Quantitative analysis collects and analyzes "mathematical and statistical modeling, measurement, and research to understand behavior." (Will Kenton, 2020, para. 1) The essential concept of Quantitative analysis is that its domain is "the measurement, performance evaluation, valuation of a financial instrument, and predicting real-world events such as changes in a country's gross domestic product (GDP)." (Will Kenton, 2020, para. 1) Therefore, Quantitative analysis evaluates and anticipates the past, current, and future events, and the values must be quantifiable.
Variables in quantitative analysis
The quantitative analysis focuses on a variety of variables, and then the top tier types are (1) Independent variables (IV), (2) Dependent variables (DV), (3) Sample variables, and (4) Extraneous variables. (Capella.Edu, 2020, p. 1) The big picture of research variables is shown in Diagram 1.
Nominal data
Nominal data or nominal scale in science (mathematics and statics) is a type of data that is used for "label variables without providing any quantitative value," and it is "the simplest form of a scale of measure." (Soetewey, 2019, p. 1). In Qualitative research and analysis, however, nominal data is the type of variable that "there is no ordering is possible or implied in levels." (Soetewey, 2019, p. 2) There are numerous amounts of actual events in which their values can not be in order, such as human gender, eye colors, etc. So, in general, the nominal values used for name, label, attributes, and categories need to be measured. But the question is, who can we assign numbers to the nominal values? We can give numbers to the nominal values by "numbers, but the order is arbitrary, and arithmetic operations cannot be performed on the numbers." (Soetewey, 2019)
There are two general types of quantitative nominal variables, including "collection technique and numeric property." A collection technique in a quantitative nominal data collection is used by surveys, questionnaires, interviews, etc. And all these methods are based on the questions answered between researcher and participants. However, the nominal questions could be "Open-ended or Closed-ended" (Soetewey, 2019, p. 2). The Open-ended questionaries give the responders the freedom to choose how to answer, and a Closed-ended method restricts and makes boundaries responders answer. So, in a nominal data collection, responders can participate in the way they would like to answer or based on the researcher's point of view.
Numeric variables, called Quantitative variables, on the other hand, are quantifiable numbers that can be continuous or infinite numbers or discrete or finite numbers in a given interval.
Ordinal data
Opposing to the nominal data, which was not in order, the Quantitative Ordinal data variables are based on rankings, order, and levels. Therefore, the scale of variables is crucial in this method. For example, collecting data to measure the severity of road accidents on a scale of "light, moderate and fatal accidents" (Soetewey, 2019) or healthcare values such as "poor, reasonable, good, or excellent" are Qualitative ordinal data.
Scale Data (Ratio Scale Data)
In Quantitative research, sometimes we need to measure the Ratio and scale of data in a predefined interval called Scale Data. Therefore Scale data has "an absolute zero point." (Lecture 1, 2020, p. 2) A true zero in Scale data means that "the data has no value point." (Unsw.Edu.Au, 2020) For example, temperature measuring research, weight research, or bank account balance are Scale data collection methods.
Interval Data
In Quantitative research, sometimes we need to measure the ratio and scale of data in a predefined interval called Scale Data. Therefore, Scale data has "an absolute zero point." (Lecture 1, 2020, p. 2) For example, temperature measuring research, weight research, or bank account balance are Scale data collection methods.
Conclusion
In brief, we can compare these four Qualitative data collection methods as "Ratio is more sophisticated than interval, the interval is more sophisticated than ordinal and ordinal is more sophisticated than nominal." (Lecture 1, 2020, p. 2) Therefore, using one of the data variable methods is depends on the researcher's requirements.
References
Capella.Edu. (2020). Variables in Quantitative Research: A Beginner’s Guide – SOBT. Capella.Edu. Retrieved 2022, from https://campustools.capella.edu/BBCourse_Production/PhD_Colloquia/Track_2/SOBT/phd_t2_sobt_u02s2_h01_quantvar.html
Lecture 1. (2020). lecture1. Pdx.Edu. Retrieved 2022, from http://web.pdx.edu/%7Enewsomj/pa551/lecture1.htm
Soetewey, A. (2019, December 10). Nominal, Ordinal, Interval & Ratio Variable + [Examples]. Statsandr.Com. Retrieved 2022, from https://www.formpl.us/blog/nominal-ordinal-interval-ratio-variable-example
Unsw.Edu.Au, U. (2020, January 30). Types of Data & the Scales of Measurement | UNSW Online. Unsw.Edu.Au. Retrieved 2022, from https://studyonline.unsw.edu.au/blog/types-of-data
Will Kenton. (2020, November 27). How Quantitative Analysis (QA) Works. Investopedia. Retrieved 2022, from https://www.investopedia.com/terms/q/quantitativeanalysis.asp
Diagrams, Tables, and Definitions
Diagram 1. The big picture of research variables. (Unsw.Edu.Au, 2020)
No comments:
Post a Comment