Site icon Codanics

Median to Mean and SD Converter for Meta-Analysis

Meta-Analysis Data Converter: free online tool by Codanics that runs in your browser
Systematic review & meta-analysis

Meta-Analysis Data Converter: Median and IQR to Mean and SD, SE, CI and Combined Groups

Papers rarely report data the way a meta-analysis needs it. Convert medians with quartiles or ranges into means and SDs (Luo 2018, Wan 2014, Shi 2020), standard errors and confidence intervals into SDs, p-values or t into the SD of a mean difference, ratio CIs into log SEs, and combine subgroups into one arm with the Cochrane formula. Do one study or a whole extraction sheet at once.

✅ No login needed100% freeRuns in your browserYour data stays on your device
Meta-Analysis Data Converter✅ Free · no login📚 Cite this tool
Your data never leaves your PC. Your data is analysed on your own computer or phone, even when you upload a CSV or Excel file. Nothing is uploaded, stored or seen by Codanics, and no login is needed.

Fill in what the paper reports. Leave a box empty if it is not given: median + quartiles, median + min/max, or all five.

  • PriceFree, no login or sign-up needed
  • Your dataProcessed in your browser, never uploaded
  • Works onPhone, tablet or computer, any modern browser
  • Made byDr. Muhammad Aammar Tufail, Codanics
  • Published17 November 2026
  • Last updated16 November 2026

📚 How to cite this tool

This tool is free. If it helped your thesis, paper, report or assignment, please cite it. It keeps the tools free and helps other students find them.

Citation · APA 7th edition

Tufail, M. A. (2026). Meta-analysis data converter: median, IQR and range to mean and SD, SE, CI and combined groups [Online tool]. Codanics. Retrieved 16 November 2026, from https://codanics.com/tools/meta-analysis-data-converter/

In-text citation: (Tufail, 2026) · Narrative: Tufail (2026)

The access date is today’s date, filled in automatically. Author: Muhammad Aammar Tufail. Published 17 November 2026.

🚀 Follow Codanics channel on WhatsApp for more updatesNew free tools, scholarships, PhD positions and research tips, straight to your phone. Free lessons on YouTube too.

How to use the meta-analysis data converter

  1. Pick the tab that matches what the paper reports: median with quartiles or range, SE or CI, a p-value or t, a ratio with CI, subgroups to merge, or change-from-baseline data.
  2. Type the numbers. In the median tab leave missing values empty: the tool detects whether you have quartiles (S2), the range (S1) or all five numbers (S3).
  3. Keep the recommended methods (Luo for the mean, Shi for the SD) unless your protocol says otherwise, and read the skewness warning if one appears.
  4. For a whole extraction sheet use Batch: paste from Excel or upload a CSV/Excel file, then download the means and SDs as CSV.
  5. Copy the results and the methods sentence into your extraction form and your paper, then pool them in the meta-analysis calculator.

What this converter does

Most meta-analyses of continuous outcomes pool means and standard deviations, but many papers report a median with an interquartile range (IQR) or a range, a standard error, a confidence interval or only a p-value. Leaving those studies out wastes data and can bias the review. The Cochrane Handbook (chapter 6) describes how to recover the numbers you need. This tool does all of those conversions in one place and shows the formula behind every result.

Median, IQR and range to mean and SD

Three reporting scenarios are covered, using the notation of Wan et al. (2014): S1 (minimum, median, maximum), S2 (Q1, median, Q3) and S3 (all five numbers).

Luo mean S1: w = 4/(4 + n^0.75); mean = w(a + b)/2 + (1 − w)m S2: w = 0.7 + 0.39/n; mean = w(q1 + q3)/2 + (1 − w)m S3: w1 = 2.2/(2.2 + n^0.75), w2 = 0.7 − 0.72/n^0.55 mean = w1(a + b)/2 + w2(q1 + q3)/2 + (1 − w1 − w2)m Wan SD S1: SD = (b − a)/ξ(n), ξ(n) = 2Φ⁻¹((n − 0.375)/(n + 0.25)) S2: SD = (q3 − q1)/η(n), η(n) = 2Φ⁻¹((0.75n − 0.125)/(n + 0.25)) Shi SD S3: SD = (b − a)/θ1 + (q3 − q1)/θ2 θ1 = (2 + 0.14n^0.6)Φ⁻¹((n − 0.375)/(n + 0.25)) θ2 = (2 + 2/(0.07n^0.6))Φ⁻¹((0.75n − 0.125)/(n + 0.25))

For small samples (n ≤ 50 for the range, n ≤ 201 for the IQR) Wan’s SD uses the exact expected values from Wan et al.’s Tables 1 and 2, exactly as the R package meta does. We checked every scenario against meta::mean_sd_iqr(), mean_sd_range() and mean_sd_iqr_range() (meta 9.0): the results agree to at least 10 significant digits.

