Updated date:

Basics of Behavioral Research: Simple Definitions of Variables and Measurements

Author:

Eric Coggins has degrees in political science, global management, and global organizational leadership. He teaches international business.

This article will break down some of the basic terms of quantitative analysis.

This article will break down some of the basic terms of quantitative analysis.

Qualitative and quantitative statistical analysis can be very helpful to a business or organization wishing to formulate an effective marketing strategy. Yet, understanding qualitative and quantitative statistics and its tools can be very confusing. This article seeks to make sense of the basic terms associated with quantitative analysis.

Variables

A variable is an observable characteristic of an object or event that can be described according to some well-defined classification or measurement scheme.

Examples of variables studied in the behavioral or social science research include: gender, income, education, social class, organizational productivity, task orientation, recall memory, recognition memory, and achievement (Kerlinger & Lee, 2001).

Independent and Dependent Variables

An independent variable is a phenomena that is manipulated by a researcher and is predicted to have an effect on other phenomena (Williams & Monge, 2001). An example of an independent variable would be a teaching method, a medical treatment, or training regimen.

A dependent variable is a phenomenon that affected by the researcher's manipulation of another phenomena. For instance, achievement is the effect of a teaching method, cure or not the effect of a medical treatment, and higher skill level or not (achievement) the effect of a training regimen.

Suppose an educational researcher wants to know how a certain teaching style affects learning in the classroom and will measure the difference by giving students a pre-test before the teaching style is applied and then retesting those same students afterwards. The independent variable would be the new teaching method (the cause) and the dependent variable would be the resulting test scores or the outcome or effect).

Active and Attribute Variables

Kerlinger and Lee make another distinction in variables between active and attribute.

An active variable is a variable that can be manipulated. Active variables are also called experimental variables. Examples of this type of variable are teaching methods, training regimens, and the like, which can be altered to gauge their effect on phenomena.

An attribute variable is a variable that cannot be manipulated. An example of an attribute variable is gender, race, psychological condition, and or any characteristic that is inherent or pre-programmed and cannot be altered.

Categorical and Continuous Variables

A third pair of important variables are categorical and continuous variables (Kerlinger & Lee).

Categorical variables belong to a measurement called nominal and demographic in nature. This means they are used for purposes of classification into mutually exclusive categories. As such, they have no rank and are thus of equal status like gender, age, race, religious preference, and political affiliation.

Continuous variables are those that have an ordered sense of values within a certain range, with a theoretical infinite number of values within that range. An example of this type of variable is intelligence, which can be designated high, medium, or low depending on scores on achievement tests.

Measurement Scales in Statistical Analysis

In statistical analysis, there are four basic levels of measurement.

Nominal Scale

The nominal scale is the weakest form of statistical measurement. Researchers use a nominal scale to classify observations with no intention to order or rank the findings in level of importance. Such observations include highlighting the color of eyes, race, religion, nationality, and the like.

Ordinal Scale

The ordinal scale incorporates the nominal scale but seeks to rank responses with some "greater than" or "less than." For instance, a research questionnaire might be designed to learn how much adults enjoy using social media like facebook or the results of a horse race might be listed in the order of finish.

Both the nominal and ordinal scales of measurement are primarily used in qualitative analysis.

Interval and Ratio Scales

A third form of statistical measurement is the interval scale. The first characteristic of interval and ratio scales is that the level of significance is treated in terms of known and equal intervals. The second characteristic of these levels or scales is that they are quantitative in nature. Furthermore, some or all arithmetic operations can be applied to them.

Validity and Reliability

In Reasoning with Statistics, Frederick Williams and Peter Monge (2001) noted:

"Procedures for statistical reasoning are themselves without safeguards for warning the researchers when a measurement scale leads to spurious descriptions."

In other words, there is always the possibility that the method chosen will indeed lead to statistical madness. In order to ensure the results of a particular statistical analysis, the would-be researcher must take into consideration the concepts of validity and reliability.

Validity

Validity in behavioral or social science research indicates the degree to which scales measure what researchers claim they measure. Williams & Monge point out that "the question of validity is a question of 'goodness of fit' between what the researcher defined as characteristics of a phenomenon and what he or she reported in the language of the measurement" (p. 29).

For instance, the concept of validity may ask such a question as "to what degree do achievement scores on an exam relate to the retention of knowledge of a certain subject?" In an absurd extreme, the concept of validity would be violated if a teacher gave an exam about Section 4 of a U.S. History text when she wanted to know how much her students learned from Section 5 of their math text. Likewise, a social science researcher would be amiss if she measured perceptions of leadership style by giving a personality test.

Reliability

Reliability in behavioral science research refers to the internal and external consistency of measurement. Reliability seeks to know whether the chosen tool of measurement would yield the same results if applied under the exact same conditions.

This article is accurate and true to the best of the author’s knowledge. Content is for informational or entertainment purposes only and does not substitute for personal counsel or professional advice in business, financial, legal, or technical matters.

Comments

Qamar mehmmod on November 29, 2011:

Above provide information is very beneficial and conceptual

Related Articles