4 Data Analysis and Interpret the Findings

Now, turn your raw data into meaningful insights. How? Compile and analyze your data, talk about what you have found and what it means, tie everything back to your research questions, and don’t forget to acknowledge the limitations and implications for future research.

Recall that we can conduct research in many different ways to answer the research question. Thus, the subsequent data analysis varied depending on your research design, the type of data collected, and your research objectives. Suppose you are collecting qualitative data (words, graphics, recording, etc.) to investigate subjective experiences, perceptions, and behaviors; proceed with qualitative analysis such as thematic analysis, content analysis, or grounded theory. If quantitative data (counting, measuring, rating, etc.) is the type of data you collected, you can use descriptive and inferential statistics based on your research design and objectives. Descriptive statistics summarize and describe your data whereas inferential statistics use your sample data to infer or draw conclusions on a larger population.

Qualitative Data Analysis

Qualitative data analysis focuses on non-numerical data such as text, images, or audio recordings. Qualitative analysis aims to uncover patterns, themes, and meanings within the data to develop rich descriptions and understandings of the research topic. Rather than relying on statistical tests, it interprets and makes sense of the data through techniques such as coding ^[1]. Box 4.1 lists a few examples of approaches and methods used in qualitative data analysis.

Check out the video to learn about qualitative data analysis [11 min, 17 sec]

^{“Why use CAQDAS for Qualitative Data Analysis?” by Amanda ‘Mandy’ Swygart-Hobaugh is licensed under CC BY 4.0}

Descriptive Statistics

Descriptive statistics summarize and describe data. It helps us to understand the main characteristics of the data, identify patterns, detect outliers, and make data-driven decisions. Descriptive statistics can be categorized into three types:

• measures of central tendency (e.g. mean, median, and mode), which describe the center of a dataset,
• measures of dispersion (e.g. standard deviation and range), which indicate how dispersed the values are in a dataset,
• measures of shape (e.g. kurtosis, and skewness), which provide information about the distribution’s shape or symmetry.

Descriptive statistics often utilize graphical tools like bar charts, box plots, histograms, and scatter plots to illustrate the data. Tables such as frequency tables can assist us in understanding how data is distributed. BOX 4.2 illustrates a scenario on how descriptive statistic was applied in a descriptive research.

Check out the video to learn how to generate descriptive statistics in Excel [3 mins, 16 sec]

^{“Basic Statistical Measures in Excel” by Open Learning is licensed under CC BY 4.0}

Inferential Statistics

Inferential statistics are used to make inferences and draw conclusions about a population based on a sample of data. These techniques include hypothesis testing, confidence intervals, and regression analysis. Inferential statistics help researchers determine if the observed patterns in the sample are likely to be representative of the larger population. It allows researchers to make informed decisions, generalize findings to larger populations, test hypotheses, and draw meaningful conclusions based on sample data (see BOX 4.3).

Check out this video to learn how to run an independent t-test in SPSS [1 min, 39 sec]

^{“Run an independent t-test in SPSS” by BrunelASK is licensed under CC BY 4.0}

Check out this video to learn how to interpret SPSS output for an independent t-test [4 mins, 16 sec]

^{“Interpret SPSS output for an independent t-test” by BrunelASK is licensed under CC BY 4.0}

Selecting the best data analysis techniques requires careful consideration of the research problem, the type of data collected, and the specific goals and objectives of your study. Researchers often employ a combination of statistical techniques to acquire a thorough grasp of their data and draw key conclusions. There are a variety of software tools and programming languages available to help with your data analysis, ranging from user-friendly interfaces like Microsoft Excel, SPSS ^[2], and PAST to R ^[3] or Python, which demand certain programming skills. Qualitative researchers may also organize, classify, and analyze vast volumes of qualitative data with tools like NVivo ^[4] and Atlasti ^[5]. Make sure you are conversant with at least one type of statistical or analytical tool for your study.

After you have finished gathering and analyzing data, it is common to feel overwhelmed by the amount of information, and making sense of it and extracting genuine knowledge may appear unattainable. Yet, the data-to-insight path, which entails extracting meaning from information, is critical in research because by connecting raw data to meaningful insights, it can help with the interpretation and decision-making. Critical thinking, analysis, and information synthesis are required to get a cohesive and meaningful grasp of your research findings. You must be able to distinguish between useful and insignificant data, identify patterns and relationships, and extract ideas. All of which will lead to a better understanding of your research and answering your research questions.

First thing first, before you interpret your findings, it is important to revisit your research questions, hypothesis, and objectives. Afterall, the purpose of a research is to answer the research question. Thus, establish a clear connection between the findings and the original purpose of the research is essential. The interpretation should address the specific goals of the study by assessing how the results align with them. Then, a few key elements should be include when you interpret your findings, which are contextualizing the findings, seeking explanations from various perspectives, evaluating methodological limitations, assessing implications and significance, and identifying future research directions. Let us explore each key element one by one.

Contextualizing the Findings

The most common practice of interpreting your research findings is to contextualize them. Simply put, compare your findings to existing literature and past research in the field to determine whether they are similar, different, or whether there are any gaps between your results and prior study. This allows you to determine whether your findings support or challenge current theories, models, or explanations. This contextualization helps to place your findings within the larger knowledge base and demonstrate how they contribute to or build on current knowledge in the field of study.

Seek Explanations and Causal Inferences

Regardless of whether your findings are consistent or contradictory with previous research, explain the apparent patterns found in the data. It involves looking into the underlying mechanisms or processes that may explain the findings. You can explore several plausible interpretations or factors that might influence the observed results to propose the most possible explanations or causal linkages. The most important thing is that you must discuss the feasibility of these interpretations critically based on current research and knowledge. By delving into the mechanisms, you can gain a better understanding of why particular outcomes occurred, resulting in a more robust interpretation of the findings.

Assess the Implications and Significance

When interpreting your findings, you should assess the implications and significance of the findings within your research context. Evaluate whether the research findings have theoretical, practical, stakeholder, or policy implications. For example, you may highlight how your discoveries expand knowledge and add to existing theories or models in the related discipline. If your findings have practical implications, explain how they might be utilized in real-world settings or decision-making processes. Highlight stakeholders or important domains that may be impacted by your findings, whether positively or negatively. Finally, consider whether your findings are consistent with any current related policies and whether changes to policies or mitigation are warranted.

Acknowledge the Limitations

No research is flawless. You should reflect on the methodological limitations of your study and how they may influence the outcomes to ensure a realistic interpretation. Limitations to consider include sample size, data collection methods, tools and equipment used, or any other potential biases. It is also advisable to assess the generalizability of the results by determining if they can be applied to different populations, contexts, or locations. For example, if your study was conducted in a specific place, at a specific time, or with a specific group, you should highlight the limitations and potential differences that may exist when applying the findings to other circumstances. Lastly, suggestions for future research that address these limitations should be provided.

Identify Future Research Directions

Finally, identify areas for further research based on your findings. This step involves discussing any unanswered questions, unresolved issues, or emerging areas of interest that arise from the study. By suggesting potential avenues for future research, you can contribute to the ongoing development of knowledge in your field and encourage further exploration of the topic.

Interpreting research findings effectively requires a systematic and comprehensive approach that considers various aspects of the study. Simply put, you interpret your results by looking at the key findings of your research, and discussing how or why they are the way they are, in terms of your research questions or hypotheses. Tie them back to previous studies and literature by discussing if the results fit in with previous research or if the results are unexpected. Provide a reasonable interpretation of why they may have appeared.