampling and non-sampling errors. When thinking about sample size, the two measures of error that are almost always synonymous with sample sizes are the confidence interval and the confidence level.

Confidence Interval (Margin of Error)

Confidence intervals measure the degree of uncertainty or certainty in a sampling method and how much uncertainty there is with any particular statistic. In simple terms, the confidence interval tells you how confident you can be that the results from a study reflect what you would expect to find if it were possible to survey the entire population being studied. The confidence interval is usually a plus or minus (±) figure. For example, if your confidence interval is 6 and 60% percent of your sample picks an answer, you can be confident that if you had asked the entire population, between 54% (60-6) and 66% (60+6) would have picked that answer.

Confidence Level

The confidence level refers to the percentage of probability, or certainty that the confidence interval would contain the true population parameter when you draw a random sample many times. It is expressed as a percentage and represents how often the percentage of the population who would pick an answer lies within the confidence interval. For example, a 99% confidence level means that should you repeat an experiment or survey over and over again, 99 percent of the time, your results will match the results you get from a population.

The larger your sample size, the more confident you can be that their answers truly reflect the population. In other words, the larger your sample for a given confidence level, the smaller your confidence interval.

Standard Deviation

Another critical measure when determining the sample size is the standard deviation, which measures a data set’s distribution from its mean. In calculating the sample size, the standard deviation is useful in estimating how much the responses you receive will vary from each other and from the mean number, and the standard deviation of a sample can be used to approximate the standard deviation of a population.

The higher the distribution or variability, the greater the standard deviation and the greater the magnitude of the deviation. For example, once you have already sent out your survey, how much variance do you expect in your responses? That variation in responses is the standard deviation.

Population Size

populationThe other important consideration to make when determining your sample size is the size of the entire population you want to study. A population is the entire group that you want to draw conclusions about. It is from the population that a sample is selected, using probability or non-probability samples. The population size may be known (such as the total number of employees in a company), or unknown (such as the number of pet keepers in a country), but there’s a need for a close estimate, especially when dealing with a relatively small or easy to measure groups of people.

As demonstrated through the calculation below, a sample size of about 385 will give you a sufficient sample size to draw assumptions of nearly any population size at the 95% confidence level with a 5% margin of error, which is why samples of 400 and 500 are often used in research. However, if you are looking to draw comparisons between different sub-groups, for example, provinces within a country, a larger sample size is required. GeoPoll typically recommends a sample size of 400 per country as the minimum viable sample for a research project, 800 per country for conducting a study with analysis by a second-level breakdown such as females versus males, and 1200+ per country for doing third-level breakdowns such as males aged 18-24 in Nairobi.

How to Calculate Sample Size

As we have defined all the necessary terms, let us briefly learn how to determine the sample size using a sample calculation formula known as Andrew Fisher’s Formula.

  1. Determine the population size (if known).
  2. Determine the confidence interval.
  3. Determine the confidence level.
  4. Determine the standard deviation (a standard deviation of 0.5 is a safe choice where the figure is unknown)
  5. Convert the confidence level into a Z-Score. This table shows the z-scores for the most common confidence levels:
Confidence level z-score
80% 1.28
85% 1.44
90% 1.65
95% 1.96
99% 2.58

 

  1. Put these figures into the sample size formula to get your sample size.

sample size calculation

Here is an example calculation:

Say you choose to work with a 95% confidence level, a standard deviation of 0.5, and a confidence interval (margin of error) of ± 5%, you just need to substitute the values in the formula:

((1.96)2 x .5(.5)) / (.05)2

(3.8416 x .25) / .0025

.9604 / .0025

384.16

Your sample size should be 385.

Fortunately, there are several available online tools to help you with this calculation. Here’s an online sample calculator from Easy Calculation. Just put in the confidence level, population size, the confidence interval, and the perfect sample size is calculated for you.

 

GeoPoll’s Sampling Techniques

With the largest mobile panel in Africa, Asia, and Latin America, and reliable mobile technologies, GeoPoll develops unique samples that accurately represent any population. See our country coverage here, or contact our team to discuss your upcoming project.

The post How to Determine Sample Size for a Research Study appeared first on GeoPoll.

]]>
Quantitative Data Analysis https://www.geopoll.com/blog/quantitative-data-analysis/ Thu, 21 Jan 2021 15:00:03 +0000 https://www.geopoll.com/?p=7452 Once quantitative data has been gathered and cleaned, the next step in the research process is to analyze the data in order […]

The post Quantitative Data Analysis appeared first on GeoPoll.

]]>
quantitative data analysisOnce quantitative data has been gathered and cleaned, the next step in the research process is to analyze the data in order to glean insights from it. This step is crucial as data must be analyzed properly before a researcher can understand which findings are significant and report on the findings or make a judgment on their hypothesis. If data is not analyzed with care, findings may be misrepresented, which can lead to decisions being made upon statistics that did not accurately represent the entire dataset.

