Data: Qualitative vs Quantitative Variables

Data

• Data consists of qualitative and quantitative variables, representing a collection of numerical facts.
• Data is raw and unorganized facts that need processing, and a single numerical fact is called a datum.
• Information is defined as data that has been processed, organized, structured, or presented in a context.
• Quantitative data includes numeric characteristics, generally known as statistical data which can be discrete (e.g., students rank) or continuous (e.g., CGPA, weight).
• Qualitative data includes non-numeric characteristics such as gender, hair color, and honesty.
• Examples of quantitative data are sales volume and scores, while examples of qualitative data are gender, hair color, and honesty.

Level of Measurements

• Nominal data have labels or names, and are mutually exclusive (e.g., gender, jersey number).
• Ordinal data have relative ranking and rating of items based on qualitative variables (e.g., students rank).
• Interval data are based on a scale where zero has a meaning (e.g., racial tolerance, measure of dress).
• Ratio data are based on a scale with a known unit of measurement, where zero has no meaning (e.g., wages, money, interest rate, distance).

Data Collection

• Data can be obtained from primary, internal, and secondary sources.
• Primary data is collected by an investigator for statistical enquiry, using questionnaires, personal interviews, mail, or telephone, and observation.
• Advantages of primary data include high accuracy, detailed depiction, reliability, and independence.
• Disadvantages of primary data collection are time consumption, high financial costs, and the need for skilled personnel.
• Internal data is a byproduct of routine business record keeping (e.g., sales amount, R&D).
• Secondary data were collected at an earlier time by a different person for a different purpose, obtainable from journals, reports, government publications, and research organization publications.
• Advantages of secondary data include being readily available, less costly, time-saving, and accurate.
• Disadvantages of secondary data include questionable reliability and sources, the need for extra precaution, and potential unverifiable accuracy.
• Factors to consider when using secondary data: suitability, reliability, unbiased collecting agency, accuracy, adequacy, and sample representativeness.

Designing a Questionnaire

• A cover letter should be included by the person in charge containing an introduction and survey objectives.
• Minimize the number of questions, arranging them logically, keeping them short and simple.
• Sensitive questions should be avoided.
• Instructions to informants should be included.
• Footnotes should be added for clarifications if required.
• Questions should be capable of objective answers.
• Answers to questions should not require calculations.
• Pre-testing of the questionnaire should occur.
• Include cross-checks and incentives to respondents.
• Method of tabulation to be used should be stated.
• A highly structured questionnaire has predetermined questions and responses.
• A highly unstructured questionnaire has questions that are tossed predetermined, allowing free response.
• A disguised questionnaire hides the purpose of the study, while an undisguised questionnaire makes it obvious.

Key Terms

• Variables are factors or characteristics with different possible values, qualitative or quantitative (e.g., income, height).
• Population is a complete set of observations of the entire group of individuals under consideration, commonly represented by 'N' (e.g., total number of students at a university).
• Parameter describes a number describing a whole population (e.g., population mean).
• Sample is a set of data drawn from a population for valid generalization, commonly represented by 'n'.
• Statistic describes a number describing a sample (e.g., sample mean).
• Sample size represents the number of items under investigation in a sample.
• Survey is a process of obtaining desired data.
• Census survey obtains data referring to the entire population, including total coverage.
• Sample survey obtains data referring to a portion of the entire population, including only a partial coverage.