Variables fall into a number of different groups, based on the type of data the variable stores, the type of question the variable is based on, and the way the variable is used. The following table lists all of the various types of variables and shows their icons.

A categorical variable that can have only one value for each case, such as a variable based on a question that requires the respondent to choose one answer from a predefined set of answers. An example is the question "Have you visited this museum before?" to which the respondent must answer "Yes" or "No". Also known as single categorical.

See Categorical variables for more information.

A categorical variable that can have more than one value for each case—for example, a variable based on a question to which the respondent can choose several answers from a predefined set of answers. A typical example is the question "What do you remember seeing in the museum today?" in response to which the respondent can select any number of items in a list. Also known as multiple categorical.

See Categorical variables for more information.

A variable that stores a numeric value for each case. A numeric variable can store an integer or a real value.

See Numeric variables for more information.

A variable that contains data that is text, such as names and addresses or responses to open-ended questions.

See Text variables for more information.

A variable that stores date and time information.

A special type of integer variable that can contain values of True or False. Also called a Yes/No variable.

See Boolean variables for more information.

A loop defines a set of questions that are to be asked more than once. In a categorical loop, the number of times the loop is to be iterated (and therefore the number of times that the set of questions in the loop are to be asked) is controlled by the categories in a category list. For example, the set of questions can be asked for each product in a product list. In a numeric loop, the number of times the loop is to be iterated is controlled by a numeric expression.

See Loops and grids for more information.

A special type of loop in which all of the iterations are presented simultaneously to the respondent in a grid format. Grid questions often ask respondents to choose a rating on a predefined scale for a number of products in a list.

See Loops and grids for more information.

When you are using a hierarchical view of the data, all loops are represented hierarchically as levels. However, when a loop is defined as expanded, it can also be viewed in an expanded (flattened) format as well, which means that you use it to create grid tables and you can select individual slices of the loop.

See Loops and grids for more information.

Group for presentation purposes a number of related questions that share a category list. A compound is not the same as a grid, although a compound may contain one or more grids.

See Blocks and compounds for more information.

Groups one or more questions into a block.

See Blocks and compounds for more information.

This icon can appear on any numeric, text, date, Boolean, and categorical variable and indicates that an axis expression has been defined for the variable.

See Axis expressions for more information.

A variable that stores the open-ended responses to an Other Specify category. These are special categories that allow the respondent to enter an answer that is not on the category list. For example, in a question that asks which other museums the respondent has visited, there are categories specifying six major museums, and one category with the text "Other". When respondents select this category, they are asked to specify the name of another museum they have visited.

See Categorical variables for more information.

A text helper variable that holds the name of a file that contains an image or a recording of a question response (such as a .TIFF file containing a scanned image of a hand-written response or a sound file that contains a recording of an open-ended response in a telephone interview).

A categorical variable that stores the responses to an open-ended question after they have been sorted into categories. The process by which the responses to open-ended questions are sorted into categories is usually called coding.

See Text variables for more information.

A special numeric variable that has been set up to weight the data. You use weighting when you want the figures in your table to reflect your target population more accurately than the actual figures do.

For example, suppose your target population consists of 57% women and 43% men, but you interviewed 50% women and 50% men for your survey. By applying weighting, you can make the women's figures count for more than the men's figures, so that they more accurately reflect the gender distribution in the target population.

See Weighting for more information.

Standard variables that are present in most data sets to store standard information, such as the respondent's serial number, the mode of data collection used, the version of the questionnaire used to collect the data, and so on. Some data sets (such as databases) do not have system variables.

See System variables for more information.

A variable that has been created from other variables using an expression. For example, you might create a numeric derived variable to show the sum of the values stored in two or more other numeric variables.

See Derived variables for more information.

This is a variable that has been created from the top or side axis using the New Variable from Side/Top option.