For example, one might use an average to represent a fact such as the amount customers are willing to pay for ice cream. However, if 95% of respondents stated that they would spend $5 or less on a pint of ice cream, and 1% of respondents stated that they would spend $100 on ice cream, an average would be skewed by the 1% who would spend much more. In this case, a researcher may decide that a different statistic, such as the median, would more accurately represent the findings. Making these judgments is an important step in the quantitative data analysis process, as are ensuring that data is properly cleaned and coded prior to analysis.

Quantitative Analysis Methods

Quantitative data is analyzed using statistical methods, as quantitative data represents numbers from which datapoints can be calculated. Data from a quantitative dataset, such as survey results, is usually loaded into a program such as Excel or the statistics software SPSS which enables researchers to quickly create tables and charts in order to examine findings. Often the first step in analyzing a dataset is to view top-level findings using descriptive statistics such as mean, median, and mode.

Descriptive Statistics

In the below definitions, we will use the example of a survey with 400 respondents who were asked to rate their opinion of chocolate ice cream on a scale of 1 ‘strongly dislike’ to 5 ‘strongly like’. The data indicated that 100 rated an ice cream flavor a ‘5’, 200 rated it a ‘4’, and 100 rated it a ‘3’.

  • Mean or average: The numerical average of a set of numbers.
    • In the above example, the average rating would be ((5×100)+(4×200)+(3×100))/400= 4
  • Median: The median is the midpoint in a set of numbers.
    • In the above example, the median would be the number in the 200th row of data. In this case it would be 4, but depending on the dataset, the median can be different from the average.
  • Mode: The number that occurs the most often in a dataset.
    • In the above example, this would also be 4 as it occurred 200 times, while 5 and 3 only occur 100 times each.
  • Range: A statement that represents the lowest and highest numbers in a dataset.
    • In the above example, the range would be from 3 to 5.
  • Distribution or Percentage: The percent represented by each category within a group, out of the total (100%).
    • In the above example, instead of looking at the dataset as a whole this would report that ‘25% rated the ice cream a ‘5’, 50% rated it a ‘4’, and 25% rated it a ‘3’ 

Cross Tabulations

After examining descriptive statistics, researchers may use cross-tabulations to dig deeper into a dataset. A cross tabulation or crosstab is a way to show the relationship between two variables and is often used to compare results by demographic groups. For the above example, we could create crosstabs to show results by age:

Crosstabs can also be created to examine one datapoint by another, such as if those who rate chocolate ice cream highly also rate vanilla ice cream highly, or if there is a different relationship between the two variables. Crosstabs are useful to better understand the nuances of a dataset and the factors that may influence a datapoint.

Calculating Statistical Significance

When researchers are looking to prove or disprove hypotheses, they will often also use measures to calculate the statistical significance of their findings. Measures of statistical significance demonstrate if a finding is merely due to chance or if it is a significant finding that should be reported on. In the above example, without calculating statistical significance we cannot be sure if the difference in results between those aged 18-24 and 25-34 is due to the difference in age groups, or if the findings are a coincidence based on the sample that was selected and not related to age.

Statistical significance is usually represented by a statistic called a p-value. A p-value is a calculated number between 0 and 1, and the lower the p-value is, the less likely it is that the results were due only to chance. Typically, a p-value of less than 0.05 is regarded as statically significant, as it means there is a less than 5% likelihood that the results were due to chance. While having a p-value of under 0.05 doesn’t necessarily mean that the stated hypothesis is true, it decreases the chances that any differences in the dataset are occurring by chance. Researchers who are running tests to make decisions, for example to determine if populations prefer vanilla or chocolate ice cream in order to make purchasing decisions, should use a test of significance in order to have more confidence in their decision making.

Programs including Excel, R and SPSS can calculate the significance of findings through a series of steps, outlined in more detail here. If you work with a full-service research agency such as GeoPoll, we can run statistical significance tests for you and include the resulting data in our data analysis.

Conduct Quantitative Data Analysis with GeoPoll

GeoPoll is a research company that gathers data for international organizations, governments, consumer brands, and media houses which enables better decision making. Our services range from study and questionnaire design to data analysis, including the creation of data tables, crosstabs, and full research reports. To learn more about our capabilities or get a quote for your next project, please contact us.

The post Quantitative Data Analysis appeared first on GeoPoll.

]]>
Quantitative vs Qualitative Data https://www.geopoll.com/blog/quantitative-vs-qualitative-data/ Tue, 17 Nov 2020 15:32:24 +0000 https://www.geopoll.com/?p=7302 Quantitative and qualitative research methods differ in several ways, including how quantitative and qualitative data is collected and analyzed and the type […]

The post Quantitative vs Qualitative Data appeared first on GeoPoll.

]]>
Quantitative and qualitative research methods differ in several ways, including how quantitative and qualitative data is collected and analyzed and the type of insights that each method can provide. While researchers can combine quantitative and qualitative methods to more fully answer their research questions, each has unique characteristics that should be considered throughout the lifecycle of a research project. Jump to GeoPoll’s cheat sheet on qualitative vs quantitative research. 

