Written by Coursera Staff • Updated on

Learning how to use interval data correctly can open new types of statistical analysis with variables you encounter in your everyday life. Explore what interval data is, how it differs from ratio data, and how you might see it across industries.

While data types might seem like a topic for statisticians, understanding the type of data you’re working with is important for professionals in every industry. Knowing the features of your data helps you pick the right data analysis method and form the right insights. Interval data, a common data type, represents a type of quantitative data where the difference between two values is meaningful and measurable, and no true zero points exist. Read on to explore what interval data is, what it measures, and how you can apply this type of data in different fields.

**Read more: **What Is a Statistician? Duties, Pay, and How to Become One

Interval data is a type of quantitative data where you measure the values along a scale with equal intervals between data points. In other words, interval data gives us the order of values and also allows us to quantify the difference between them. You can manipulate interval data with addition and subtraction, not multiplication and division.

Temperature is a common example of interval data. If one day the temperature is 50 degrees and the next it is 60 degrees, we can say that the second day was exactly 10 degrees warmer than the first. The same would be true if the temperature were 20 degrees one day and 30 degrees the next. Regardless of the temperature, the difference represented between values stays the same.

In addition to consistent differences, zero on a temperature scale doesn’t mean there is no temperature. Instead, it’s just another point on the scale.

**Read more: **Understanding Different Types of Data

Interval and ratio data both have equal spacing between values, but ratio data has a true zero point. For example, the number of cookies you have would be an example of ratio data. The difference between four and five cookies is the same as between three and four cookies, but zero cookies represent a true absence.

Ratio data are continuous and offer an infinite number of possible values, which can lead to more measurement precision than interval data or other types of data. Ratio data also lends itself to dividing values, while the interval scale makes more sense when subtracting values. For example, with interval data, it would not make sense to say somewhere is “twice as hot” as somewhere else if their temperatures were 35 degrees and 70 degrees. With ratio data, such as the cost of a house, it would make sense to say one house costs twice as much as another.

When you understand the characteristics of interval data, you can make informed choices on how to collect, process, analyze, and interpret your interval data. Some key features that set interval data apart include:

**Distinct order:**Interval data has a definitive order. The order allows us to rank the data points from lowest to highest, such as temperature, responses on a scale, or IQ measure.

**Equal intervals:**This characteristic allows us to order our data points and measure the exact distance between them. This is useful in various statistical analyses, such as calculating the mean of a data set. With equal intervals, we can make precise statements about how much larger or smaller one measurement is compared to another.

**Addition and subtraction are meaningful:**You can make valid mathematical computations like addition and subtraction with interval data. The difference between two data points at any scale level should represent the same difference. If you had an interview question with possible responses of one through ten, the difference between one and three should be the same as between four and seven.

**Multiplication and division are not meaningful:**With this data type, addition and subtraction make sense, while multiplication and division do not. For example, having an IQ score of 120 does not indicate someone is twice as smart as someone with an IQ of 60.

Interval data shows up in many types of everyday information. When you learn to recognize interval data, you can access a new range of information for statistical analysis and insights. Some places you’ll find interval data include areas such as the following.

IQ (intelligence quotient) scores derive from standardized tests measuring human intelligence. Scores are equally spaced, and the difference between scores is the same, regardless of where they fall on the scale. You also do not have a true zero, as an IQ of zero does not mean the absence of intelligence.

Temperature is a common measure in weather forecasts and is typically recorded as interval data. On scales like Celsius or Fahrenheit, the difference between 15 and 20 degrees is the same as between 25 and 30 degrees, but 0 degrees does not imply a complete lack of temperature.

If we consider years of education as a variable (such as five years, 10 years, or 15 years), it is interval data where the difference between various levels is meaningful, although there is no true zero point (zero years of education does not mean an absence of knowledge).

A student’s grade point average and standardized test scores are also interval data, as you have clear intervals and consistent differences between values (2.7 versus 2.8 GPA, 3.5 versus 3.6 GPA), but you don’t have a true zero value.

Marketing researchers can use interval data, particularly in areas like customer satisfaction surveys. For instance, you might treat a five-point or seven-point scale measuring customer opinions as interval data. The distances between points on the scale are equal, enabling researchers to calculate means and standard deviations. However, the scale doesn't have a true zero point, as a satisfaction score of 0 doesn’t necessarily mean the absolute absence of satisfaction.

Time is an example of interval data. Each hour or each year is the same length, and you can add or subtract time units meaningfully to represent differences. You can use this type of interval data in science experiments to measure an experiment's reaction time or length.

Professionals in many industries use interval data, including health, education, science, business, and social sciences. Some ways in which you might see interval data across fields include:

**Science:**Measuring reaction times and material properties such as pH levels**Health:**Measuring biological data such as heart rate or blood pressure**Education:**Measuring GPA and standardized test scores**Business:**Measuring customer satisfaction in market research**Social sciences:**Measuring responses to survey questions

Analyzing interval data involves several steps that help summarize and provide insight into your data. Some ways in which you can do this include:

**Distribution**: You can organize your data using tables or graphs to visualize its distribution. For example, you could use a frequency distribution table showing how often certain values or variables appeared in your data.

**Central tendency**: You can also determine the central tendency of your data. This could be the mode (most frequently repeating value), the median (middle value when data is in ascending order), or the mean (average of all values). If your data is normally distributed without skew, all three measures can provide useful insight.

**Variability**: You can evaluate the spread of your data using the range, interquartile range, standard deviation, and variance. These measures can give you an understanding of the dispersion of your data. You generally want low variability in your data, as it shows your data is more consistent and may lead to more accurate predictions.

You can also use more complex statistical tests to analyze your data set. If your data has a normal distribution, you can apply both parametric and non-parametric tests. If your data is not normally distributed, you can only apply non-parametric tests, such as a chi-squared test. Parametric tests, which are more statistically powerful, allow for more robust conclusions, but your data must meet specific criteria for their use. Common parametric tests for interval data include t-tests, analysis of variance (ANOVA), and regression analysis.

Interval data is a data type characterized by scale-like distributions with equal spacing and no true zero point. You might see this data showing up in your field as temperature measurements, survey answers, or time intervals. With this data, you can perform statistical tests to look at the distribution, central tendency, variation, and more.

To learn more about data types and data analytics, you can take exciting courses offered on the Coursera learning platform by top universities. To start, consider taking highly rated courses such as Foundations: Data, Data, Everywhere by Google. If you want a more comprehensive program, the IBM Data Science Professional Certificate can guide you through in-demand data skills to help you enter an entry-level position.

Updated on

Written by:### Coursera Staff

C

Editorial Team

Coursera’s editorial team is comprised of highly experienced professional editors, writers, and fact...

This content has been made available for informational purposes only. Learners are advised to conduct additional research to ensure that courses and other credentials pursued meet their personal, professional, and financial goals.