Data collection is defined as systematically gathering data for a particular purpose from various sources. The process is a preliminary to statistical analysis of the data. There are two broad methods of data collection – quantitative and qualitative data collection methods.
Quantitative data collection methods
Quantitative data methods explain phenomena by collecting numerical data. The data is then analyzed using mathematically based methods, particularly statistics (Wyszecki, Günter, and W. S. Stiles, 2000). They rely on random sampling and structured data collection instruments that tally varied experiences into predetermined response categories. They produce results that are easy to summarize, compare, and generalize. Typical methods of quantitative data collection are interviews and questionnaires. Interviews are conducted as face-to-face interviews, telephone interviews, or Computer Assisted Personal Interviewing (CAPI). In CAPI, the interviewer brings along a laptop in which he enters the data directly into the database. Questionnaires are either paper-pencil-questionnaires or web based questionnaires (in which the responder receives an e-mail on which he or she finds a link to an address that takes them to a secure website where they fill in a questionnaire. Responses are graded numerically. For instance, responders may be asked to rate a number of statements, for example, “e-commerce is better than conventional commerce”. Responses are then graded as either ‘agree strongly’, ‘agree’, ‘disagree’ or ‘disagree strongly’, and the answers are given a number (e.g. 1 for ‘disagree strongly’, 4 for agree strongly). Quantitative methods are used in the natural sciences
Qualitative data collection methods
Qualitative data collection methods provide data that give an in-depth understanding of human behavior and the reasons that govern such behavior. (Tracy, S. J, 2013). The qualitative method investigates the why and how of decision making. Hence, smaller but focused samples are more often used than large samples. The data obtained provides information useful for understanding the processes behind observed results and gauge changes in people’s perceptions. Techniques used include individual or focus group interviews, which use structured or unstructured questions; observations, and action research in which the researcher actively participates in an organization change situation whilst conducting research.
Data analysis
Data analysis is the process of interpreting and summarizing data so that it becomes information. The information can be easily interpreted, and conclusions made to support decision making.
In the analysis of Quantitative data, four levels of measurement are identified: nominal data, ordinal data, interval data and ratio scales. (Beck, M. S, 2006) Nominal data has no logical order. It is basic data such as male or female. Ordinal data has a rational order but the differences between values are not constant, such as levels of education. Interval data is continuous, has a logical order, and has standardized differences between values, but no natural zero such as the Likert scale which ranks the level of satisfaction on a scale of 1-5. Ratio or scale data is continuous, ordered, has standardized differences between values, and a natural zero, for example, height, weight, age, length. Once the levels have been identified data is tabulated to give frequency distributions & percent distributions. The data can then be analyzed descriptively to give the mean, minimum and maximum values, median and mode. The data can also be disaggregated and cross tabulated across multiple categories. For example, it may be established who between men and women prefer e-commerce to standard commerce. Finally, advanced analytical methods will include correlation, Analysis of variance (ANOVA) and regression. Correlation describes the relationship between two variables (i.e., strong and negative, weak and positive, statistically significant). Analysis of variance (ANOVA) determines whether the difference in means (averages) for two groups is statistically significant. Regression is used to determine whether one variable is a predictor of another variable.
Qualitative data analysis identifies, examines and interprets patterns and themes in textual data. It determines how these patterns and themes help answer the research questions. It is a very fluid process that is highly dependent on the surveyor and the context of the study. The data is then processed to assess the highlights of the interaction and then it is grouped into meaningful patterns and/or themes observed through content or thematic analysis. One or both types of analysis can be used. Content analysis is carried out by coding the data for particular words or content, identifying their patterns and finally interpreting their meanings or patterns. Thematic analysis, on the other hand, groups the data into themes that help answer the research questions. These themes may be directly evolved from the research questions which were pre-set before data collection even began, or may naturally emerge from the data as the study was conducted. Once the themes or content patterns are identified, they are organized into a display that facilitates a conclusion to be drawn. The display can be graphic, in the form of tables, or textual display.
Conclusion
In this regard, quantitative data collection methods, specifically questionnaires will be used in research. It will give information from a large sample size, therefore, the conclusions drawn from the study will be more accurate in comparison to using quantitative data that use smaller samples. It is also easy to conduct and summarize. The data will be tabulated and cross analyzed to provide information that will answer all the questions this research aims to answer, specifically the evolution of e-commerce over the past decade.