Research Methodology and Method

Introduction

The numerous processes, techniques, stages, and algorithms utilized in research are research methodologies. The phrase “research methods” refers to all methods employed by an investigator during a research project (Christofi et al., 2020, p. 12).  They are primarily scientific, planned, and value-neutral in nature. A few examples are theoretical methods, observations, experimental investigations, numerical techniques, and statistical methodologies. Methods of research assist in collecting samples and data and in determining a solution to problems. Business and management research techniques, for instance, need justifications based on gathered data, assessments, and observations rather than on pure logic. They acknowledge only those hypotheses that are experimentally verifiable. In this light, it is essential to analyze different research methodologies and methods.

Research Paradigms

When it comes to research procedures, a research paradigm refers to the practices, norms, and ideas held among researchers about how different problems should be viewed and handled. Scientists’ responses to three basic inquiries: ontological, epistemological, and methodological issues, according to Bell et al. (2018, p. 13), may be characterized by research paradigms. As a result, in business and management, research paradigms are regarded as distinct research methodologies on various concepts such as truthfulness of research, information satisfactoriness in the study, quality as a factor in research, and the ways to gather information. The positivist, interpretive, realism, and pragmatism paradigms are the four main research paradigms in management research. When it comes to social sciences research methodologies, positivism and interpretivism are the two most important approaches to consider because of the methodological differences between quantitative and qualitative research methods, as stated by Bell et al. (2018, p. 49). Positivists prefer quantitative research methods, while interpretivists prefer qualitative approaches that are more humanistic. Groenland and Dana (2020, p.163) said that positivists prefer quantitative methods such as sociological studies. Structured surveys and official insights have high reliability and representativeness and are thus more reliable than qualitative techniques. According to Park et al. (2020, p. 694), the positivist paradigm includes derivative concepts, including realism, which is described as a study methodology aimed toward discovering reality using all available techniques and bringing the humanistic element of business and management research into account. The researcher pays careful attention to the data collected by other researchers, as well as to societal problems and expansive global views while doing their study.

The positivist stress the necessity for quantitative studies, such as samples and significant studies, to understand the whole of the population and to identify social trends, including the link between the margins of profit and the cost of production (Berryman, 2019, p. 271). A qualitative approach to social study would be much more interpretivist, relying on techniques such as unstructured meetings and member perception to accomplish its goals. Interpretivists criticize positivism because a significant portion of the insights it depends on are the product of social construction. To put it another way, interpretivists argue that to grasp human behaviour, we must first achieve Verstehen, which is a humanistic knowledge of social issues (Berryman, 2019, p. 276). Pragmatism is yet another essential management research paradigm. The constructivist theory categorizes it with the ideographic approach to knowledge, observation as the collection of knowledge, and a high demand for complex statistical analysis in information technology, which is essential for mixed methods research. Another essential management research methodology is the scientific method.

Another research paradigm is the realism philosophy of social research, which has lately gained popularity in business research, particularly in the analysis of explaining case studies and other fields. As per Rahi (2017, p. 5), the research philosophy of a realist derives from the notion that reality is independent of subjective views and ideas based on the human mind. Reality seekers think that scientific approaches to creating knowledge are the most suitable method to research in the social sciences, and they are correct. However, as Levitt and colleagues (2021, p. 357) noted, realism, either critical or direct, emphasizes the raw reality and intimate experiences of study participants and their families. Direct realism, at its core, depicts things as they are and shows the world through the eyes and ears of a human being.

In contrast, critical realism asserts that individuals have firsthand experience of their emotions and perceptions of truth compared to subjective developing understanding. For instance, Gemignani (2017, p. 185) assert that realism opposes the idea that humans may have an accurate, impartial understanding of the world. Rather than that, it recognizes the potential of alternate truths in the context of a hypothetical situation or hypothetical circumstance (Newman, 2020, p. 450, Martin, 2020, p. 155). Realists are concerned with the truth and beliefs that exist in a given context, and they approach social research with the idea of examining the raw facts and realities that exist in that environment.