Difference Between Quantitative and Qualitative Data

The primary difference between quantitative and qualitative data is that quantitative data represents data that can easily be measured or quantified, such as the number of people who have bought a product. Qualitative data represent opinions or feelings and cannot be represented by a numerical statistic such as an average.

For example, if a survey asked 500 respondents the question “Did you buy ice cream today?”, and 300 responded ‘yes’ while 200 responded ‘no’, we would know that 300/500 or 60% bought milk, a quantitative fact. If the same survey asked an open-ended follow-up question: “Why did you choose the brand of ice cream you bought?” you would receive qualitative insights that are unique to each respondent. One person may say, ‘I liked the packaging and label colors’ while another may state, ‘It was the first one I saw on the shelf.’ These descriptive insights cannot easily be quantified into numbers, so they are qualitative.

Qualitative vs Quantitative Analysis

Another difference between quantitative and qualitative research is how data is analyzed. While quantitative data can be analyzed statistically and calculated into averages, means, and other numerical data points, qualitative data analysis involves a more complex system.

To glean insights from qualitative data, researchers conduct a manual analysis of datasets and often code responses into categories. For example, to analyze focus group data, researchers could review transcripts or recordings and group similar sentiments together into categories. Due to this manual process, qualitative data analysis is a longer and more labor-intensive process than quantitative data analysis, which is another factor to keep in mind when deciding what type of data to collect.

While some methods such as focus groups typically collect qualitative data, other methods such as surveys often collect quantitative and qualitative data within one survey instrument, as outlined below.

Quantitative Data Examples

Quantitative data is collected through several methods, including surveys, controlled experiments, and certain observation types. Quantitative data types include:qualitative vs quantitative examples

  • Yes/no questions
    • “Did you go to work today? 1) Yes 2) No”
  • Single choice questions
    • “What is your favorite flavor of ice cream? 1) Vanilla 2) Chocolate 3) Cookie Dough 4) Peppermint 5) Chocolate chip”
  • Multiple choice or ‘select-all-that-apply’ questions
    • “Which of the following products did you buy last week? 1) Toothpaste 2) Soap 3) Vegetables 4) Meat 5) Grains 6) Bread”
  • Ranking questions
    • “Please rank the statement ‘I enjoy ice cream’ from 1: Strongly disagree to 5: Strongly agree”
  • Numerical range questions
    • “How much money did you spend at the grocery store today? Please respond with a dollar amount”
  • Quantitative observations
    • Observations that can be categorized or quantified, such as the number of times a person checks their phone in a given time. These observations often take place in a controlled environment.

As all of these question types collect data that fit into set categories or can be calculated into averages and other statistics, they are quantitative.

Qualitative Data Examples

Qualitative data can also be collected through certain types of survey questions, in addition to interviews and focus groups. Examples of qualitative data include:

  • Open-ended survey questions
    • “Why is cookie dough your favorite flavor of ice cream?”
  • Unstructured or semi-structured interviews
    • Unstructured and semi-structured interviews allow topics and questions to flow naturally, rather than only asking questions from a set question list in a specific order.
  • Focus groups
    • In focus groups, multiple people have a discussion (in-person or via an online or mobile-based chat group) facilitated by a trained moderator who gives prompts to start conversations.
  • Unstructured observation
    • Researchers can gather qualitative data through unstructured observations, such as observing participants as they partake in certain activities such as shopping.
  • Documents or content analysis
    • Reviewing documents to better understand a particular topic or categorize elements of documents is a type of qualitative research.

Data collected from these methods and question types do not provide numerical statistics but instead, give insights that are often longer and more detailed than their quantitative counterparts.

When Should I Use Quantitative or Qualitative Research?

focus group qualitativeOnce you understand the types of data provided by qualitative and quantitative research and the methods for each, it’s essential to understand how to utilize each type of data best. Generally, quantitative data is used to answer precise questions and prove or disprove hypotheses, while qualitative data provides richer insights on a smaller scale.

Qualitative research is often conducted at the beginning of a study when researchers are looking to gather broad, unstructured information on a topic to create a hypothesis, which can then be more clearly answered by quantitative research. Qualitative data collected through unstructured interviews or focus groups can also inform the development of a more structured questionnaire administered to a larger group.

For example, a focus on different ice cream brands may uncover that participants generally consider price and packaging first. That information can then be inputted into a quantitative question: “Which is more important to you when buying ice cream? 1) Price 2) Packaging” administered to a nationally representative sample.

Qualitative data may also be used as part of a mixed-methods research study to add additional context to quantitative data. A researcher may administer both a quantitative questionnaire and conduct a qualitative analysis of interviews with subject-matter experts to form a more robust conclusion.

Surveys can also be split between qualitative and quantitative; Many surveys are mostly quantitative questions that can be quickly analyzed, plus one or two qualitative questions that provide deeper insights into the topic being studied.

