# Classification

Base Period – A period of time during which data have been collected, data that are used as a base for an index number or for some other fractional number. The base period is usually one year. However, it can also be one day or average of a number of years.

Bivariate – Relating to, or involving two variables. See also: Bivaraite distribution

Breakdown – Syn: Crosstable/Cross tabulation See: Cross Table

Category – A homogeneous class or group of objects, persons or measurements. The category may be named for one of its finite characteristics or for the limits of the measurements assigned. For example: sex (male or female); age ( 1-5; 6-10 years).

Class – Data, persons, objects, opinions, etc., assigned to a specified group. The purpose of this method is to clarify the data and/or to render the data more accessible to analysis. For example: classification according to age (16-30 years, 31-35 years, 36-40 years) consists of three classes.

Classification – The division of persons, objects, scores, possession, etc. into groups in accordance with specific criteria. Examples: men; households in the State of New York; or owners of dogs.

Column – The vertical classification of data ( figures, persons, objects) in distribution table. The horizontal distribution is termed a row. (All cross tables have columns and rows).     See also: Cross Table/Table/Distribution

Cross Table – Syn: Cross Tabulation/Breakdown      The structure of, as a rule, two frequency distributions. The cross table consists of two (or more) variables that reveal coherence that would be difficult to discover otherwise.   See also: Column

Cross Tabulation – Syn: Cross table/Breakdown See: Cross Table

Dichotomy – From Greek “diche’ = in two. Division into two parts, into two classes or categories. For example: yes/no answers, true/false, men/women   See also: Attribute/Category/Trichotomy

Double Dichotomy – The division of a set of elements usually attributes, into two dichotomies. In this manner a set of elements maybe divided into A and not-A. Both groups can be subdivided into two subgroups that have a second attribute: B or not-B. See also: Dichotomy/Attribute/Two-by-two frequency table

Frequency – The number of elements of a population (persons, objects) that are a placed in a specified class. For example: own washing machine: 94%.”

Frequency Table – Frequency distribution represented in the form of a table, which or may not be in interval classes (depending on the distribution). It is difficult to tabulate data of more than two variables. See also Frequency distribution

Inventory Statistics – A form of statistics in which an inventory is drawn up concerning data interest. It usually takes the form of a table or graph. It is the simplest form of statistics. Example: a table consisting of the different kinds of patients in hospitals, mentioning the number in each category.

Limit of class – The end, the boundary, of a class. In the example of the classification 16-30 years, 31-35 years, 36-40 years, the limits of the classes are; 16, 30,31,35,36 and 40 years.    See also: Class

Open-ended Classes – When in a frequency distribution the first and/or the last class interval is not specified, the term “open-ended” is used. For some kind of calculation, such classes are undesirable. In the calculation of medians and quartiles open-ended classes have no effect. For example: open-ended classes: 65 years or older: “10%.”       See also: Frequency Distribution/Limit of Class/Quartile

Parameter – 1. Mathematics: an arbitrary constant that may vary between a set of values.

1. Statistics: the constant in cases in which frequency distributions are being defined (such as population parameters) or in models that describe stochastic situations (for example: regression parameters). The area of tolerable variation of parameters defines the class of the population or model under study.
2. Graphics: the constant factor in an equation that determines the curve of a graph.

Proportion – A segment of a sample or population with a specific characteristic.

Raw Score – Unprocessed scores. Data that still require processing. They are sometimes transformed to standardized scores with the aid of table or formula so that data may be compared.     See also: Standard Score

Size of Class – The extent of a class in a classification or frequency distribution. In the example 16-30 years, 31-35 years, 36-40 years, the sizes of class are: 15 years and 5 years.    See also: Class/Frequency Distribution

Standard Score – Raw scores from different studies cannot in every instance be compared to one another. When it is necessary to do so, they are transformed to standardized scores; for this purpose, transposition formulas or special tables are used. Standard scores have a fixed average and a fixed standard deviation. See also: Standard Deviation/Raw Scores

Table – Systematic classification of data, figures. The purpose is to render these (research) data more accessible (readable).