Many organizations are in the process of integrating technological developments in their management practices and systems. In order to enhance quality in their services and decision making, these business organizations use statistical research methods in collecting data. However, the choice of the sample size for such research plays a significant role in drawing conclusions from the study. This paper seeks to address the effects that are associated with the use of small sample size in data collection during a research study. The report used interviews as a method of data collection and further employed qualitative research in analyzing the data collected. NVivo software was used to further sort and analyze data in MS word software.
Keywords: Sample size, data, qualitative research, big data, and big data analytics.
The innovative advancements that have graced the contemporary world have led to the development of an age of information for different investigative research in various extents of the economy. For example, innovation has been utilized to create information to evaluate the market estimation of an organization’s item, the level of rivalry or potentially the significance of corporate social obligation to business associations (Wamba et l., 2017, P. 357). Information is deemed as a significant asset in the present world. The past few years have seen disruptive innovation presenting the big data (BD) idea, which has been utilized on a basic level, recognize the old organized and known information from the present time information.
BD is on a very basic level a tremendous measure of various information concepts that can be utilized to help various distinctive classes of choices in firms. BD can be created both internally and externally by business organizations. It is worth noting that business organizations appreciate the value of BD in advancing sound authoritative administration and basic decision-making processes. As indicated by Aras and Crowther (2013), firms need to form feasible practices that are custom-fitted towards incorporating BD concepts in their management framework. This will help the business organization to improve the requirement for advancing quality decision making processes described by shrewd leadership. Notably, firms that focus on the utilization of BD in their decision-making process are likely to maintain a competitive advantage in the market trends.
Statement of Purpose
The research article mainly focuses on the Telecom companies in the Jordanian economy. The sample size used for the research was minimal and could not be applied to other industries in the economy. Notably, there are only three established Telecom industries in Jordan and thus the research should have been extended to other industries as well. This paper, therefore, seeks to address the effect of using a small sample size to gather data for a research. Traditionally, there are organizations in Jordan that use the BD concept in enhancing innovation. There are areas that have been under-explored in the study on Telecom companies.
The Scope of Research
The research will use professional analysis from Jordan published between 2014 and 2018. Recent peer-reviewed articles were used to enhance the scope of this research reports since BDA is a new concept in the various sectors of the economy. Jordan was considered for the study since many companies in the country have adopted the BDA concept in enhancing decision making for innovation.
⦁ Research Questions
This study report aims at examining the effects that result from the use of a sample size in analyzing the how business organizations in Jordan use BDA in decision making to enhance innovation. Significantly, this research report was spurred by the ongoing expert investigations that show BDA is a new idea that organizations need to adopt in their decision-making process to advance innovative development, consequently keeping up with the present market trends (Al-Kodmany, 2016, P.30). This research was motivated by the fact there are new technologies that have brought about the disruptive change in the different industries in the economy. The drastic changes have been evident in management practices, particularly in the way business organizations use BDA in promoting their services and products in the market.
Researchers believe that technological disruption in any industry is accompanied by an inadvertent desire to change the culture and traditions that were characteristic of the industry. Business organizations in the various economic industries are thus obligated to adjust to a more diversified and new technological ecosystem (Wamba et l., 2017, P. 358). The ripple effect of aligning the company’s culture and traditions to the new disruptive technological will be significant if the researchers used a relatively huge sample in the study. Thus, to ensure that the study had statistical power and finer conclusions, the researchers should have used a wide sample size.
Although the use of small sample sizes in research enhances efficiency in data collection and analysis, the conclusions drawn from the study affect the variability and visualization of the data results to be used on a large scale study. Both the inductive and deductive results may not hold true for business organizations that use both SDA and BDA in their decision making processes for innovation (Al-Kodmany, 2016, P.31). Additionally, there are internal processes within the business organizations that are used to combat the stiff market competitions. This makes it increasingly crucial for researchers to incorporate such diversity measures form various industries to give their studies fundamental statistical power, which can only be achieved through a big sample size.
General Research Question
⦁ What was the impact of using a small sample size in data collection for the research study?
Specific Research Questions
⦁ How does a small sample size in data collection affect the variability and visualization of the research study?
⦁ Does a small sample size in data collection contribute to bias in data analysis?
