Introduction
Social research utilizes two data analysis methods: quantitative and qualitative. The qualitative approach interprets textual data and observations, while the quantitative method analyzes numerical data using statistics. This paper will compare qualitative and quantitative data analyses based on two articles published in the Public Administration Review. One study, conducted by Cheng et al. (2022), utilized a quantitative data analysis to identify the relationship between park access and the density of park-supporting nonprofit organizations and the differential impact of nonprofits on different racial groups. Another article, written by Foley and Williamson (2019), used qualitative data analysis to study managers’ attitudes toward implicit biases and affirmative action. The author of this paper undertakes this comparison to determine the appropriate data analysis method for the dissertation topic, “The Impact of Executive Orders on the Implementation of Diversity, Equity, and Inclusion (DEI) Programing and Federal Agencies.” It is concluded that both quantitative and qualitative data analysis have their strengths and weaknesses and can sometimes be combined for achieving the most accurate and useful research results.
Differences between Quantitative and Qualitative Data Analysis
Using the two specified articles as examples, the first difference between quantitative and qualitative methods one can identify is the focus of the data analysis. The quantitative study by Cheng et al. (2022) aimed to analyze the relationship between the density of nonprofits and distributional equity in individuals’ access to public parks. In other words, the researchers used a large data set to discover facts about a particular social phenomenon – access to public parks. In contrast, the qualitative study by Foley and Williamson (2019) focused on exploring managers’ attitudes toward affirmative action, implicit bias, and merit as part of a larger research project into barriers and facilitators of gender equality. The researchers studied human experiences from participants’ perspectives, which was important to understand why policies aimed at increasing gender equality may not work as intended. Thus, a quantitative data analysis appears to be appropriate when there is a need to capture the state of affairs related to a particular social phenomenon. A qualitative method is more applicable to studies intended to identify reasons behind the given state of affairs.
Another difference between the two data analysis approaches lies in the techniques used to reach the research results. Cheng et al. (2022) performed a range of quantitative analyses to identify the mean and standard deviation in park access and the relationships between the dependent variable of park access and independent variables of nonprofit density and race-specific variables, such as income gaps. The quantitative study makes extensive use of statistical methods to reach conclusions. In contrast, Foley and Williamson (2019) used a qualitative content analysis method by audio-recording and transcribing 104 face-to-face and telephone interviews and coding them in NVivo. The coding was performed to identify common themes in interviewees’ responses. Hence, quantitative methods apply statistics to obtain research results, whereas qualitative approaches analyze textual data to discover repeated patterns.
Strengths and Weaknesses
While the two data analysis methods are different, each has its strengths and weaknesses. One advantage of quantitative methods is that it enables researchers to use large sample sizes, thus allowing for greater generalizability of results. For example, the study by Cheng et al. (2022) utilized a sample of 2,392 inner and suburban cities. Even though this sample size does not allow to generalize results to all US cities, it is large enough to produce highly generalizable findings. Another strength of quantitative data analysis is the high objectivity and accuracy of results. Cheng et al. (2022) used multiple datasets for their study and analyzed data using objective statistical methods, including Ordinary Least Squares and quantile regressions. Given the objectivity of the data and methods used, quantitative data analysis generates highly objective and accurate findings.
Quantitative approaches also have several weaknesses, one of which is the inability to measure human experiences. For example, Cheng et al. (2022) managed to capture the racial-ethnic equity in access to public parks. However, their study results are impersonal since they do not provide evidence on human attitudes and experiences affecting park access. This is because purely quantitative methods are not intended for measuring this type of data. Further, the quality of quantitative analysis results depends on the quality of the used datasets. For instance, Cheng et al. (2022) admitted that their data on nonprofit density could be biased upward because of the discrepancy between service areas and nonprofits’ office locations, so they made efforts to minimize measurement errors. Thus, when conducting quantitative research, scholars should choose their data carefully to avoid false representation.
With regards to measuring human experiences, what appears to be a weakness of quantitative research is a strength of qualitative methods. Qualitative data analysis is an effective way of exploring human attitudes, beliefs, and behaviors. It analyzes participants’ extended responses to identify common themes and explains why people behave the way they do and how they feel about it. For example, by using qualitative analysis, Foley and Williamson (2019) explored managers’ attitudes toward affirmative action and found that, although managers recognized implicit bias, they viewed affirmative action as a violation of merit. Thus, qualitative data analysis allows for gaining a deep understanding of reasons for certain social phenomena, such as why some policies do not produce the expected results. Qualitative methods can strengthen quantitative studies by explaining the facts obtained through statistical analyses.
Qualitative data analysis is not devoid of weaknesses as well. Qualitative research produces a large amount of textual and observational data, collecting and analyzing which takes much time and effort. For this reason, researchers using these approaches have to use smaller sample sizes, meaning that the results of their studies are less generalizable. For instance, the sample size in Foley and Williamson’s (2019) study was 104 managers, which is a relatively large sample for qualitative research. Due to the researchers’ intent to collect and analyze as much data as possible, the researchers did not cover all topics with all participants. Thus, in qualitative research, scholars should always balance the depth of data and the sample size.
Assessing Data Analysis Methods Against Course Readings
The specific data analysis methods used in both studies are reflected in course readings. For example, Cheng et al. (2022) conducted quantile regressions to identify distributional impacts of nonprofits on different racial groups’ benefits received from nonprofit service providers. According to Khandker et al. (2009), quantile regression approaches are one way to assess the distributional effects of program interventions. Assessing distributional impacts is important because the average results often do not reflect which parts of the population benefited most from the intervention (Khandker et al., 2009). Further, Foley and Williamson (2019) used axial coding to capture themes in the collected data. Axial coding is described by Babbie (2021) as a reanalysis of the results of open coding with the purpose of discovering important general concepts. It is a second step in the grounded theory method, which identifies links between ideas in the collected data.
Conclusion
To sum up, quantitative and qualitative data analyses are different in their focus and techniques used. The quantitative analysis captures the facts about specific social phenomena, while qualitative analysis can explain these facts based on human attitudes and experiences. To get the most comprehensive research results, scholars may combine these methods to have both objective numerical data and in-depth explanations of why these findings were obtained.
References
Babbie, E. (2021). The practice of social research (15th ed.). Cengage Learning.
Cheng, Y., Yang, L., & Deng, S. (2022). Nonprofit density and distributional equity in public service provision: Exploring racial/ethnic disparities in public park access across US cities. Public Administration Review. Advance online publication.
Foley, M., & Williamson, S. (2019). Managerial perspectives on implicit bias, affirmative action, and merit. Public Administration Review, 79(1), 35-45.
Khandker, S. R., Koolwal, G. B., & Samad, H. A. (2009). Handbook on impact evaluation: Quantitative methods and practices. The World Bank.