Biserial correlation is a statistical measure used to identify linear correlation between continuous and dichotomous variables. The word "biserial" is pronounced /baɪ'sɪrɪəl/, with the emphasis on the first syllable. The "bi-" prefix signifies two, while "serial" comes from the word "series", which denotes a sequence or succession. Thus, the term refers to the correlation between two types of variables that are arranged in a series, i.e., continuous and dichotomous. This method is commonly used in research studies and data analysis to determine the strength and direction of the relationship between these two types of variables.
Biserial correlation is a statistical measure that assesses the strength and direction of the relationship between two variables, one of which is continuous and the other dichotomous. It quantifies the linear association between the dichotomous variable and the ranks of the continuous variable. The biserial correlation coefficient ranges from -1 to 1, where -1 indicates a perfect negative correlation, 1 indicates a perfect positive correlation, and 0 indicates no correlation.
To calculate biserial correlation, the data is divided into two groups based on the dichotomous variable. Then, the ranks of the continuous variable are assigned to each group. The correlation coefficient is obtained by applying the usual formula for calculating the correlation between two variables. However, it is important to note that the biserial correlation assumes that the continuous variable follows a normal distribution.
Biserial correlation is commonly used in research fields such as psychology, education, and social sciences when one variable is dichotomous, for example, gender or presence/absence of a trait, and the other variable is on a continuous scale, such as intelligence scores or test performance. It is useful in evaluating the strength of association between these types of variables and can provide insights into the relationship and predictive power of the dichotomous variable on the continuous variable.
The word "biserial" comes from the Latin prefix "bi-" meaning "two" and "serial" meaning "in a series" or "in a sequence".
The word "correlation" derives from the Latin word "correlatio" which combines "cor-" meaning "together" and "relatio" meaning "relation" or "relationship".
When combined, "biserial correlation" refers to the statistical measure that quantifies the relationship between a continuous (quantitative) variable and a binary (categorical) variable.