Interval data is quantitative data measured along a scale. By discussing its definition, characteristics etc., we will have a better understanding of where and how to use interval data

In market research or any other form of social, economic or educational research, researchers demand data types which support most statistical tests and transformation. This demand is made to ease analysis and arrive at a correct conclusion. 

When studying data types, we discover that interval data is compatible with most statistical tests. It has distinct attributes which make it more in-demand compared to its counterparts – nominal data, ordinal data and ratio data. 

What is Interval Data?

Interval data is a type of data which is measured along a scale, in which each point is placed at an equal distance (interval) from one another. Interval data is one of the two types of discrete data. An example of interval data is the data collected on a thermometer—its gradation or markings are equidistant. 

Unlike ordinal data, interval data always take numerical values where the distance between two points on the scale is standardised and equal. Also, arithmetic operations can be performed on interval data. 

However, these operations are limited to addition and subtraction.

What are Characteristics of Interval Data 

Here are some of the characteristics of interval data:

• Quantitativeness:

Interval data is one of the two types of numerical data. Therefore, it is parametric or quantitative. Sometimes called integer,interval data not only takes quantitative value but also perform the operations of an integer. It is quite different from categorical data (nominal & ordinal data) which takes numeric value but exhibit qualitative character. 

• Arithmetic Operation

One can perform arithmetic operations like addition and subtraction on interval data. However, interval data cannot be multiplied or divided. True to its quantitative character, almost all statistical analysis is applicable when calculating interval data. This includes, but not limited to mean, mode and median.

• Measurement Scale

Interval data is measured using an interval scale, which not only shows the order but also shows the exact difference in the value. It is different from ordinal data which only shows order and direction, with no standardised difference on each variable in the scale. 

Let us consider a ruler for instance, the difference between markings or gradings on a ruler are equal. This is an interval scale.

• Interval Difference:

The difference between each interval are equal. For example, the difference between 10° and 20° on a thermometer is the same as the difference between 20° and 30°.

• Negative Reading:

In an interval scale, a variable can be measured even if it is negative. Since an integer takes both positive and negative value, the interval scale also reads negative values. 

For example, when reading the temperature of a place during winter, we can have a temperature as low as -10 degree Celsius. However, there are no zero points. 

Interval Data Collection Technique

There are different techniques for collecting interval data. Techniques used by a researcher is influenced by the target audience, data usage and the person collecting the data. Technique used in collecting interval data includes; observation, interviews, document review, surveys and probability sampling.

• Observation

This is a data collection technique where researchers make systematic observations through counting. This may include counting the number of people present at a particular event at a specific time and a specific venue or number of people attending the event in a designated venue. There are two different observation approaches, namely; naturalistic and standardised approach. 

• Interviews

Respondents are interviewed to collect data from them. Unlike random interviews where people sometimes swerve from the topic at hand, this interview is structured with researchers asking a standardised set of questions and nothing other than that. Some of the interview techniques used are face-to-face interviews, telephone interviews and computer-assisted personal interviews. 

• Surveys & Questionnaire

This may be created using online form builders like Formplus. Also used to collect qualitative data, surveys are designed to gain trust and improve the experience of respondents. There are two major types of online questionnaires, namely; web-based questionnaire and an online questionnaire.

Read Also: Ultimate Guide to Data Collection Methods & Tools For Research

• Document Review:

This is a data collection technique which involves reviewing existing documents. It is a very good technique, as it gives researchers access to past and present data. 

Three primary document types are being analyzed for collecting supporting quantitative research data. They are; personal documents, physical evidence and public records. 

• Probability Sampling:

This is a technique that involves carrying out random selection which enables researchers to make probable conclusions based on the collected data. There are three major types of probability sampling, namely; simple random sampling, systematic random sampling and stratified random sampling. 

What are the Examples of Interval Data? 

Examples of interval data includes temperature (in Celsius or Fahrenheit), mark grading, IQ test and CGPA. These interval data examples are measured with equal intervals in their respective scales. Interval data are often used for statistical research, school grading, scientific studies and probability.

• Temperature

When measuring temperature in Celsius or Fahrenheit, it is considered interval data because 0 is arbitrary. That is, 0°C and 0°F cannot be read on the thermometer. 

