PERRLA/Guides/MLA 9/Data set

How to Cite a Data Set in MLA 9

An MLA 9 Works Cited entry for a data set gives the author (the researchers or the agency), the data set's title in quotation marks and title case, the repository or website that holds it (like ICPSR or Dryad) in italics, the version, the date, and the DOI or URL. You can end with the words Data set. The in-text citation is the author's last name: (Hummer et al.).

The format

Last Name, First Name, et al. "Title of the Data Set." Repository or Website, version #, Day Mon. Year, https://doi.org/xxxx. Data set.

First, the easy way: PERRLA

Choose Datasets, then A published dataset. Add each person as an Author, or the agency as a Group Author (Organization). Type the title in Title of the Dataset and the version, like Version 26, in Version Information. The Publication Year box also takes a full date: type the version's date, like 3/3/2026, and PERRLA writes it 3 Mar. 2026. Put the repository or website, like ICPSR or Dryad, in Publishers and paste the DOI or URL. Using a database that keeps changing? Fill in Retrieval Date, and PERRLA adds Accessed and the date at the end. PERRLA puts the title in title case, names the first author and et al. for three or more, adds Data set. at the end, and leaves the author out when it matches the publisher.

Have a DOI? PERRLA's reference search reads data set DOIs, like the ones ICPSR and Dryad give, and fills in the authors, the title, the version, the publisher, and the DOI. Check four things before you save: add the month and day of the version you used (the search fills the year only), add the periods after middle initials, put the repository's short name in Publishers (ICPSR, not its full name), and fix the version line. For ICPSR, change it to Version 26; for Dryad, clear it, since the number the search fills is Dryad's internal one, not a version the page shows.

For data that were never published, pick Unpublished raw data. The form switches to Collection Year and Data Source, and PERRLA ends the entry with unpublished raw data. Data you collected yourself is a different case: MLA describes it in your paper instead of the Works Cited list.

Not using PERRLA yet? Here is how to build the same works cited entry by hand.

The parts of the works cited entry

1. Author

The author is whoever created the data: the principal investigators of a study, or the agency that runs a survey or database. Start with the first person's last name, a comma, and their first name, then et al. if there are three or more. Spell out an agency's full name.

Hummer, Robert A., et al.

When a government agency is several layers deep, name the most specific one as the author, like the National Center for Health Statistics rather than the Department of Health and Human Services. If the same organization created and published the data, skip the author and start with the title: MLA names it once.

2. Title

A data set you found in a repository or on a website is a work inside a container, so its title goes in quotation marks and title case, with the period inside the closing quotation mark. The MLA Handbook's own data set example does it this way. Keep years, acronyms, and bracketed parts that belong to the title.

"National Longitudinal Study of Adolescent to Adult Health (Add Health), 1994–2025 [Public Use]."

No title? Write a short description in plain type in its place, like Survey responses on sleep quality among night-shift nurses.

3. Repository or website

The repository or website that holds the data, like ICPSR or Dryad, is the container. Its name goes in italics, followed by a comma. MLA doesn't count a repository as a publisher, so it goes here, as the container.

ICPSR,

If you downloaded the data from the organization's own website, and the site's name is the organization's name, name it once: the site's name in italics as the container, with no separate publisher.

4. Version

Archives like ICPSR release new versions of a data set, and each one can change the numbers. Give the version you used, after the container, in lowercase: version and the number, then a comma.

version 26,

No version shown? Leave it out.

5. Date

Give the date the version you used was released, as fully as the source gives it, written day, month, year, with the month abbreviated (except May, June, and July). That's often not the year the study began or the years the data cover: Add Health began in 1994, the data run to 2025, and Version 26 came out on 3 March 2026.

3 Mar. 2026,

6. DOI or URL

End with the DOI as a full https://doi.org/ link when the data set has one, followed by a period. Without a DOI, give the URL of the page where the reader gets the data, without https://.

https://doi.org/10.3886/ICPSR21600.v26.

For a database that keeps changing, like a provisional mortality file that adds records every week, add Accessed and the date you used it after the URL.

7. Data set label

MLA lets you end an entry with a word that says what kind of work it is, when the title doesn't make that clear. For data, write Data set and a period.

Data set.

Examples

A data set from ICPSR with a version and DOI

Add Health, the national study that has followed a cohort of U.S. adolescents into midlife, on ICPSR. The study has four principal investigators and a numbered version. The date is the Version Date of Version 26, not the year the study first went up.

  • In-text citation(Hummer et al.)
  • Narrative citationHummer et al.'s Add Health data show that …

A data set posted to a repository with a DOI

The data from a randomized controlled trial of a virtual reality mindfulness program for nurse managers, posted to the Dryad repository on 29 October 2025. Dryad lists ten authors, so the entry names the first and et al.

