The four measurement scales that I have chosen will be Nominal, Ordinal, Interval, and Ratio.
These measurements all severe a purpose when conducting marketing research especially when conducting questionnaires or surveys. Without these scales market researchers could not find the answers to most of their questions. If the questionnaire has no one standard result, it will indicate that the system has a flaw and needs one of these four scale to accurately determine such anticipated results. I will now go into more depth to the following measurement scales.Qualitative Data Before focusing on the selected scales I would like to cover a bit on qualitative data which is a non-numerical documents that are conveyed into words and sentences.
This type of information can be documents through the comments made by individuals on a product or service. Nevertheless, qualitative data can later be transferred into a numerical sense and only then can be nominal or ordinal. A lot of analyzing has to be used in cases like these to insure minimal trial for error.The nominal scale is a form of numerical means that involves counting, for example if researchers wanted to know things like hair or eye color they would use an nominal scale this scale can also apply for gender, residence or even age differences. This is why nominal scales are used principally to differentiate between certain items or characteristics of a product or service in the marketing sense. When researcher work with nominal data, the substances do not include a nature, evocative order and thus researchers can count these items but will not be able to order or measure them.
On the other hand the calculation that are based on frequencies are considered to be effective. Since there are many errors or miscalculations from traditional assigning of numbers to the object which may include certain ideas or behavior used, researchers have found nominal data more convenient for analyzing numerical data. Ordinal data has an array of characteristics that involve objects as a type of data that does not have a great degree value but can produce an even flow and significant order. It is because of this fact that ordinal data cannot be measured but has the potential to be ordered and counted for.
Researchers can neither add nor subtract when working with the ordinal scale but, the objects within the scale can be used to rank-ordered merely based on the amount of items they possess. With this fact it will the result of data analysis will conclude in rank order. According to www. statistics. com, objects at ordinal scale have differences in comparison to the other objects measured.
The most common methods used in the ordinal scale are: 1st, 2nd, best, worst, strongly disagree, disagree, agree, strongly agree, and no opinion. Quantitative Data Quantitative data signifies the direct measurement of an object or idea.This form of data may be the result of something in the form of a number or an amount. For example the number of employees to a company and the amount of money in the company’s budget are just a few examples.
Yet, researchers often use numbers to code certain objects or characteristics and thus not making these numbers data. Interval data is when the researcher collections needed objects that are based on some type of intervals where the distance between any two adjacent units of measurements are one in the same, the results are in the form of interval data.Since there is no absolute zero on the interval scale the zero point now becomes arbitrary. It is fairly easy to measure order and magnitude on this scale. Even though interval data may have the capacity to either be added or subtracted, multiplication or division however is not possible on the interval scale. Interval data has to do with ordering the results in such a way that almost mirrors the ordinal data.
Nonetheless, interval data goes more in depth by including dates, measures of longitude, or latitude of tides are just a few examples of what the interval data in tales.The focal point of the differences between interval data and ratio data is that ratio data contains a meaningful zero point value as a pose to the interval data. It is not to say that the ratio between other numbers is not meaningful. However, in the ratio data the researcher can now handle this data in a number of ways which include addition, subtraction, multiplication and division properties. Many managers of large organizations at times find it rather difficult to differentiate between ratio and interval data when conducting research.When it comes to complications dealing with age, education, wages, weight, money or distance the ratio data needs to come into play.
Conclusion: In conclusion, sampling is necessary when the objective population for the conducted study is rather large in size. These samples can be easily obtained by using random, systematic, and stratified or cluster methods. On the other hand both qualitative and quantitative data can be collected from the same sample group. This type of research can be used when working with media such as television, radio, online and so on.