When not to convert. These formulas assume the data are roughly normal. Authors often report medians precisely because the data are skewed (length of hospital stay, costs, bacterial counts). If the median sits far from the middle of the quartiles, the tool warns you. Consider a sensitivity analysis without the converted studies, or the quantile-based methods of McGrath et al. (2020).

The other conversions

SE to SD SD = SE × √n 95% CI of a mean to SD SD = √n × (upper − lower) / 3.92 (2 × t(0.975, n−1) instead of 3.92 when n < 60) CI of a difference SE = (upper − lower) / 3.92 ; SD = SE / √(1/n₁ + 1/n₂) p or t to SD t = t⁻¹(1 − p/2; n₁+n₂−2) ; SE = |MD|/t ; SD = SE / √(1/n₁ + 1/n₂) Ratio CI to log SE SE = (ln upper − ln lower) / 3.92 ; from p: SE = |ln ratio| / Φ⁻¹(1 − p/2) Combine groups M = Σnᵢmᵢ/N ; SD = √{[Σ(nᵢ−1)sᵢ² + Σnᵢ(mᵢ − M)²]/(N − 1)} Change from baseline SD = √(SDb² + SDf² − 2r·SDb·SDf)

Worked example

A trial reports for 40 patients: median 26, IQR 21 to 33, range 12 to 52. With all five numbers (S3), Luo’s weights are w₁ = 0.122 and w₂ = 0.605, giving a mean of 27.33. Shi’s method gives an SD of 9.26. With only the IQR (S2) you would get a mean of 26.71 and an SD of 9.21; with only the range (S1), 27.21 and 9.25. Click Load example to reproduce these numbers.

References

  • Hozo SP, Djulbegovic B, Hozo I (2005). Estimating the mean and variance from the median, range, and the size of a sample. BMC Medical Research Methodology 5:13.
  • Wan X, Wang W, Liu J, Tong T (2014). Estimating the sample mean and standard deviation from the sample size, median, range and/or interquartile range. BMC Medical Research Methodology 14:135.
  • Luo D, Wan X, Liu J, Tong T (2018). Optimally estimating the sample mean from the sample size, median, mid-range, and/or mid-quartile range. Statistical Methods in Medical Research 27(6):1785–1805.
  • Shi J, Luo D, Weng H, et al. (2020). Optimally estimating the sample standard deviation from the five-number summary. Research Synthesis Methods 11(5):641–654.
  • Higgins JPT, Li T, Deeks JJ (eds). Chapter 6: Choosing effect measures and computing estimates of effect. Cochrane Handbook for Systematic Reviews of Interventions, version 6.5.
Want to run a full systematic review and meta-analysis? Our two-month, self-paced course takes you from your research question to a publishable review, with R, Excel, Word and EndNote. It is taught in Urdu/Hindi by Dr. Aammar Tufail.

Frequently asked questions

Which method should I use to convert a median and IQR to a mean and SD?

The current recommendation is Luo et al. (2018) for the mean and Wan et al. (2014) for the SD when you have the IQR, and Shi et al. (2020) for the SD when you have all five numbers. These are the defaults here and in the R package meta.

Is it acceptable to convert medians in a meta-analysis?

Yes, the Cochrane Handbook allows it, but say so in your methods and run a sensitivity analysis without the converted studies, especially when the data are likely to be skewed.

Can I get the SD from the IQR alone?

Yes. SD ≈ IQR / 1.35 for large samples. For small samples the tool uses the exact divisor from Wan et al. (2014), which is a little smaller than 1.35.

How do I combine two intervention arms into one?

Use the Combine groups tab. It applies the Cochrane Handbook formula, which accounts for both the SDs and the difference between the group means. Simply averaging the SDs is wrong.

The paper only gives p < 0.05. Can I calculate the SD?

Not reliably. You need an exact p-value or the t statistic. With p < 0.001 you can use 0.001 to get a conservative (too large) SD, but say so in your review.

Do my numbers leave my computer?

No. Every calculation runs in your browser and nothing is uploaded or stored.

Do I need to log in or create an account to use the meta-analysis data converter?

No. There is no login, no sign-up and no email required. Open the page and start using it straight away, for free, on any device.

How do I cite this tool in my thesis or paper?

Use the citation box on this page. In APA 7th edition: Tufail, M. A. (2026). Meta-analysis data converter: median, IQR and range to mean and SD, SE, CI and combined groups [Online tool]. Codanics. Retrieved [date you used it], from https://codanics.com/tools/meta-analysis-data-converter/. BibTeX, RIS (EndNote, Mendeley, Zotero), MLA, Harvard, Chicago and Vancouver formats are also available.

Free guides and courses from Codanics

More free tools

See all free Codanics tools → · Codanics on YouTube · WhatsApp channel

Made by Dr. Muhammad Aammar Tufail, Codanics. First published 17 November 2026, last updated 16 November 2026. Found a bug or have an idea for a new tool? Tell us on the WhatsApp channel or in the comments on YouTube. Results are for learning and planning; check important analyses with a statistician or your supervisor.
Exit mobile version