The term binary data has various meanings in different technical fields. In general, it refers to a unit of data which can take on only two possible values, traditionally termed 0 and 1 in accordance with the binary numeral system. Related concepts in various fields are *logical value (or "truth value") in logic, which represents the truth or falsehood of a logical proposition
In statistics
In statistics, binary data is a statistical data type described by binary variables, which can take only two possible values. Binary data is used to represent the outcomes of Bernoulli trials, statistical experiments with only two possible outcomes. It is a type of categorical data, which more generally represents experiments with a fixed number of possible outcomes. The two values in a binary variable, despite being coded numerically as 0 and 1, are generally considered to exist on a nominal scale, meaning that they represent qualitatively different values that cannot be compared numerically. In this respect, also, binary data is similar to categorical data but distinct from count data or other types of numeric data. Often, binary data is used to represent one of two conceptually opposed values, e.g.
- the outcome of an experiment ("success" or "failure")
- the response to a yes-no question ("yes" or "no")
- presence or absence of some feature ("is present" or "is not present")
- the truth or falsehood of a proposition ("true" or "false", "correct" or "incorrect")
However, it can also be used for data that is assumed to have only two possible values, even if they are not conceptually opposed or conceptually represent all possible values in the space. For example, binary data is often used to represent the party choices of voters in elections in the United States, i.e. Republican or Democratic. In this case, there is no inherent reason why only two political parties should exist, and indeed, other parties do exist in the U.S., but they are so minor that they are generally simply ignored.
Binary variables that are random variables are distributed according to a Bernoulli distribution. Regression analysis on predicted outcomes that are binary variables is accomplished through logistic regression, probit regression or a related type of discrete choice model.
In computer science
In modern computers, almost all data is ultimately represented in binary form, and the entire architecture of the modern computer is built on the binary numeral system. On a basic level, then, binary data can refer to any data represented directly in binary form rather than interpreted on a higher level or converted into some other form.
Nonetheless, in applied computer science and in the information technology field, the term binary data is often specifically opposed to text-based data, referring to any sort of data that cannot be interpreted as text. The "text" vs. "binary" distinction can sometimes refer to the semantic content of a file (e.g. a written document vs. a digital image). However, it often refers specifically to whether the individual bytes of a file are interpretable as text (usually ASCII or Unicode) or cannot so be interpreted. When this last meaning is intended, the more specific terms binary format and text(ual) format are sometimes used. Note that semantically textual data can be represented in binary format (e.g. when compressed or in certain formats that intermix various sorts of formatting codes, as in the DOC format used by Microsoft Word); contrarily, image data is sometimes represented in textual format (e.g. the X PixMap image format used in the X Window System).
See also