Quantitative vs Qualitative Data: Definitions and Uses Cheat Sheet


qualitative vs quantitative
GeoPoll has experience designing and administering both quantitative and qualitative research studies around the globe. Our research methods include surveys with closed-ended and open-ended question capabilities, mobile-based focus groups, concept testing, and more. To learn more about GeoPoll’s capabilities, please contact us today.

The post Quantitative vs Qualitative Data appeared first on GeoPoll.

]]>
Benard Okasi on GeoPoll’s Research Processes https://www.geopoll.com/blog/benard-okasi-geopolls-research-processes/ Tue, 03 Nov 2020 16:00:41 +0000 https://www.geopoll.com/?p=7273 Benard Okasi Interview Benard Okasi is GeoPoll’s Director of Research, and oversees GeoPoll’s research team and data outputs. Below is an abbreviated […]

The post Benard Okasi on GeoPoll’s Research Processes appeared first on GeoPoll.

]]>

Benard Okasi Interview

Benard Okasi is GeoPoll’s Director of Research, and oversees GeoPoll’s research team and data outputs. Below is an abbreviated version of a conversation he had with Roxana Elliott, VP Marketing, about his background in research and how the industry is shifting to mobile methods.

Roxana Elliott: Thanks for joining me! Can you start by telling me a bit about your background and where you worked before GeoPoll?

Benard Okasi: Prior to GeoPoll I was at Synovate, a research company that operates in multiple countries – I started there in 2011 and it was later acquired by Ipsos in 2012. At Ipsos I worked in different positions, moving from a research assistant up to a senior research executive. My role was mainly business development, project management and providing insights to clients through reports with actionable insights. Towards the end of 2014, my main focus was on Coca Cola account, and I was placed at Coke as an implant for a year where my main role was to support the client on the projects that were executed by Ipsos for Coke in the then CEWA business unit team.

RE: Why did you first come to GeoPoll and how long have you been here?

BO: While working at Ipsos, the CEO of GeoPoll gave a presentation to research firms in Nairobi about mobile research and where the future of data collection is heading, which is self-completion surveys through mobile, and GeoPoll is here to help bridge the gap. I was curious about the new way GeoPoll was doing data collection through mobile and not having researchers need to go out and collect data in person. I have now been at GeoPoll for 5 years, I first started as a research executive working on data and client support, then managing our partnership relationships with other research agencies, and now leading the research team.

RE: Can you tell me more about the research team and what your responsibilities are?

BO:The research team now is made up of 15 staff, within which we have a data processing team, data analysts, and media analysts. The data processing team does data cleaning, processing and data quality checks. Our data analysts deal with complex analysis of data – for example if clients need significance testing. The media data team looks at audience measurement data and generates actionable insights for our clients. Most of our team members have a research background and have studied statistics hence able to look into data from a statistical point of view and provide complex analysis when required.

RE: What excites you about working for GeoPoll?

BO: What excites me is the team energy and synergy to support clients – when you look at the speed at which we complete projects, with the combined efforts of different departments, we can deliver projects within 2-3 days or a week. We are also able to sit in a central office and collect data in over 50 countries, which shows what the future is in remote data collection. I love the combined effort of the team, and if there are issues in a project we sit down as a team and come up with solutions and the way forward without delays.

RE: How does what we offer at GeoPoll compare to traditional methods in your experience?

BO: If clients go for traditional research, you can only use past data or say old data to inform on their decisions, and what we’ve found at GeoPoll is that most clients want real time information. With mobile research, we can get a set questions from client today and be able to give clients results tomorrow. GeoPoll plays a key role in delivering quality, timely and cost-effective results to clients.

RE: Have you seen a resistance of people moving to mobile research?

There are tracker projects that have been running using traditional research for a long time targeting general population and because mobile data collection only targets a mobile owned population, some clients are resistant to changing the methodology. But markets are changing quickly as mobile penetration has grown over the years – in Kenya I think mobile penetration is over 90%, so that tells you that the people we are targeting through mobile and the information they give us won’t be different from what we would get through traditional (face to face) research. I think that mobile data collection is the future, and the future is here.

RE: Are there any new products you are working on within the research team?

As we continue to drive real-time data delivery to clients, we have made improvements in our systems, including the creation of dashboards which enable us to have more automated systems so we can deliver to clients even quickly. Clients can go directly to a dashboard and pull data and do extra analysis as soon as it’s collected. This innovation around our deliverables will help clients make decisions right away. For some of our larger clients, our team has been able to work on projects in over 30 countries at once, and we’ve created automated processes to deliver quality data regularly for them which has led us to improve our processes over time.

RE: What do you like outside of work?

I love meeting with friends and driving around, and spend most of my time with my family.

RE: Finally, what do you think it takes to be successful in a researcher?

You need to be open-minded and flexible to succeed, and must put the client first in everything you do. Teamwork plays a key role towards the success of any organization or any team so if teams work together you can achieve anything.

The post Benard Okasi on GeoPoll’s Research Processes appeared first on GeoPoll.