However, this is not the case when measured in Kelvin. There can’t be a temperature below zero degrees in Kelvin because, for Kelvin, 0 is absolute. 

• Mark Grading

When grading test scores like the SAT, for example, the numbers from 0 to 200 are not used when scaling the raw score to the section score. In this case, absolute zero is not used as a reference point. Therefore, it is an interval data. 

• Time

Time passes as a good example of interval data if measured during the day or using a 12-hour clock. The numbers on a wall clock are on an interval scale since they are equidistant and measurable. For example, the difference between 1 o’clock and 2 o’clock is the same as that between 2 o’clock and 3 o’clock.

• IQ Test

According to psychological studies, one can not have zero IQ. Also, IQ is determined using a fixed measurement scale. Therefore, IQ is an example of interval data. 

• CGPA

This represents a student’s Grade Point Average in his/her studies over a set period e.g. one semester. The mean of the GPA is used to find the CGPA of a student over a longer period e.g. two sessions. The intervals in the CGPA are also equidistant, making it an interval data example. 

Categories of Interval Variables

Interval variable is the difference between two data values that gives credible meaning. interval variable examples in timing is when the difference in one pm to two pm is the same as three pm to four pm.Interval variable is a subcategory of a numerical or continuous variable. Hence, interval data variables can similarly be categorised based on their distribution. 

Normal Distribution 

This is also known as Gaussian distribution. It is used to represent real-valued random variables whose distributions are not known. 

These variables may be classified into matched and unmatched samples. 

Matched Sample 

Matched samples are variable samples in which each member of a sample is matched with a corresponding member in every other sample by reference to qualities other than those immediately under investigation. The tests carried out on this sample include; paired t-test and repeated measures ANOVA.

Tests

• Paired t-test: This is used to compare two sample population means, where both samples consist of the same test subject. 
• Repeated measures ANOVA: This compares means across three or more variables, based on repeated observations. 

Unmatched Sample

Unmatched samples, sometimes called independent samples are samples in which each member is randomly selected. The tests carried out on this sample include; unpaired t-test and ANOVA.

Tests

• Unpaired t-test: This is used to compare two sample population means, where both samples consist of distinct test subjects.
• ANOVA: This compares means across three or more variables, based on a single observation. 

Non-Gaussian Distribution

This is also known as Non-Normal distribution. It is used to represent real-valued random variables whose distributions are known.

Like in Normal distribution, these variables may be classified into matched and unmatched samples.

Matched Sample

The tests carried out on matched samples include; Wilcoxon rank-sum test and Friedman 2-way ANOVA. 

Tests

• Wilcoxon rank-sum test: This is a non-parametric test used to compare two groups of matched samples. It is also called the Wilcoxon signed-rank test. 
• Friedman 2-way ANOVA: This is a non-parametric test used to compare the difference in means across 3 or more groups. 

Unmatched Sample

The tests carried out on unmatched samples include; Wilcoxon rank-sum test and Kruskal-Wallis test. 

Tests

• Wilcoxon rank-sum test: This test is used when the requirements for the t-test of two unmatched samples are not satisfied. However, it may only be used provided the two independent samples are drawn from populations with a non-gaussian distribution. 
• Kruskal-Wallis test: This is used to investigate whether three or more groups of unmatched samples originate from the same distribution. It is sometimes called one way ANOVA. 

How to Analyse & Interpret Interval Data 

Interval data can be interpreted using the two main statistical methods of analysis, namely; descriptive and inferential statistics. The interval data analysis method used depends on the nature of the investigation being carried out. 

Descriptive Statistics

This is the type of statistics used to describe a sample population using data sets collected from that population. Descriptive statistical methods used in analysing interval data include:

• Mean: This measures the average of the interval data sample provided. 
• Median: This is used to determine which variable in the data set is at the centre. It is easily calculated because interval data is equidistant. 
• Standard deviation: This illustrates the spread of data relative to the mean.
• Variance: It is used to illustrate how much of a spread exists in the data.

Inferential Statistics

This is used to make predictions or inference on a large population-based on the data collected from a sample population. In some cases, the inference is based on time and not the population as stated earlier. Below are some of the methods used for analysing interval data. 