The Distinction between Qualitative and Quantitative Study, and the Situations in Which Each Kind of Study is Suitable

Qualitative and quantitative research are two of the most often used research techniques in management. According to Apuke (2017, p. 8), the quantitative method is research for studying a population by gathering and examining numerical data. By contrast, qualitative research is a technique for collecting, verifying, and analyzing data instead of quantitative methodologies, as defined by Rose and Johnson (2020, p. 433). The quantitative study is most closely linked with the positivist viewpoint and frequently entails population studies and the translation of knowledge into statistical information to facilitate data analysis. To do research, scientists must develop at least one hypothesis, which includes questions for the study and predictions about possible relationships between variables. To determine the responses to these queries, the investigator would have access to a variety of equipment and resources, as well as a well-defined research plan. According to Salloum et al. (2018, p. 397), data is collected using various techniques that are all part of a strict methodology and then organized for statistical analysis. It has only recently become necessary to do data analysis utilizing sophisticated statistical analysis techniques. The study’s findings provide the researchers with the authority to determine the degree to which there is a connection between at least two aspects. Additionally, the statistical study allows investigators to deduce complex causal connections and quantify the effect of one factor on the other through testing.

As per Sahin and Mete (2021, p.28), qualitative study is primarily descriptive in nature and is involved with non-statistical information. It is used to get an understanding of underlying motives, hypotheses, and sources of inspiration. It provides tidbits of information about the problem of aids in developing ideas or hypotheses for a future quantitative study. Methods of quantitative data gathering may be classified as unstructured or semi-organized, depending on the situation (Alharahsheh and Pius, 2020). Focus groups, individual interviews, and observations are just a few of the fundamental methods used. The sample size is often small, and responders are selected based on their ability to meet certain criteria. According to Bloomfield and Fisher (2019, p. 27), quantitative study uses measurable information to create realities and discover study designs in the field of science. The procedures used for quantitative data gathering are much more structured than those used for qualitative data collection. Qualitative study is often linked with the social constructivist perspective, which primarily stresses the world’s reality as a result of human social evolution. It is intertwined with the process of documenting, researching, and attempting to discover the more fundamental significance and meaning of human behaviour and experience, all of which are related. Scientists are often more concerned with developing a detailed knowledge of an individual’s experience than collecting information generalized to more significant populations. (Mohajan, 2018, p. 23).

In most cases, the inductive technique will be used by qualitative researchers, which means that they will develop a hypothesis or seek a statistically significant sample based on the information they have collected. This entails a shift from the particular to the general, sometimes described as a “hit a base up” strategy. Nevertheless, the majority of research efforts include an element of a deductive argument. Qualitative researchers do not prioritize the details of their study in accordance with pre-determined hypotheses, as quantitative researchers do. The qualitative study employs a deliberate data collection and analysis strategy but with a more considerable degree of freedom than quantitative study. Member perception, top to bottom meetings, and centre populations are examples of how information is collected text-based based on perception and relationship with the members. Neither the numerical data nor the statistical analysis of the quantitative data is performed on the data. It has been suggested by Castleberry and Nolen (2018) that data gathering may be completed in many stages rather than all at once. The researchers may even make changes to the interaction in the middle of it, deciding to address more problems or removing questions that are not appropriate depending on what they learn throughout the cycle.

Different Data-Collection Methodologies

For companies, institutions, and personal usage as well, data gathering is critical. Data is among the most important resources available to everybody in the technological era. When utilized correctly, the appropriate data can push a brand ahead by assisting a person or organization in making the best choices possible in areas like selecting a product category, determining the best promotional mix, making economic choices, and much more (Bornovalova et al., 2020, P. 27).  When utilized improperly, it may seem as though an individual’s decisions are constantly falling short. How can one be confident that they have all of the knowledge they need to make critical decisions? By using good data gathering and analysis techniques. However, in a commercial and management context, the data gathering process and procedures are much more formal, and the results seem to be better. This is partly attributable to a clear distinction between the many kinds of data that may be gathered. The following are among the data collection methods used in quantitative and qualitative management and business research:

Close Ended Question Surveys

Closed-ended survey questions are a kind of primary data gathering that is quantitative. It is the practice of posing a set of questions with a predetermined set of possible responses. Bear in mind that closed-ended and open-ended queries may be included inside the same assessment (Schmidt et al., 2020, p. 32). Nonetheless, this implies that a researcher may gather both qualitative and quantitative data from the same responder. An NPS assessment is an excellent illustration of this. The first question utilizes a grading scale, while the second one is an open-ended inquiry that aims to explain the response. Questions using the Likert scale are also included in this subcategory. They are excellent for quantifying things like frequency or sensation.

Open-ended Surveys and Online Analytics Tools

Open-ended questionnaires are excellent for eliciting information on the motives, traits, or sentiments behind a perspective. A researcher can produce data that closed-ended inquiries cannot. While open-ended questionnaires may provide a lot of information, caution should be exercised. When a researcher is faced with an excessive number of open-ended questions or those that are too difficult, exhaustion sets in, this raises the chance of responders abandoning the survey entirely, leaving researchers with insufficient data.