]]>
GeoPoll’s John Paul Murunga on the Evolution of the Market Research Industry https://www.geopoll.com/blog/john-paul-murunga-on-the-evolution-of-the-research-industry/ Tue, 20 Oct 2020 16:17:12 +0000 https://www.geopoll.com/?p=7247 John Paul Murunga is GeoPoll’s Regional Director for East Africa, and oversees our business development efforts in East Africa. Below is an […]

The post GeoPoll’s John Paul Murunga on the Evolution of the Market Research Industry appeared first on GeoPoll.

]]>
John Paul Murunga is GeoPoll’s Regional Director for East Africa, and oversees our business development efforts in East Africa. Below is an abbreviated version of a conversation he had with Shannon McCrocklin, Marketing Specialist, about his experience in market research and what excites him about GeoPoll’s work.

Shannon McCrocklin: Tell me about your background before you came to GeoPoll – what space did you work in?

John Paul Murunga: I am a statistician by training and on top of that an Accredited marketing professional from the Chartered Institute of Marketing in the UK. Before I came to GeoPoll I was working as a marketing research consultant with a focus on commercial or consumer research. Prior to GeoPoll, I worked with Synovate and then Ipsos, and earlier I was with Nielsen. Hence, I am a research industry person out-and-out.

SM: What drew you to GeoPoll and how long have you been with the team?

JPM: I have been with GeoPoll for 4 and a half years, it’s funny how time flies! What first drew me to GeoPoll was seeing how much research was evolving and wanting to be part of the next generation in research. Back then, people would not consider SMS as a method of doing surveys, and online/remote research modes were frowned upon.

Presently we live in a world that is moving so fast, we cannot afford to wait for months to receive information that should inform decision making. Can you imagine waiting for 2 months to identify what your target consumers think about your product offering? We have seen for instance from the COVID-19 pandemic how a week can alter the world as we know it. Research solutions must be timely and be specific to remain useful.

SM: Can you briefly describe your role now?

JPM: Currently, I am the Regional Director for the Eastern Africa region. I oversee a team of dynamic, highly skilled, and motivated professionals whose mission is to support clients across the region with information to inform their decision-making. We work with customers across various sectors, including large multi-nationals, local organizations, and small and medium-sized enterprises. Because our solutions are varied, we are well-positioned to support a diverse range of clients.

SM: What do you most enjoy about working for GeoPoll? 

JPM: I cherish many things about working with GeoPoll – GeoPoll epitomizes what research in the information age looks like. When research is paired with technology, I think that is where the magic happens! This axis constantly inspires me: Quality research-delivered on the back of technology, delivered with speed, at a fraction of what traditional research would cost making it more affordable.

SM: What has surprised you about GeoPoll and the projects we work on?  

JPM: Many things, but early on it was how suddenly, working with the same clients, we were able to be efficient in study design, especially from a questionnaire length perspective. For clients who traditionally would have 40-50-page questionnaires asking all sorts of things, we were able to conduct studies for them with 10-30 very definite questions tailored to specific objectives.

The speed of how projects can be turned around was mind-blowing at the start, but now I am used to it. Can you imagine doing a survey of n=3,000 nationally in 2-3 days, and delivering the results displayed on an online dashboard immediately once data collection is closed? This is work that would take weeks or months in other settings. In face-to-face research, interviewers would still be on the ground, with clients worrying about if an interviewer in fact went to the field. Meanwhile, GeoPoll would have reported the results, and the client made informed decisions for their businesses and moved on to other pressing issues.

SM: What are you excited about in terms of where GeoPoll will go in the future?  

JPM: I think the COVID-19 pandemic has accelerated the need to infuse technology in research. GeoPoll is at the center of this and we are already pioneering many efficient, forward-looking research solutions for customers across multiple geographies. We will continue developing these as we go into the future as this is the direction the world is taking.

SM: Do you have a favorite project or experience at GeoPoll you’d like to share?

JPM: I have always given this as an example of how best research studies can be executed in today’s world. The project was looking to reach farmers in the Kandahar region of Afghanistan. The end client was in the US; the agency implementing the client’s intervention was in Afghanistan, and I was the project lead was based in Nairobi. We conducted 1,000 successful IVR interviews in the local languages (Pashto and Dari) remotely from our Nairobi operations Hub. This done within 2 weeks, and the client had their study results and went ahead to implement the recommendations from the research.

SM: What’s a fact about yourself that people may not know right away?  

JPM: I love farming and am a smallholder crops farmer. I like giving back to society whenever I can and work with various charity organizations. I am always keen on being outdoors and visiting new places, and this year was planning to do the famous Cairo to Cape route by road joining from Kenya but was hampered by COVID-19. We will be back in 2021 inshallah!

SM: What does it take to succeed in your line of work? 