  • In-text citation(Steinberg et al.)
  • Narrative citationThe trial data Steinberg et al. posted show that …

In-text citations

An MLA 9 in-text citation for a data set is the first thing in the Works Cited entry, usually the author's name. Data sets have no page numbers, so there's no number to add, and MLA never adds the year.

  • Researchers as authors: one or two last names, or the first name and et al. for three or more: (Hummer et al.), (Steinberg et al.)
  • An agency as author: the name, shortened in parentheses to its first noun phrase if it's long: (National Center) for the National Center for Health Statistics. Name it in full in your sentence.
  • Name in your sentence: leave the parentheses off: Hummer and his colleagues' Add Health data follow a national cohort of adolescents into midlife.

To point to a specific table, variable, or query, name it in your sentence. MLA doesn't use APA's bracketed abbreviation, (National Center for Health Statistics [NCHS], 2026).

Common mistakes

  • (Hummer et al., 2026)(Hummer et al.)That's APA. MLA in-text citations give the name, not the year, and a data set has no page to add.
  • Hummer, R. A., Aiello, A. E., Harris, K. M., & Udry, J. R. (2026).Hummer, Robert A., et al.MLA spells out the first author's first name, uses et al. for three or more authors, and moves the date after the container.
  • ICPSR, version 26, 2008,ICPSR, version 26, 3 Mar. 2026,Use the date of the version you used. Add Health first went up on ICPSR in 2008, and that year is still in its DOI record, so generators often print it.
  • Steinberg, Beth, et al. Data Related to a Randomized Controlled Trial …Steinberg, Beth, et al. "Data Related to a Randomized Controlled Trial …"A data set in a repository is a work inside a container, so MLA puts its title in quotation marks, as the MLA Handbook's own data set example does. The repository's name goes in italics, as the container.
  • Citing the data set for a statistic you read in a reportCiting the report, article, or webpage where you read the statisticCite a data set when you worked with the data yourself. A number you read in a published source comes from that source.

Quick checklist

  • Cite the data set only if you worked with the data yourself
  • Author inverted, full first name, et al. for three or more
  • Title in quotation marks and title case
  • The repository or website in italics, then the version
  • The date of the version you used, day, month, year
  • DOI as a https://doi.org/ link, or the URL, then Data set.

Questions students ask

Do I cite the data set or the article that reported it?

If you downloaded the data and ran your own analysis, cite the data set. If you are using a number someone else reported, cite the article, report, or webpage where you found it. A paper can cite both: the data set you analyzed and the articles that used it before you.

How do I cite data I collected myself in MLA?

You don't make a Works Cited entry for it. MLA asks you to explain in the paper how you collected the data, like how you sent out a survey and sorted the answers, and to share the survey itself in an appendix or a link if you can.

How do I cite the results of a database query, like one from CDC WONDER?

If what you're citing is the results of your own custom query, MLA says you don't need a Works Cited entry for them: describe your query terms in your text or a note, and share the resulting table if you can. If you're citing a published report or data set behind the query, cite that source instead.

How do I cite a single table from a big data set?

Usually you cite the data set or report the table comes from, and name the table in your sentence. When a separate entry is more practical, MLA lets you give the table its own: the table's title in quotation marks, then the data set or report it belongs to in italics, as the container.

Do I need an access date for a data set?

Usually not. A versioned data set with a DOI, or a final annual release, stays the same. Add Accessed and the date when the data are designed to change, like a provisional database that adds new records, or when there's no date at all.

Is it data set or dataset?

Either spelling is common, and MLA's own advice uses data set as two words, so this page does too. Keep a repository's own spelling when it's part of a title.

Rules checked against the MLA Handbook (9th ed.), chapters 5 and 6 (the core elements, containers, optional elements, and in-text citations), and the MLA Style Center's answers on citing raw and published data (data you collected yourself is described in the text; a published data center takes an italic title and its website as the container; the results of a custom query need no Works Cited entry; a website whose name matches the publisher is named once, as the container), on citing a data table, on a work in a digital repository (the repository is a container), on repositories as publishers (they have none), and on access dates; and the MLA Handbook's appendix example of a data set published separately (title in quotation marks, repository in italics). Example sources verified on October 29, 2026: the Add Health authors, title, and Version 26 date (3 Mar. 2026) against the DataCite record for its DOI and the archive's listing (ICPSR's own page blocks automated requests), and the Dryad data set against DataCite and the Dryad API (ten authors, published 29 Oct. 2025).

PERRLA builds the data set entry from its DOI or your details, with the title in quotation marks, the repository in italics, and Data set added at the end.

Try PERRLA free for 7 days