⦁ Conceptual Framework
Statistical Power for Decision Making
Industries in the economy are described by their basic leadership forms that promote their existence and aggressiveness in the market. This makes it necessary for business organizations to develop marketing strategies that will remain appealing to their customers, thus playing a critical role in guaranteeing these business organizations a significant stay regardless of the dynamic market patterns (Rajaraman, 2016, P.697). Due to the changing idea of innovation, business organizations in Jordan need to completely conform to the market powers by taking into consideration the new dimensions and meanings of development in light of both the internal and external information they have in their data management frameworks.
Furthermore, it is essential for business organizations to integrate relevant data devices for gathering and analyzing the BD. After a successful analysis of the collected data, the business can make innovative ideas from the information gathered. The deficiency of such firms to boost this aspect of research is commensurate to losing their market order and grasp. According to Faber and Fonseca (2014, P.27), a huge sample size for analysis of data does not only boost the confidence in the research but also plays an integral part in ensuring that business organizations make favorable, effective and efficient decisions, which in turn helps them to maintain a good market command.
In any market, competition among business organizations is inevitable. This can be attributed to the fact that each business organization strives to remain relevant in the market by providing services and goods that are in tandem with consumers’ tastes and preferences (Rajaraman, 2016, P.699). In a bid to promote the brand of each business organization, the integration and adoption of BDA in decision-making processes for innovation needs to be spread over a relatively big sample size of different business organizations. The need for a big sample size is aimed at enhancing variability and clear visualization of the analyzed data (Faber et al., 2014, P.28). The size of the effect enacted by the integration of BDA in decision making for innovation will stem from the analysis done on the data collected.
Sampling theory: In line with the sampling theory, to ensure the quality of conclusion drawn from a research, the sample of study should have almost similar characteristics so that the results can be stretched to estimate the characteristics of the entire population (Robinson, 2014, P. 26). Since the research was based on Telecom companies, the variability and visualization of the simulate BDA would be quite challenging. This is due to the fact that the characteristics of the Telecom industry are relatively different from other sector of the economy. Therefore, the sample size used was biased.
HO1: There is no significant impact on the use of a small sample size in data collection for the research study.
HO2: Small sample size in data collection does not affect the variability and visualization of the research study.
HO3: A small sample size does not contribute to bias in data analysis.
A standard research needs to have a considerable sample size for data collection and analysis. This ensures that the data has enough statistical power and can be spread over to an entire population with similar characteristics (Faber et al., 2014, P.28). It follows that the samples used should not be too small or too big since all of them are characterized by scientific limitations that can generally compromise the conclusions that are made from the research study. For instance, a small sample size like from the telecom industry research article used for the development of this research report prevent extrapolation of the research findings (McNeish, and Stapleton, 2016, P. 296). On the contrary, large samples have the negative effects of amplifying the existing statistical differences among the characteristics of the study sample that may be clinically inadmissible.
In this regard, there is need for researchers to develop an appropriate sample size for a specific study. An appropriate sample is relevant in that it ensures the study is capable of incorporating clinically relevant statistical differences in the conclusions drawn from the research. According to Malterud, Siersma, and Guassora (2016, P.1754), there are various methods of coming up with a suitable sample size for a research. For instance, it is crucial to understand the variable of the sample under study, which will be significant in establishing the relationship that exists between the groups that will be evaluated and designing the statistical analysis method that will be used.
A small sample size has the major limitation of interpreting the results drawn from the study. The conclusion drawn is vulnerable to bias. The sample size increases the chances of assumption. (McNeish et al. (2016, P. 298) maintain that the researcher develops a true or false premise which does not have a sound statistical backing. The assumption premise and increased biases in the use of a small sample size in a research study significantly dilutes the statistical power of the research. Noteworthy, Faber et al. (2014, P.29) maintains that the statistical power of a study is its ability to detect an effect under study. For instance, in the research article used for the development of this research proposal report, the effect that was studied was to identify the role of BDA in innovation decision making across the Telecom industry in Jordan.