JPM: There are no excuses, and one must put in the grind – hard work and consistency are key. You also must be widely read and have a flexible mindset, as we work with clients across multiple industries. As a market research consultant, having knowledge of various industries is vital, or else you are not going to have proper engagements. Finally and most important is nurturing human relationships. We are in a people business, and humans require authentic interactions. We must be understanding, communicate effectively, and be empathetic in how we undertake our work.

The post GeoPoll’s John Paul Murunga on the Evolution of the Market Research Industry appeared first on GeoPoll.

]]>
What is Random Digit Dialing? https://www.geopoll.com/blog/what-is-random-digit-dialing/ Tue, 29 Sep 2020 23:16:03 +0000 https://www.geopoll.com/?p=7211 Sample selection is an important part of any research project, and for those conducting research through telephone interviews, random digit dialing is […]

The post What is Random Digit Dialing? appeared first on GeoPoll.

]]>
Sample selection is an important part of any research project, and for those conducting research through telephone interviews, random digit dialing is a useful sampling technique. Random digit dialing or RDD is a type of probability sampling in which phone numbers are randomly generated using a software system and used to create the sample for a research project.

Random digit dialing or RDD is commonly used to conduct general population studies, as it allows researchers to create a sample frame that represents everyone with access to a phone in a population, rather than only those who are listed in a phonebook or have shared their phone number with another source. As random digit dialing does not require researchers to gain access to existing lists of phone numbers, it is one of the fastest and simplest ways to create sample for researchers who do not have an existing sample source. At GeoPoll, we have access to a large database of mobile subscribers in most of the countries we work in, however, we utilize Random Digit Dialing as a sample source for certain projects or in countries where we do not have existing sample.

Pros and Cons of Random Digit Dialing Sample

While random digit dialing is a popular technique, there are some pros and cons to using RDD over a provided sample source, such as a list of specific phone numbers. Some of the pros and cons of random digit dialing include:

Pros of Random Digit Dialing

Cons of Random Digit Dialing

  • May be difficult to reach more targeted respondents, such as those with specific professions, as you do not have any prior information about the characteristics of each respondent, which other sample sources may provide. You also do not have information about those who do not respond to your survey (known as nonresponse error) for the same reason.
  • Depending on the phone number format within a country and use of mobile phones versus landlines, targeting respondents by location can also be a challenge
  • Not all generated numbers may be valid, which can lead to lower response rates than with a pre-verified list of numbers

Overall, when administered through an experienced research firm, RDD is an excellent way to gather high-quality sample, especially for projects aiming to gather a nationally representative sample.

GeoPoll’s Random Digit Dialing Process

GeoPoll has our own database of respondents in many of the countries we operate in who are profiled by demographics include age, gender, and location, but in certain circumstances, we may turn to RDD to gather sample. In these cases, GeoPoll uses our extensive knowledge of telephone samples to intelligently generate RDD sample that has response rates in-line with those found from the GeoPoll respondent database. GeoPoll’s random digit dialing has three main steps for generating and testing phone numbers:

  1. Mobile number generation: Using public information, GeoPoll’s team will identify the most common prefixes for each mobile network operator operating in a market, as well as the percentage share that each mobile network operator represents. We then randomly generate lists of unique numbers that include numbers from each telecom network. This ensures that every mobile number within a country has an equal opportunity of being selected and reduces risks of selection bias.
  2. Mobile number validation and testing: Once the initial files are generated, GeoPoll conducts a validation process that identifies likely active and inactive numbers, allowing us to remove numbers that are inactive before proceeding with live testing. GeoPoll’s call center teams then conduct testing with the final list of numbers. If the response rates during testing are in line with expectations based on previous work, we proceed with a survey. If we encounter high numbers of disconnected numbers, we may generate additional numbers.
  3. Survey administration: Once GeoPoll has finalized the list of mobile numbers, it is handed off to our trained survey interviewers for full survey administration. During this stage, each interviewer is given a unique list of mobile numbers and is equipped with the GeoPoll Computer Assisted Telephone Interviewing (CATI) Application, which tracks the outcome of each call. The CATI application tracks the percent of phone numbers that are invalid, and the percent of respondents who refuse to take a survey. For those respondents who agree to take a survey, GeoPoll’s system securely stores demographic information along with their telephone number so they can participate in future research.

Random digit dialing is a useful method for conducting surveys via telephone calls in almost any country around the globe. To learn more about GeoPoll’s experience with RDD surveys or to get a quote for your own project, please contact us.

The post What is Random Digit Dialing? appeared first on GeoPoll.

]]>
Weighting Survey Data: Methods and Advantages https://www.geopoll.com/blog/weighting-survey-data-raking-cell-weighting/ Tue, 08 Sep 2020 18:47:02 +0000 https://www.geopoll.com/?p=7174 In two of our previous blogs, we discussed the importance of the sample frame and sampling techniques for any research project. Understanding […]

The post Weighting Survey Data: Methods and Advantages appeared first on GeoPoll.

