Independent vs Dependent Variables: Definitions, Examples and Real Data

Home › Research Methodology › Independent vs Dependent Variables

Quick answerAn independent variable is the thing you change, choose or compare. A dependent variable is the result you measure to see whether it changes. In the question “Does fertiliser increase crop yield?”, the amount of fertiliser is the independent variable and the crop yield is the dependent variable.

A simple way to remember it: the dependent variable depends on the independent variable. If you can say “Y changes because of X”, then X is independent and Y is dependent.

Independent vs dependent variable at a glance

Independent variable Dependent variable
What it is The thing you change, choose or compare The result you measure
Question to ask What am I changing or comparing? What am I measuring?
Also called Explanatory variable, predictor, factor, X Response variable, outcome, Y
On a graph Usually the horizontal (x) axis Usually the vertical (y) axis
Simple example Hours spent studying Exam score

Example: independent and dependent variables in ScholarsColab’s data

To explain these two variables, we take an example from ScholarsColab’s own data: 41,792 papers, mostly published between 1998 and 2026, by 967 ScholarsColab mentors (data updated 15 October 2026). We will ask one simple question of this data and find the independent and dependent variables step by step.

Step 1
Ask a question. Researchers publish different kinds of papers. Some report a new study (original research); others summarise many earlier studies (review articles). When another researcher mentions a paper in their own work, that is a citation. So we ask: do review articles get more citations than original research papers?

Step 2
Find the independent variable: what are we comparing? We are comparing two kinds of paper. So the type of paper is the independent variable. It has two values, or levels: review article and original research.

Step 3
Find the dependent variable: what are we measuring? For each paper we count how many times it has been cited. So the number of citations is the dependent variable. It is the result that may change depending on the type of paper.

Type of paperindependent variable
→
Number of citationsdependent variable

Step 4
Look at the result. Each bar below is one level of the independent variable (one type of paper). The length of each bar is the dependent variable (the typical number of citations).

Median citations by type of paperOriginal research620,930 papersReview articles13980 papers
Median citations per paper, by type of paper. Papers published 2010–2022 by ScholarsColab mentors; type identified from the title. Source: ScholarsColab Research Methods Index.

Among 22,045 papers published between 2010 and 2022, review articles received a median of 13 citations, compared with 6 for original research papers: about 2.2× as many. In other words, when the independent variable changes (from original research to review), the dependent variable changes too.

We show the median, the middle value, because a few very famous papers would make a simple average misleading.

Other variables in the same example

Once you know your independent and dependent variables, the next question is: could anything else change the dependent variable? In our example, the number of citations is the dependent variable, so we ask what else could change how often a paper is cited.

One answer is easy to see: time. A paper published ten years ago has had ten years to be cited; a paper published last month has hardly had any. If we compared old reviews with new research papers, we would be unfair to the new papers. So in Step 4 we only compared papers published in the same years. Keeping something the same like this makes it a control variable.

Median citations by publication period2010–201484,574 papers2015–201866,260 papers2019–202177,468 papers2022–2024312,817 papers2025–202605,843 papers
Median citations per paper, by when it was published. Older papers have had more time to collect citations. Source: ScholarsColab Research Methods Index.
Papers from 2010–2014 have a median of 8 citations, while papers from 2025–2026 have 0. Newer papers have simply had less time to be cited.

Here is how the other common types of variables fit into the same example:

Type of variable What it means In our citation example
Independent What you change or compare Type of paper
Dependent What you measure Number of citations
Control Kept the same so it cannot affect the result Publication years (we compared papers from the same years)
Confounding Something that is not controlled and could mislead you Paper age, if we had not kept the years the same
Moderator Changes how strong the effect is Research field: the difference between reviews and original papers is larger in some fields than others
Mediator Explains why the effect happens How many people read a paper: reviews may be cited more because more people read them

You do not need all of these in every study. Every study has at least one independent and one dependent variable; the others help you make the comparison fair and explain the result. Moderators and mediators are explained in our guide to mediator vs moderator variables.

