You are here: Home Introduction to statistical analysis of biomedical data Types of variables
07 - 11 - 2014
 Save \$25 on orders of \$100+, \$50 on orders of \$150+, and save \$100 on orders of \$250+ by entering code AFF2014 at store.elsevier.com!

## Types of variables

A variable is something which we can measure in an experiment and also manipulate or control. They are classified as dependent (outcome) or independent (predictor) and also as categorical (qualitative) or continuous (quantitative).

Independent (also called as experimental or predictor) variable influences values of studied parameter. In the above-described example, when we compare activity of oils against bacteria of different species, just species is independent variable. Dependent (outcome) variable is influenced by another factor (for example, minimal inhibitory concentration, which is changed depending on species of bacteria).

Categorical (discrete or qualitative) variables are further divided into nominal, dichotomous and ordinal:

1) Nominal variables have two or more categories but do not have an intrinsic order, they can be names, colors and other characteristics which cannot be either graded or compared.

2) Dichotomous variables are in fact subgroup of nominal which has only two categories, for example, gender ‘male’ or ‘female’, or presence of some property of studied object which is expressed in the way ‘present’ or ‘absent’ and can be coded during analysis as ‘0’ and ‘1’.

3) Ordinal variables have two or more levels which already can be compared. For example size of object can be expressed as ‘small’, ‘moderate’ or ‘large’. We can answer the question ‘Which is bigger’ but cannot answer ‘How much bigger’.

Continuous (quantitative) variables include interval and ratio variables.

1) Interval variables can be measured along a continuum and have a numerical value (for example, temperature measured in degrees Celsius or Fahrenheit). The difference between 10°C and 20°C is the same as 30°C to 40°C. We can answer the question ‘Which value is bigger?’. We can also compare differences between the values, but still we cannot answer, by how many times one value is bigger than another. It cannot be done because zero value also indicates some presence of variable; that is, 0°C does not indicate absence of temperature at all.

2) Ratio variables are interval variables but with the condition that zero value indicates that there is none of the variable. In such way values can be compared because present absolute point of comparison. Example of this is a mass or size of an object, we can say that 3 mm are 3 times bigger than 1 mm.

Sometimes one measurement can be transformed to another, such as mass (ratio variable) can be easily transformed to ordinal variable (light, heavy). However, without performing additional measurements such transformation is only possible with reduction of the scale.

blog comments powered by DISQUS back to top
See also...
Most read content
Recently added
 Please do not change this code for a perfect fonctionality of your counter medicine
 All Rights Reserved © Biomedical Statistics | Designed by