Small sizes are economically infertile. If the financial resources are used in developing research and the researchers opt to use a small sample size may preside over invalid and biased conclusions from being made (Hopkins, 2017). If financial and time resources are used in the development of such a study, then the research is rendered economically infertile. It is, therefore, the sole responsibility of the researchers to ensure that they use appropriate samples in research. This will ensure that the data generated will be of high quality and reliable (Malterud et al., 2016, P. 1755). Otherwise, the use of a small sample sizes in developing a research affects both the internal and external validity of statistical concept under study.
⦁ Methods Research Methodology
The proposed research method is qualitative research. This methodology was adopted for the development of this report since it was easy to integrate the feelings of the respondents with data analysis in a natural setting. More so, qualitative research is easy for the researcher in collecting relevant data since it inculcates the beliefs, feelings, and values of the respondents which cannot be captured in quantitative research (McCusker et al., 2015, P. 540). Qualitative research is objective in nature since it targets a specific cadre of people in a study. Formulation of functional hypotheses was aided by the concepts of qualitative research which are instrumental in developing a conceptual framework for developing the statement problem. McCusker et al. (2015, P.541) argue that research anchored on the principles of interpretive methodological principles, qualitative research enhances a deeper understanding of the research problem through the use of structured and semi-structured techniques in data collection.
The study sample for this research was limited to three Telecom companies in Jordan (Cleary, Horsfall and Hayter, 2014, P.474). The inclusion criteria also Telecom companies that use BDA in decision making for innovation. This sampling strategy was relevant to the study since it was easy for the researcher to understand common characteristics among the study population to promote multiple common patterns in decision making for innovation in the telecom industry. Only companies that are registered with the ministry of communication and information science in Jordan were also considered in data collection.
Data Collection Instruments
The study report utilized interviews as a tool for data collection whereby the senior managers of the Telecom organizations were interviewed. Moreover, business executives in the companies were also distinguished as the perfect subjects for data collection (Hahn and Lülfs, 2014, P.401). The business executives were considered the perfect source of information since they were acquainted with issues relating to innovation within their firms and they were additionally better set to clarify the abilities of their organizations in utilizing and managing BDA (Zhang and Wildemuth, 2016, P.318). To encourage information quality, the interviews will be done on a face to face basis and semi-structured, which forms the foundation for carrying out qualitative research.
The analysis of data gathered will comprise a keen reading of the interview transcripts line by line several times to encourage simple coding and consequently dissecting the reactions of the interviewees. Microsoft Word was used to sort out and manage the data collected from the interview transcripts. NVivo, computer programming software concepts, were used to further sort out and analyze the data using the word software.
The topic ‘the effects of using a small sample size in data collection for research’ is relevant to the contemporary Telecom industry and other sectors of the economy as well. As earlier discussed, the desire to make innovative decisions by business organizations is based on the basic foundation of meeting consumers’ tastes and preferences. The sample size used in decision making should thus be tailored towards ensuring the business organization maintains a good market command (Cleary et al., 2014, P.475). The study also provides good insights into how researchers need to remain objective in their studies and shun subjective tendencies in data collection and analysis that may result in bias. For instance, in collecting data through interviews, the researcher should not twist questions to fit their ideal situation under study.
This research report also has a literature gap in its development, thus presenting an opportunity for future studies. It is crucial to point out that that the research is ideally based on the telecom industry. The inclusion of other industries in the research may not be sufficient evidence to support the conclusions drawn from this research since each and every industry has its unique features of how they utilize their BDA in enhancing innovative decision making (Robinson, 2014). This research report does not provide the parameters within which such statistical disparities can be contained. Hopkins (2017) argues that a literature gap is significant in a study since scholars can further it to identify how the disparities in the use of BDA by different industries in Jordan affect innovative decision making in their quest to maintain a competitive market advantage.
⦁ Limitations and Delimitations
The main limitations of this study stem from the research method used in this study. Qualitative research used as a tool for data collection focused mainly on the observable outcome of the results. Orcher (2016) maintains that researchers have to ensure that data collection uses primary techniques like the use of questionnaires and open-ended interviews to maintain the objectivity of the research study. The researcher might develop objectiveness in sorting the data for analysis. The conclusions that the researcher draws may be prone to bias if they decide not to follow the inclusion-exclusion criteria outlined in the study research guidelines and thus inadvertently affecting research processes. This negatively influences the objective of the study research (Cleary et al., 2014, P.475). Noteworthy, any empirical bias in data collection and analysis contributes to weak and incomprehensive conclusions for the specific study research.