Spotting variables in real research titles

Many research titles follow the pattern “Effect of X on Y”. Whenever you see it, X is the independent variable and Y is the dependent variable. Here are real examples from papers published by our mentors (the selection changes every day):

Published paperIndependent variableDependent variable
The effect of board the size and audit committee the size on earnings management in Nigerian consumer industries companies
Rabiu Saminu Jibril		board the size and audit committee the sizeearnings management
Influence of stainless steel surface properties on whey protein fouling under industrial processing conditions
Prof. Maude Jimenez		stainless steel surface propertieswhey protein fouling
Effect of ohmic heating on food products: An in‐depth review approach associated with quality attributes
Dr. Ajay Singh		ohmic heatingfood products
Effect of Branding on Consumer Buying Behaviour at Vijay Bharat Motors Pvt Ltd, Bidar
Dr Bhadrappa Haralayya		BrandingConsumer Buying Behaviour
Impact of salinity on mangroves
ABHIJIT MITRA		salinitymangroves
Influence of emotional intelligence and locus of control on academic achievement of underachieving high ability students
Fagbemi Olusegun Olujide		emotional intelligence and locus of controlacademic achievement
Effect of deposition strategy and post processing on microstructure and mechanical properties of serviced Inconel 625 parts repaired using laser directed energy deposition
Vamsi Krishna Balla		deposition strategy and post processingmicrostructure and mechanical properties
Evaluation of the effect of methotrexate on the hippocampus, cerebellum, liver, and kidneys of adult male albino rat: Histopathological, immunohistochemical and biochemical studies
Mohamed El-Sakhawy		methotrexatehippocampus, cerebellum, liver, and kidneys

How to identify the variables in your own study

  1. State your research question as one sentence, ideally in the form “Does X affect Y?” (for example, “Does curing temperature affect the strength of concrete?”).
  2. Find what you change, choose or compare. That is your independent variable (curing temperature).
  3. Find what you measure. That is your dependent variable (concrete strength). Decide exactly how you will measure it.
  4. List anything else that could change your result (cement type, curing time, humidity) and keep these the same as control variables.
  5. Check the direction. Make sure Y could not just as easily be causing X.
Field Independent variable Dependent variable
Civil engineering Curing temperature Strength of concrete
Medicine Dose of a blood-pressure drug Blood pressure after eight weeks
Computer science Size of the training dataset Accuracy of the model
Management Hours of employee training Productivity per employee
Psychology Hours of sleep before a test Memory test score
Agriculture Amount of fertiliser Wheat yield per hectare

Common mistakes reviewers point out

  • Confusing a variable with its levels. “Type of paper” is the variable; “review” and “original research” are its levels.
  • Reversing the direction. Saying X affects Y when Y could just as easily affect X.
  • A dependent variable that cannot be measured reliably, or is measured differently in different groups.
  • Forgetting other things that could change the result, like paper age in our example.
  • Claiming cause and effect too quickly. Our example shows reviews tend to be cited more; it does not prove that being a review is the reason. Proving a cause usually needs an experiment.

Frequently asked questions

What is an independent variable?

It is the thing a researcher changes, chooses or compares to see whether it has an effect, such as the dose of a drug or the type of paper. It is also called the explanatory variable or predictor.

What is a dependent variable?

It is the result a researcher measures to see whether it changes with the independent variable, such as blood pressure or the number of citations. It is also called the response or outcome variable.

Are explanatory and response variables the same as independent and dependent variables?

Yes, in practice. “Explanatory variable” is another name for the independent variable and “response variable” is another name for the dependent variable. The explanatory and response terms are common in statistics.

Can a study have more than one independent or dependent variable?

Yes. Many studies compare several factors at once, or measure several results, for example the effect of fertiliser and irrigation on both yield and grain quality.

What is the difference between an independent variable and a control variable?

The independent variable is what you deliberately compare. A control variable is something you keep the same, so that it cannot affect the comparison.

Is the independent variable always the cause?

No. In experiments, where the researcher sets the independent variable, a cause can often be shown. In studies that only observe, like our citation example, the independent variable is only a possible cause.

Use this data in your own work

Use this data in your own research. Download the aggregated figures behind these charts (counts, medians and shares by type of paper, period, method and discipline) as a CSV file. Please cite it as:ScholarsColab (2026). ScholarsColab Research Methods Index [Data set]. Vidhilekha Soft Solutions Pvt Ltd. Retrieved 15 October 2026, from https://scholarscolab.in/research-methodology/. Licensed under CC BY 4.0.Download the data (CSV) →

Need help applying this to your research?

Discuss your research problem with a PhD mentor, hand the whole project to a research project manager, or post your project and let matched experts apply.

Hire a Research Project Manager Hire Experts Browse Mentor Profiles

Mentors whose published work uses this approach:

More research methodology guides

About the data on this page. The ScholarsColab Research Methods Index is built from the Google Scholar publication lists of PhD researchers who mentor on ScholarsColab, and is updated daily as mentors and publications are added. Methods, designs and paper types are identified from titles, so papers whose titles do not mention them are not counted in those groups. The mentors are not a random sample of all researchers (engineering and computer science are strongly represented), so the figures describe this group of researchers and may not apply to research as a whole.