On the other hand, researchers have access to a plethora of analytics tools for tracking and understanding user activity in the digital era. If a researcher has a website or an app, they may collect an abundance of data. For instance, utilizing Google Analytics, one may determine the most popular sites, the number of visitors, the route visitors follow before converting, and more. With this information, a person may optimize many parts of the sales funnel and continuously enhance outcomes.

Interviews

Interviews are a time-tested method for collecting qualitative information and offer several benefits over other methods. Interviews may occur in person, over the phone using a dependable cloud system, or through video calls. The in-person approach is optimal since it allows for reading facial expressions and body language and their correlation to the answers provided. Three distinct kinds of interviews exist. First, a systematic interview may be regarded as a spoken questionnaire. Thus, there is little to no divergence from the first set of questions. Second, a semi-structured interview follows a basic framework but allows the interviewer to go into various topics depending on the answers. Finally, while an unstructured interview has a defined goal, the investigator has discretion over the kind of questions to ask, what to investigate, and what to leave out. This provides the most significant degree of versatility.

Data Analysis Methods Utilized in Quantitative and Qualitative Business Research

Once data has been gathered, the next stage in research is to extract knowledge from it. For instance, if a clothing company wishes to ascertain the current trends amongst women, the company will first contact women and ask pertinent questions. After gathering this data, the firm will examine it for directions. For instance, it may find that the majority of women want a greater variety of jeans. As such, data analysis is the process through which researchers transform a deluge of data into actionable information (Beheshti et al., 2020. P. 26). There are numerous data analysis techniques available, based on the kind of investigation. The following are a few techniques for analyzing qualitative and quantitative data.

Quantitative Data Analysis Methods

Inferential statistics and descriptive statistics are the two most often utilized quantitative data analysis techniques. Having stated that, descriptive analysis is often used as the initial stage of analysis. It assists researchers in summarizing data and identifying trends. Descriptive statistics, on the other hand, give absolute figures. They never, however, articulate the logic or reasoning underlying such statistics. Therefore, before using descriptive statistics, it is critical to consider which kind is most appropriate for the research topic and the information. For instance, a percentage is an effective method to depict the respondents’ gender distribution. On the other hand, descriptive statistics are most advantageous when the study is restricted to small sample size and does not need generalization to a broader population. For instance, if comparing the vaccination rate of children in two separate communities, descriptive statistics will suffice.

Analyzing Qualitative Data

The qualitative approach differs from quantitative analysis in many ways, most notably since qualitative data is composed of observations, words, pictures, and symbols. Because it is virtually difficult to derive absolute meaning from such data, it is primarily utilized for the investigative study. In addition, whereas quantitative research clearly distinguishes the data gathering and analysis stages, qualitative analysis often starts with analysis as the information is recorded immediately.

However, many techniques for qualitative analysis are present. Narrative analysis and content analysis are two of the most often utilized data analysis techniques. Having stated that, content analysis is among the most frequently used techniques for analyzing qualitative information. It is used to evaluate data that has been recorded in the form of words, media, and physical objects. When to utilize this technique is determined by the study questions. Typically, content analysis is employed to examine interviewee answers. On the other hand, narrative analysis is a technique used to evaluate material from various sources, including respondent interviews, field observations, and surveys. It emphasizes eliciting responses to survey questions via the use of personal narratives and experiences.

Issues of validity and reliability

The reliability and validity of the data and the results of data analysis are used to evaluate the overall quality of a research project. The degree to which a notion can be accurately quantified in quantitative research is the validity of the concept. For example, a study designed to examine happiness instead of assessing well-being would not be regarded as legitimate research in this situation. The extent to which a metric or idea is appropriately evaluated in a research study is described as validity, according Mohajan (2017, p. 59). In a nutshell, it’s the technique by which a survey or piece of research assesses how well it evaluates what it is supposed to examine. There are two kinds of Authenticity Measurements in a quantitative assessment. Inside validity measures how much information about causal relationships can be gleaned from a study plan based on its design. Business management research is focused on evaluating internal validity. It does so via the use of three methods: criterion-related validity, construct validity, construct validity, and content validity, to address the objectives underlying the findings of the study.

