Statistic Definitions
The levels of measurement from the lowest to the highest level are nominal, ordinal, interval, and ratio
Variables measured at the nominal level of measurement are at the lowest level and must follow three rules: (1) the data categories must be exhaustive (each datum will fit into at least one category identified by the researcher), (2) the data categories must be exclusive (each datum will fit into only one category), and (3) the data cannot be rank ordered. Nominal data differ from ordinal data in that ordinal data can be rank ordered. Examples of nominal data include gender, ethnicity, marital status, medical diagnoses, and primary language.
Nonparametric or distribution-free analysis techniques can be used to analyze nominal level data to describe variables, examine relationships among variables, and determine differences between groups in distribution-free or non-normally distributed samples. The assumptions of nonparametric statistics are: (1) values from measurement of study variables need not be normally distributed in the sample, and (2) the level of measurement of study variables is usually nominal or ordinal. The mode is the only measure of central tendency that can be calculated for nominal data and is the most frequent occurring value in a data set. Frequencies and percentages are also used to analyze nominal data to describe the study or demographic variables. Chi square is an analysis technique conducted on nominal data to identify relationships and differences in studies.
Ordinal level measurement includes categories that can be rank ordered and also, like nominal level measurement, the categories are mutually exclusive and exhaustive.
In ranking categories of a variable, each category must be recognized as higher or lower or better or worse than another category. However, with ordinal level of measurement, you do not know exactly how much higher or lower one subject's score is in relation to another subject's score on a variable. Thus,
Variables measured at the nominal level of measurement are at the lowest level and must follow three rules: (1) the data categories must be exhaustive (each datum will fit into at least one category identified by the researcher), (2) the data categories must be exclusive (each datum will fit into only one category), and (3) the data cannot be rank ordered. Nominal data differ from ordinal data in that ordinal data can be rank ordered. Examples of nominal data include gender, ethnicity, marital status, medical diagnoses, and primary language.
Nonparametric or distribution-free analysis techniques can be used to analyze nominal level data to describe variables, examine relationships among variables, and determine differences between groups in distribution-free or non-normally distributed samples. The assumptions of nonparametric statistics are: (1) values from measurement of study variables need not be normally distributed in the sample, and (2) the level of measurement of study variables is usually nominal or ordinal. The mode is the only measure of central tendency that can be calculated for nominal data and is the most frequent occurring value in a data set. Frequencies and percentages are also used to analyze nominal data to describe the study or demographic variables. Chi square is an analysis technique conducted on nominal data to identify relationships and differences in studies.
Ordinal level measurement includes categories that can be rank ordered and also, like nominal level measurement, the categories are mutually exclusive and exhaustive.
In ranking categories of a variable, each category must be recognized as higher or lower or better or worse than another category. However, with ordinal level of measurement, you do not know exactly how much higher or lower one subject's score is in relation to another subject's score on a variable. Thus,