• Trend analysis

Trend analysis is an interval data analysis technique, used to draw trends and insights by capturing survey data over a certain period. It is conducted by studying the trend for a certain period, then analysing it to infer what it is going to look like in the future. 

• SWOT analysis

This is mostly used by organisations or businesses to evaluate their current performance in the market and develop effective business strategies for the future. SWOT is an acronym for Strengths, Weaknesses, Opportunities and Threats. Strengths and Weaknesses are for internal analysis, while Opportunities and Threats are for external analysis of an organisation. 

• Conjoint analysis

This is a market research analysis technique that investigates how people make choices. It factors in all the underlying factors involved in the decision-making process. For example, when deciding on which phone to buy, a customer may consider price, camera quality, beauty, colour etc. 

• TURF analysis

This is an acronym for Total Unduplicated Reach and Frequency analysis, and is used to assess the market potential for a combination of products or services.  

Uses of Interval Data 

• Marketing & Advertising

Before engaging in any marketing or advertising campaign, companies need to first analyse some internal and external factors that may affect the campaign. In most cases, they use a SWOT analysis.

Here, the internal factors are Strength and Weakness, while the external factors are Opportunities and Threats. This analysis technique is also used when a new company wants to enter the market afresh. 

• Product Development

During the product development stage, researchers use TURF analysis to investigate whether a new product or service will be well-received in the target market or not. For example, if a software company decides to add a new feature to their product, it is important to know whether their new and existing users will like it. 

• Education

Interval data is used in the education sector to compute the grading system. When calculating the Cumulative Grade Point Average of a student, the examiner uses an interval data of the student’s scores in the various courses offered. 

This is similarly used for SAT, IQ tests and even competency test during job applications. 

• Medicine

Doctors use the thermometer to measure a patient’s body temperature as part of a medical check-up. In most cases, body temperature is measured in Celsius, therefore passing as interval data. 

Disadvantages of Interval Data 

• Information gathered from interval data are limited as they provide quantitative descriptions. These descriptions are not narrative and generally provide less elaborate accounts of human perception.
• The use of standard questions by researchers may lead to bias and false representation, where the data reflects their view instead of the participating subject. This is the case with IQ tests, SAT and other similar interval data examples. 
• Compared to nominal data, it collects a much narrower dataset.

What Is The Best Tool For Collecting Interval Data? 

Formplus is a web-based form builder software which is the best tool for collecting interval data. Interval data can be best collected through a tool that creates a seamless experience for the researcher and participants. 

With a platform that integrates all the data collection and analysis techniques, businesses or organisations can easily collect data from respondents (e.g. customers) and analyse them on the go. Formplus helps ease business research processes with its rich features. 

Why Use Formplus to Collect Interval Data? 

• Choice Options

Formplus forms give users access to different choice options, namely; radio choice, image choice, checkboxes and single select. Researchers have the flexibility to use one or all of these choice options for interval data collection. 

• Scale Rating

When assessing the extent to which an event happened, scale rating helps Formplus users easily take records. This scale may be used to evaluate product performance, employee skill level, customer service performances etc. for a particular purpose. 

• Matric Ratings

Formplus has unique features that like matrix ratings, which assign weights to each answer choice. This feature makes it easy for researchers to collect answers to multiple questions from respondents at a go

• Mobile-Friendly Forms

With Formplus, it doesn’t matter whether your respondents are filling the form using a computer or mobile phone, they both have access to the same features. Formplus forms equally ideal user experience across any device. 

• Export Data as PDF or CSV

Formplus gives you the freedom to choose how you want your interval data to be collected. You can either choose to export interval data as PDF or CSV format, depending on the purpose of data collection. 

• Storage & Security

Be assured of the safety of the data collected through Formplus forms. Formplus stores interval data in a secure database, using end to end encryption. You can choose from the different available storage options without trading data security for any option chosen. 



Conclusion

Interval data is one of the most used data types due to its compatibility with most statistical tests. It has distinct features, setting it aside from other data types.

Unlike nominal and ordinal data, interval data is a type of numeric data which not only allows for ordering of variables but also provides a precise, quantifiable understanding of the intervals between them. Therefore, satisfying the three properties of identity, magnitude, and equal intervals.

This allows for a broader study, involving a greater number of subjects, and enhancing the generalisation of the results.