In contrast, external validity is the level to which the after-effects of analysis may be generalized to other populations, locations, or situations; it is often used in laboratory research. The second criterion for quality in quantitative research is unshakable quality, which may be defined as the exactness of an instrument in the study. In accordance with Hopkins (2017, p. 21), reliability is defined as the degree to which a research instrument consistently produces comparable results when used in similar circumstances on identical occurrences. Thus, the consistency of the measurements or the amount by which a device measures the equivalent with each use under the same circumstances is essential in research. Lechien et al. (2020, p. 313) said that dependability is often evaluated by examining the relationship between different test results or instruments, known as inner consistency. Typically, these correlations are evaluated using Cronbach’s alpha coefficient. This statistical analysis splits all of the outcomes in half and looks for connections among the two different sets of study information.

As per Chan and Idris (2017, p. 400), validity and reliability are concepts used to evaluate the nature of exploratory research. They demonstrate the accuracy with which a method, technique, or test guesses something. The consistency of a measure is what reliability is all about, and the accuracy of a standard is what validity is all about. When designing your exploration configuration, organizing your methods, and evaluating your results, it is critical to keep unchanging quality and validity in mind. This is especially true in a quantitative investigation. Face validity according to Chan and Idris (2017, p. 406), is the degree to which an estimate method seems on its face to be able to measure the development of interest. When doing a quality assessment, content validity should be considered. Content validity is the extent to which a measure covers the construct of interest. Aside from that, the very nature of investigation necessitates the estimate of criterion validity. Guideline validity is the degree to which people’s results on a measure correlate with various models that one would expect to be linked to. Because the standards should be obtained from a variety of research, the validity and reliability of a measure cannot be established in a single study, as previously stated.

Sampling Methods and Techniques

Probabilistic and non-probabilistic sampling methods are used in management science research to choose a sample from a population for investigation. A component of probability sampling is random determination, which enables researchers to obtain a representative sample of the whole population. The second kind of sampling method is non-probability sampling. It entails non-random selections depending on variables such as convenience and other factors, enabling one to collect information more efficiently than with a random sample. When doing quantitative research, various sampling methods may be used to enroll participants in the study. An uncomplicated random sample is one in which each person from the population has an equal chance of being selected. According to Sharma (2017, p. 749), a sample frame should include the whole population of the study population. Systematic sampling is similar to a simple random sample in that it is easier to direct, but it is also more time-consuming for the researchers to implement. Even though each person from the community is identified by a unique number, rather than selecting individuals at random, people are chosen at regular intervals. Furthermore, sampling design is used by the researchers, which entails segmenting the population into subgroups which may vary significantly (Engl et al., 2019, p. 3). For example, one must segment the population into subpopulations centered on important trademarks such as sexual orientation and age to use the quota sampling method.

When recruiting participants for qualitative research, a variety of sampling techniques are used to gather information. Convenient sampling and purposive sample are very well sampling techniques because they are the most adaptable across almost all qualitative research designs and are thus the most often used (Andrade, 2021, p. 88). Non-probabilistic sampling methods are often used in qualitative and exploratory research, and they have several advantages. A typical sampling method used in qualitative research is the inclusion criterion, which defines the individuals who will be generally accessible to the researcher once they have been selected. Several researchers, including Akkaya et al. (2021, p. 13), have said that convenience sampling is perhaps the most widely used method in research today, owing to the reduced costs and simplicity of data collecting that it provides. Subjects are selected for convenience sampling based on their availability, which is beneficial to the researcher Saunders et al. (2015, p. 102) said that convenience sampling should be used in exploratory study when the investigator obtains a fair amount of qualitative data from the participants. For the most part, a non-probabilistic approach is used during essential research efforts to get a broad picture of the results without incurring the cost or time required to select a random sample.

According to Saunders et al. (2015, p. 21), conventional sampling, which economic researchers often use, maybe more effectively using qualitative research. Essentially, researchers are assigned a share of participants of a certain kind to recruit to complete their study. For example, a researcher may be instructed to perform a market study by choosing 50 married males and 50 single men to speak with them about their preferences for online shopping. In the majority of instances, the sample chosen would represent the characteristics of the sample population. Purposive sampling, also known as judgment sampling, is another essential sampling method in qualitative research. It entails the investigator using their ability to pick a sample that is usually beneficial to the reasons for the study, rather than randomly selecting a selection (Etikan et al., 2016, p. 4). For example, if the researcher wants to gather itemized information on a specific marvel rather than making quantifiable deductions, or if the data is large and well-defined, the researcher will often use the sampling technique in qualitative research. A good purposive sample should have well-defined inclusion and exclusion criteria, as well as a justification for their inclusion. Sampling methods for qualitative and quantitative research are based on concerns recognized by the investigator and various other variables including resources, design of the study, time, and participants’ knowledge of the subject matter.