Cited by 129Multidisciplinary Science and Engineering ResearchStatistical Methods in EpidemiologyStatistics Education and Methodologies

What we need to know when calculating the coefficient of correlation?

Open access
Udovicic, Martina, Bazdaric, Ksenija, Bilic-Zulle, Lidija, Petrovecki, Mladen·2007·Biochemia Medica

Abstract

Izvorni znanstveni članak Original scientifi c article Odabrane teme iz biostatistike Lessons in biostatistics Sa že tak Ko re la ci ja je sta tis tič ki pos tu pak za iz ra ču na va nje po ve za nos ti dvi ju va ri jabli.Vri jed no st ko re la ci je broj ča no se is ka zu je koe fi ci jen tom ko re la ci je, naj češ će Pear so no vim ili Spear ma no vim, dok se zna čaj no st koe fi ci jen ta is ka zu je vri jednoš ću P. Koe fi ci je nt ko re la ci je po ka zu je u ko joj su mje ri prom je ne vri jed nos ti jed ne va ri jab le po ve za ne s promje na ma vri jed nos ti dru ge va ri jab le.Pred znak koe fi ci jen ta ko re la ci je (+ ili -) go vo ri nam o smje ru po ve za nos ti.Pri li kom iz raču na va nja ko re la ci je naj češ će se pog r ješ ke od no se na uv je te za iz ra ču na va nje ko re la ci je, tu ma če nje koe fi ci jen ta i zna čaj no st ko re la ci je, vi so ke koe fi ci jen te ko re la ci je, pret pos tav lja nje uz roč no-pos lje dič ne ve ze, ja či nu po ve za nos ti (koe fi ci je nt de ter mi na ci je), te us po red bu dva koe fi ci jen ta ko re la ci je.Ključ ne ri je či: ko re la ci ja, Pear so nov koe fi ci je nt ko re la ci je, Spear ma nov koe fici jent ko re la ci je, koe fi ci je nt de ter mi na ci je, pog r ješ ka, sta tis ti ka Ab stra ct Cor re la tion is a sta tis ti cal pro ce du re ap plied to cal cu la te as so cia tion be tween two va riab les.The va lue of cor re la tion is nu me ri cal ly shown by a coeffi cie nt of cor re la tion, mo st of ten by Pear so n's or Spear ma n's coeffi cie nt, whi le the sig ni fi can ce of the coeffi cie nt is expres sed by P value.The coeffi cie nt of cor rela tion shows the exte nt to whi ch chan ges in the va lue of one va riab le are corre la ted to chan ges in the va lue of the ot her.A si gn pre ce di ng the coeffi cie nt of cor re la tion (+ or -) in di ca tes the di rec tion of cor re la tion.The mo st freque nt er ro rs in cal cu la ti ng cor re la tion are re la ted to con di tio ns for cal cu la tion, in terpre ta tion of the coeffi cie nt and cor re la tion sig ni fi can ce, hi gh cor re la tion coeffi cien ts, as sum ption of cau sal re la tion ship, the stren gth of cor re la tion (coefficie nt of de ter mi na tion), and com pa ri son of two cor re la tion coeffi cien ts.Key wor ds: cor re la tion, Pear so n's cor re la tion coeffi cie nt, Spear ma n's cor re lation coeffi cie nt, coeffi cie nt of de ter mi na tion, er ror, sta tis ti cs Što tre ba zna ti ka da iz ra ču na va mo koe fi ci je nt ko re la ci je?What we need to know when cal cu la ti ng the coeffi cie nt of cor re la tion?Mar ti na Udovičić 1 , Kse ni ja Baždarić 1 , Li di ja Bi li ć-Zul le 1,2 , Mla den Pet ro več ki 1,3 1 Katedra za me di cin sku in for ma ti ku, Me di cin ski fa kul tet Sveu či liš ta u Ri je ci, Ri je ka 1 Department of Me di cal In for ma ti cs, School of Me di ci ne, Uni ver si ty of Ri je ka, Ri je ka, Croa tia 2 Zavod za la bo ra to rij sku dijag nos ti ku, Kli nič ki bol nič ki cen tar "Rijeka", Ri je ka 2 Institute of La bo ra to ry Diag no sis, Ri je ka Cli ni cal Hos pi tal Cen ter, Ri je ka, Croa tia 3 Kli nič ki za vod za la bo ra to rij sku di jag nos ti ku, Kli nič ka bol ni ca "Dubrava", Zag reb 3 Clinical In sti tu te of La bo ra to ry Diag no sis, Dub ra va Cli ni cal Hos pi tal, Zag reb, Croa tia Pris tig lo: 6. ožujka 2007.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.11613/bm.2007.002

Cites

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Correlation describes a linear relationship between two sets of data but not their agreement.

    “Correlation describes linear relationship between two sets of data but not their agreement (3).”

    From Understanding bland altman analysis (2015) · cites this paper as [3]

    The Introduction supports the linear-relationship part for Pearson correlation, but explicitly describes correlation as “agreement of values from two data sets.” That contradicts the cited sentence’s assertion that correlation does not describe agreement. No page number is available in our copy. (LLM, conf=0.84)

    Checked by a reasoning model — may be wrong.

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

No references could be resolved yet.

Research works printed but not linked: 4

  1. Udovičić M. et al. What we need to know when cal cu la ti ng the coeffi cie nt of cor re la tion? Biochemia Medica 2007;17(1):1-138
  2. Dawson B, Tra pp RG. Ba sic and Cli ni cal Bios ta tis ti cs. 4th Ed. New Yo rk: Lan ge Me di cal Boo ks/McGraw-Hill; 2004.
  3. La ng T. Twen ty Sta tis ti cal Er ro rs Even YOU Can Fi nd in Bio me di cal Re- sear ch Ar tic les. CMJ 2004;45(4):361-70.
  4. Zou KH, Tun ca li KT, Sil ver man SG. Cor re la tion and Sim ple Li near Reg- res sion. Ra dio lo gy 2003; 227:617-28.

Cited by

Sorted by citations

Authors
Udovicic, M., Bazdaric, K., Bilic-Zulle, L., & Petrovecki, M.
Affiliations
University of Rijeka (HR)
Venue
Biochemia Medica
Published
2007
Pages
10-15
ISSN
  • 1330-0962 (ISSN-L)
  • 1846-7482
OpenAlex
W1515315778
Cited by
129
References
0
Citations by year
2026: 9 · 2025: 12 · 2024: 16 · 2023: 23 · 2022: 15 · 2021: 9 · 2020: 12 · 2019: 10 · 2018: 7 · 2017: 2 · 2016: 5 · 2015: 3 · 2013: 1 · 2012: 1
FWCI
1.11
Type
journal article
Language
en
Open access
Licence
cc-by
Locations
Biochemia Medica (publishedVersion, cc-by)
Topics
  • Social Sciences › Decision Sciences › Statistics, Probability and Uncertainty › Multidisciplinary Science and Engineering Research
  • Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods in Epidemiology
  • Physical Sciences › Mathematics › Statistics and Probability › Statistics Education and Methodologies
Keywords
correlation coefficient, Pearson correlation, Spearman correlation, R-squared, significance testing, correlation versus causation, direction of association, statistical errors, biostatistics education

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review