Afregarde Research is a social entrepreneurial team specialising in supporting evidence-based practices across political, social, business, economic and scientific disciplines. We support the generation of objective knowledge that can be used in improving the quality of decision-making on problems and challenges existing in Africa. We believe in the power of qualitative, quantitative and mixed research methodologies to provide applied research outcomes that minimise the use of unsubstantiated popular beliefs, trial and error, guesswork and non-factual directive approaches in decision-making. Through the collection, analysis, interpretation and reporting of statistical, mathematical, econometric and qualitative data using known best practices and systems, we enhance the private and public sector entities’ probability of implementing efficient, effective and sustainable strategies, policies, programs and actions.

In addition to applied research, we provide writing, editing and publication services. We believe that research output has a greater impact if and when it is professionally and skilfully published for the targeted audience. We offer 360-degree assistance and support to NPOs, academia, business and governments – locally and regionally.

There are those who seek knowledge in order to serve; that is Love.”

― Bernard of Clairvaux

Data analysis support systems

We use globally-reputed statistical and analytical packages for conducting qualitative and quantitative data analysis. These include SPSS, SPSS-Amos, XLStat and SAS for qualitative data analysis and NVivo and Atlas. Ti for qualitative data analysis. We have our own custom package branded AfreQUAL which has proven to be a system to reckon with in voluminous qualitative data analysis.

Qualitative Data Analysis

Afregarde Research conducts Qualitative Data Analysis in all research disciplines. Qualitative research designs have several benefits for the research community. These benefits however require skillful methodology as they are also come with a host of challenges that can either derail or discredit the whole qualitative research effort. The reasons why researchers do qualitative research are:

  • It is effective in bringing out emotions, feelings and deeper perspectives from research subjects
  • It enables the collection on rich and undisturbed data through natural and unlimited response processes
  • It is important when dealing with subject matter that is generally new or that is not well known or defined
  • Sometimes it is the only possible research design that will apply to a given sample. e.g. when small children cannot be expected to effectively complete close-ended questionnaires

Qualitative data analysis presents various challenges for researchers mainly:

  • The need to process unstructured data into structured analyzable information
  • Dealing with large volumes of data
  • Designing and documenting an effective coding system
  • Coming up with distinct yet logical and related themes and topics that comprehensively bring out the general perceptions, views, opinions and emotions of research samples
  • Expressing emotions and feelings into objective, meaningful views
  • The need to deal with data in various formats including scanned questionnaires, audio tapes, video tapes and observation notes

Several common mistakes or weaknesses that the above challenges bring include:

  • Leaving out or dropping important themes that are part of the findings
  • Overemphasizing on a particular view as a result of the researcher’s subjective views or limited understanding of related themes
  • Under-presenting particular themes and content
  • Poor presentation structure and failure to categorise data into logical and meaningful units

Systems and processes

We use various logical approaches to ensure that findings from qualitative research processes are duly analysed, logically group and comprehensively presented. We rely on various generic data analysis tools such as NVivo and Atlas Ti as well as our own in-house systems.

  • Grounded Theory
  • Thematic Content Analysis
  • Discourse Analysis
  • Narrative Analysis
  • Hermeneutical Analysis
  • Event Analysis
  • Matrix and Logical Analysis
  • Metaphorical Analysis
  • And many more…

Often a single qualitative data analysis process may require the combination of various approaches presented above although there is usually an overarching dominant analysis method.

What is required for a qualitative data analysis

To perform a qualitative data analysis, Afregarde Research requires the following:

  • Unprocessed data collection media:
  • Interview transcripts
  • Audio tapes
  • Video clips
  • Observation notes
  • Open-ended questionnaires
  • Focus group minutes

The analysis team will code and analyse the provided media with the intention of ensuring that the objectives of the study are clearly brought out.

Quantitative Data Analysis

Quantitative Data Analysis relies of numerical effects to present, analyse and report on data. It is generally commoner than Qualitative Data Analysis and is used to meet a wide range range of research objectives in the business, economic, social sciences, humanities, legal  fields and natural sciences. Common advantages of Quantitative Data Analysis are:

  • It is comparatively easier to analyse large volumes of data using quantitative methods than qualitative methods
  • Results from a study can be inferred to a different population group and setting
  • Reliability and validity of results can be controlled thereby improving the quality of the results in terms of representing the real views of the study sample or population
  • It supports representativeness of views and therefore applies well in situations where public opinions and perceptions rather than individual views are important

Types of Quantitative Studies

Quantitative research can be carried out through a variety of studies. These include:

  • Cross-sectional studies
  • Before and after studies
  • Longitudinal studies
  • Experimental studies
  • Semi-experimental studies
  • Causal studies
  • Comparative studies
  • Case studies
  • Feasibility studies
  • Impact studies
  • Opinion studies
  • Effectiveness studies
  • Baseline studies
  • And many others

These studies are by no means mutually exclusive and it is also not uncommon for different writers to classify or define them differently. The bottom line is that they guide researchers in choosing the appropriate type of study that supports the given set of objectives.

Afregarde Research provide data analysis support for Structural Equation Modelling. Structural Equation Modelling (SEM) is an advanced form of quantitative data analysis that uses statistical models to test research hypothesis and to prove or quantify the nature of relationship between or among variables. Structural Equation Modelling (SEM) is important when dealing with the following data analysis situations:

  • Large number of variables are involved in affecting the phenomenon under study such that the use of ordinary statistical means would not effectively capture this multiplicity.
  • Complex relationships that cannot be effectively understood through bivariate statistical methods (methods that analyse the relationship between two variables or two sets of variables at a time) and require a multivariate approach (analysing more than two variables simultaneously).
  • Structural Equation Modelling is also of importance in cases where a researcher is dealing with or suspects the effects of unobserved variables (latent variables) on the analysis outcome. SEM models take cognisance of and record the presents and strengths of latent variables that are otherwise unaccounted for when using ordinary statistical analysis techniques.
  • SEM is naturally applicable when one’s study objectives, research questions or hypotheses involve the testing of theoretical models or the comparison of such models. In such situations, researchers are compelled by the nature of the study to use SEM for analysis data.

SEM is becoming commoner due to the continued evolution of SEM software packages such as SPSS Amos, LISREL and SAS.  This evolution has resulted in more user-friendly systems that are more widely available than in the past. Our SEM services include:

  • Designing models that meet the given hypotheses
  • Testing models for goodness-of-fit
  • Generating theories from tested models and testing hypotheses
  • Providing detailed reports describing the model

Data Collection Services

Afregarde Research offers data collection services for various study disciplines. This includes the deployment of enumerators to physically collect data in the field or the use of electronic means to reach out to the targeted sample or population.

Data collection methods used include:

  • Interviews
  • Questionnaires
  • Focus groups
  • Observation
  • Experiments
  • Case studies
  • Secondary source studies

The method of choice depends on the clients objectives and the nature of the data to be collected. Professional enumerators are used to collect and to capture the collected data for further analysis.

Data Capturing and Transcription

Afregarde Research offers data capturing services for research efforts of all sizes. This include: Capturing and coding of qualitative data Capturing and coding of quantitative data.Data capturing processes also include transcribing services where audiographic and videographic data is transformed into written documents for further analysis.

Please wait while flipbook is loading. For more related info, FAQs and issues please refer to DearFlip WordPress Flipbook Plugin Help documentation.