The main intention of this research is to identify the effect of using a small sample size in research. As such, there is need for inclusion of other data collection parameters like cross cultural diversity and the difference in database systems used by the respective industries under study.
⦁ Ethical Issues
The researcher will start by seeking approval from the university’s board for internal research on the chosen topic of study and objectives of the research. The researcher will conduct a search of the relevant peer-reviewed scholarly sources on the web to get more information on the topic study apart from the assigned article meant for developing this research (Rhodes, 2018, P. 489). An in-depth analysis of peer-reviewed sources is vital since it enhances the ability of the researcher to critique the objectives of the study and in the matching limitations presented in the articles with the research topic. It is worth noting that doing an in-depth analysis of peer-reviewed articles relevant to the topic research helps in developing a strong problem statement for the research report.
The researcher will formulate a confidential agreement that will be used in data collection and analysis of the results. The confidential report will be instrumental in guiding the researcher to strictly observe the privacy terms and policies of the financial institutions identified for the data collection (Mulvey, 2015, P.478). The researcher will seek permission from the university board to publish the research on reputable web pages for future references by scholars and researchers globally.Free research proposal samples and dissertation proposal examples available online are plagiarized. They cannot be used as your own paper, even a part of it. You can order a high-quality custom proposal on your topic from expert writers:
EffectivePapers.com is a professional research proposal writing service committed to writing non-plagiarized custom proposals of top quality. All research proposals and thesis proposals are written from scratch by PhD academic experts you can hire online. Just proceed with your order, and we will find the best expert for you!
Al-Kodmany, K., 2016. Scope of Research. In New Suburbanism: Sustainable Tall Building Development (pp. 28-32). Routledge.
Aras, G. and Crowther, D., 2013. Sustainable practice: The real triple bottom line. In The governance of risk (pp. 1-18). Emerald Group Publishing Limited.
Cleary, M., Horsfall, J., and Hayter, M., 2014. Data collection and sampling in qualitative research: does size matter? Journal of advanced nursing, 70(3), pp.473-475.
Faber, J. and Fonseca, L.M., 2014. How sample size influences research outcomes. Dental press journal of orthodontics, 19(4), pp.27-29.
Hahn, R. and Lülfs, R., 2014. Legitimizing negative aspects in GRI-oriented sustainability reporting: A qualitative analysis of corporate disclosure strategies. Journal of business ethics, 123(3), pp.401-420.
Hopkins, W.G., 2017. Estimating Sample Size for Magnitude-Based Inferences. Sportscience, 21.
Malterud, K., Siersma, V.D. and Guassora, A.D., 2016. Sample size in qualitative interview studies: guided by information power. Qualitative health research, 26(13), pp.1753-1760.
McCusker, K. and Gunaydin, S., 2015. Research using qualitative, quantitative or mixed methods and choice based on the research. Perfusion, 30(7), pp.537-542.
McNeish, D.M. and Stapleton, L.M., 2016. The effect of small sample size on two-level model estimates: A review and illustration. Educational Psychology Review, 28(2), pp.295-314.
Mulvey, G.J., 2015. Ethics in research. Bulletin of the American Meteorological Society, 96(3), pp.477-479.
Orcher, L.T., 2016. Conducting a survey: Techniques for a term project. Routledge.
Rajaraman, V., 2016. Big data analytics. Resonance, 21(8), pp.695-716.
Rhodes, R., 2018. The goodness of ethics in research ethics review. Journal of medical ethics, 44(7), pp.489-490.
Robinson, O.C., 2014. Sampling in interview-based qualitative research: A theoretical and practical guide. Qualitative research in psychology, 11(1), pp.25-41.
Wamba, S.F., Gunasekaran, A., Akter, S., Ren, S.J.F., Dubey, R. and Childe, S.J., 2017. Big data analytics and firm performance: Effects of dynamic capabilities. Journal of Business Research, 70, pp.356-365.
Zhang, Y. and Wildemuth, B.M., 2016. Qualitative analysis of content. Applications of social research methods to questions in information and library science, 318.