]]>
data weighting image 2In two of our previous blogs, we discussed the importance of the sample frame and sampling techniques for any research project. Understanding the sampling frame, potential sample errors, and the best sampling technique for your specific project is a critical step that must be taken before data collection begins. However, even with careful planning, sometimes the sample you end up reaching does not match the sample universe you were aiming to meet. This could be due to factors including time or budget constraints, high non-response from certain groups, or a sample frame that did not perform as expected. In order to mitigate the effects of any sample imbalances, researchers often use survey weighting.

Weighting is a statistical technique in which datasets are manipulated through calculations in order to bring them more in line with the population being studied. The key difference between the initial sample composition and weighting is that weights are applied after data is collected, and allow researchers to correct for issues that occurred during data collection. For this reason, weighting is also known as post-stratification, as it takes place after the sample has been selected, as opposed to pre-stratification, which is used to balance a sample before data has been collected.

Researchers applying weights are most often weighting on demographic characteristics, such as age, gender, location, and education, but weighting can also account for the differences between those who partake or do not partake in research studies (known as self-selection bias). Weights can also minimize any effects the survey design or data collection mode may have on the sample makeup and resulting data.

In addition to weighting on common demographic variables, studies have found that weighting based on other variables such as internet usage and political affiliation can further reduce bias in some cases. If conducting a phone survey, for example, weights can be applied based on mobile versus landline phone users.

Survey Weighting Methods: Raking and Cell Weighting,

There are several ways in which the actual weighting is performed. Two of the most common include cell-based weighting and raking:

Cell-based Weighting

One of the simplest types of weighting, cell-based weighting can be used when you know the number of respondents your sample should have who are, for example, males age 15-24 or females age 25-34. If your desired sample included 100 males aged 15-24 and 80 females aged 25-34 but should have included 80 males aged 15-24 and 120 females aged 25-34, you can apply simple cell-based weights as illustrated to the left.

Raking or RIM Weighting 

Raking, also known as random iterative method (RIM) weighting or iterative proportional fitting, is a slightly more complex method that can be used when you are weighting to a number of variables, but may not know how the variables interlock; For example, if you need 100 females and 120 people aged 25-34, but do not know how many females aged 25-34 are required. With raking, a researcher would first balance the sample based on one variable, such as gender, and then on the next variable, such as age. If the adjustments for one variable affect another variable too much, then more adjustments are performed until a balanced sample is achieved.

Raking is one of the most common and accepted methods of weighting for public opinion surveys, as it allows for weighting based on multiple variables and aims to adjust each variable by as small an amount as possible. It can be performed quite quickly using a statistical software such as SPSS.

Other methods of weighting include matching, in which a researcher selects a set of cases that is representative of the population from another dataset and aims to match cases from the dataset being studied. Logistic regression modelling and propensity weighting are other types of weighting that are used to account for selection bias amongst a sample. For a more in-depth explanation of various weighting methods see this paper from Pew Research and this from the Journal of Official Statistics.

Pros and Cons of Weighting Data

As with any technique used to manipulate a dataset, there are both pros and cons of weighting, and several guidelines that should be kept in mind when weighting data.

Advantages of weighting data include:

  • Allows for a dataset to be corrected so that results more accurately represent the population being studied.
  • Diminishes the effects of challenges during data collection or inherent biases of the survey mode being used
  • Ensure the views of hard-to-reach demographic groups are still considered at an equal proportion to the population in the final data.

Disadvantages of weighting data are:

  • Can over-represent the views of one or several people who may not be an accurate reflection of their entire demographic group
  • Can inadvertently introduce additional biases into the dataset
  • Can make the findings more variable as it increases the standard deviation of answers (check)

In order to reduce the impacts of data weighting, it’s recommended to weight by as few variables as possible. As the number of weighting variables goes up, the greater the risk that the weighting of one variable will confuse or interact with the weighting of another variable. Also, when data must be weighted, try to minimize the sizes of the weights. A general rule of thumb is never to weight a respondent less than .5 (a 50% weighting) nor more than 2.0 (a 200% weighting).

Additional Information on Data Weighting

GeoPoll provides nationally representative data through a combination of a carefully selected sample frame, use of quotas to manage the demographic composition of those who respond to surveys, and application of weights where necessary. GeoPoll can use multiple weighting methods, including both cell-based and raking, based on the project specifications. To learn more about GeoPoll’s data collection and research process, please contact us here.

The post Weighting Survey Data: Methods and Advantages appeared first on GeoPoll.

]]>
Market Research Methods https://www.geopoll.com/blog/market-research-methods/ Tue, 28 Jul 2020 15:00:54 +0000 https://www-new.geopoll.com/?p=6809 Market research is an important tool for understanding both population needs and consumer audiences. It can lay the groundwork for advertising and […]

The post Market Research Methods appeared first on GeoPoll.

