Explaining Differences with Dependent and Independent variables

When attempting to explain differences between two or more subgroups, researchers often find it helpful to consider some variables dependent variables and others independent variables.

If a certain variable is believed to be influenced by some other variable, the former can be considered to be a dependent variable. Rates of product usage, brand preference, and attitudes are variables that can be influenced or affected by product quality, advertising, price and other things. Since product usage, preferences, and attitudes are at least partially dependent upon the firm’s marketing activities, such variables can be treated as dependent variables.

An independent variable is one, researchers believe can help explain the differences between the two or more sub groups that have been formed by the dependent variable. Changes in a pizza’s price, ingredients, and freshness are thought to affect the pizza’s sales, rather than vice versa. Consequently, these three variables can be viewed as independent variables. If pizza is believed to be consumed more by students who are upperclassmen and who have more spending money, then year in college and amount of spending money are considered to be independent variables that influence the dependent variable – frequency of eating pizza. It is in the manner that researchers use some variables as independent variables to help explain the differences observed in a dependent variable.

Cross tabulation:

Perhaps the method of analysis used most often in marketing research is cross tabulation. The reader has already been introduced to the fundamentals of cross tabulation discussion on bivariate and multivariate tabulation. However, three additional points will help the reader gain a better understanding of the use of cross tabulation.

The Data are in categorical form: Cross tabulation is applicable to data in which both the dependent and the independent variables appear in categorical form. There are two types of categorical data.

One type consists of variables that can be measured only in classes or categories. For convenience, call them type A categorical variables. Marital status, type of occupation, whether a respondent rents or owns the home he or she lives in, and sex are examples of survey variables that can only be measured in categories. It is important to note that the different categories associated with such types of categorical variables are not quantifiable (i.e. there is no measurable number that identifies a person as being unmarried or having a blue collar occupation).

A second type of categorical variable – call them type B – includes one more conveniently measured in categories than on a continuum such as age (younger than 30,30-50, older than 50) or income (less than $20,000; $20,000or more). For these types of variables, the different categories are associated with quantifiable numbers that show a progression from smaller values to larger values.

Also included in this second type of categorical variable are ones in which the different categories are imprecisely quantifiable but that nevertheless are also shown as a progression from smaller values to larger values, or from a low level to a higher level. Three frequently encountered examples of such categorical variables are: the intensity of a respondent’s intention to buy a particular product (definitely will not buy, probably will not buy, undecided, and so forth); the level of a respondent’s agreement or disagreement with a particular attitude statement (disagree completely, disagree somewhat, neither agree nor disagree, and so on); a person’s frequency of readership of a magazine (never reads Time, reads some issues of Time, reads most issues of Time, and so on).

Cross tabulation is used on both types of categorical variables. However, when constructing a cross tabulation using type B categorical variables, researchers find it helpful to use several special steps to make such cross tabulations more effective analysis tools.