]]>
Market research is an important tool for understanding both population needs and consumer audiences. It can lay the groundwork for advertising and product launches, provide data and actionable insights that direct strategic decisions, and demonstrate the status of indicators such as food security or job stability. The best market research method depends on the types of questions and the target research population. Quantitative research is excellent for quantifying behaviors, opinions, and attitudes while qualitative research is ideal for understanding the ‘why’ behind it all. Research can even be multi-modal, meaning a project could start with qualitative interviews or focus groups with a smaller number of respondents and finish up with SMS or web surveys to a larger group. Below we outline some of the most common market research methodologies and how, even during COVID-19, it is still possible to conduct research effectively. 

Research Methodologies

Self-Administered Surveys 

A survey is a series of simple questions that build on each other and are designed in a specific order to explore one or more topics. Depending on the survey, questions and responses can be text or multimedia. Self-administered surveys are surveys that are completed by the respondent and are often sent to and completed by SMS, web link, or mobile application. 

Respondents can complete surveys via Short Message Service (SMS or text message) one question at a time. This method is ideal for some populations, such as those found in countries in sub-Saharan Africa or Latin America, because it does not require respondents to have internet connectivity. 

Surveys can also be internet-based via a web link, mobile web link or a mobile application. With mobile web links, respondents with internet-capable phones click on a link within an initial SMS message and then complete the survey in a basic web browser. Mobile web supports video/picture questions, and question formats such as matrices which are not supported in SMS surveys.

Respondents who own smartphones can complete surveys through a mobile application which, with the respondent’s consent, has additional capabilities for GPS location, passive data collection and picture taking. Mobile applications can also facilitate tasks such as retail audits or billboard monitoring. 

Interactive Voice Interviews (IVR) are a self-administered audio interview, in which respondents listen to audio pre-recordings and answer questions using their dialpad. This method is useful for reaching illiterate populations through voice calls, without needing to train call center interviewers, however response rates can be lower than when using CATI, a method outlined below.

Interviews through CATI, CAPI, or Pen and Paper  

Example of a GeoPoll call center

Similar to surveys, interviews are a series of questions that explore one or more topics. One major difference is that the interview methods discussed here are interviewer-administered, rather than self-administered. Depending on the targeted population and the amount of time needed for data collection, interviews can be done in person or over the phone. Interviewers must be trained, fluent in the respondent’s language of choice, and familiar with their cultural context.

Computer Assisted Telephone Interviewing (CATI), is done over the phone with the interviewer based in a country-specific call center. This methodology allows for interviewers with multiple language capabilities to easily speak with respondents across a large or hard-to-access region more quickly than is possible using face-to-face interviews. 

For in-person interviews, Computer Assisted Personal Interviewing (CAPI) facilitates face-to-face data collection in the field through a mobile application and removes the need for paper questionnaires or manual data collection. Pen and paper interviews are still used in some contexts but are inefficient and can lead to data input errors or interviewer error.

Observative Research

Observation is a qualitative methodology where researchers witness a respondent’s natural behavior in their usual environment. Depending on the goal, a researcher may engage with the situation or remain at a distance and only watch. The benefit of this methodology is that researchers can understand how a respondent actually acts, rather than what they self-report.

Observational research may be used as a precursor to a survey when researchers need more information about a specific question. Or, observation might be used if researchers are concerned that self-reported behaviors may differ from a person’s actions, even if this inaccuracy is unintentional. 

Focus Groups

A focus group is a small group of people (usually 6-8) who represent a larger group. In traditional focus groups,  respondents meet in one location with a researcher for up to two hours and discuss specific research topics. Similar to surveys or interviews, the researcher will lead respondents through a series of predetermined questions. This methodology allows for discussion and collaboration between respondents.

Digital focus groups can also be administered through either computer-based chats, often called Market Research Online Communities, or using mobile-based group chats, such as ones GeoPoll has facilitated with brands including Unilever. 

Big Data Analytics

Analysis of large amounts of data is a useful way to understand patterns and trends. Gartner defines big data as “data that contains greater variety arriving in increasing volumes and with ever-higher velocity.”  Big data can be valuable in identifying certain types of consumer insights. It can lead to robust decision-making around consumer needs or satisfaction and help predict future opportunities for innovation. However, the large amount of information is not infallible. Just as important is the interpretation and application of this data. While big data analysis tries to make sense of large amounts of information, market research methodologies like surveys and interviews can answer a specific research question. 

Market Research Methods During COVID-19

In-person research is one of the most traditional types of data collection and still remains popular today. However, the worldwide outbreak of coronavirus has made in-person research impossible, and researchers must find other ways to collect data that keep both themselves and their respondents safe. 

Using the aforementioned remote methodologies, which include SMS, mobile web link, CATI, and mobile-based focus groups,  data collection is still possible and safe during coronavirus. GeoPoll has experience transitioning face-to-face research to remote methodologies and has the existing infrastructure to support robust data collection. Our team are experts in remote data collection methodologies and can quickly transition an in-person study to a remote, mobile-based methodology. To speak to a member of our team about your project, please contact us today. For more information about GeoPoll’s research methodologies and conducting research throughout Africa, Asia, and Latin America, download our guide to research in emerging regions. 

The post Market Research Methods appeared first on GeoPoll.

]]>