Basic Statistics for Clinicians_2. Basic Statistics for Clinicians_ Confidence Intervals.pdf

Basic Statistics for Clinicians_2. Basic Statistics for Clinicians_ Confidence Intervals.pdf

Info icon This preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
-- --[ statistics statistique ] BASIC STATISTICS FOR CLINICLNS: 2. INTERPRETING STUDY RESULTS: CONFIDENCE INTERVALS Gordon Guyatt,*t MD; Roman Jaeschke,*t MD; Nancy Heddle,t MSc; Deborah Cook,*t MD; Harry Shannon,* PhD; Stephen Walter,* PhD i1 .I 1 In the second of fotur articles, the authors discuss the /estima- tioin" approach to linterpreting stuidy results. Whereas, in hy- pothesis testing, study restIlts lead the reader to reject or ac- cept a null hypothesis, in estimationi the reader can assess whether a result is strong or weak, definitive or not. A confi- dence interval, based on the observed result and the size of the samnple, is calcUlated. It provides a range of probabilities wlithir which the true probability would lie 95% or 90%Y of the time, depeniding on the precisionl desired. It also provides a way of determining whether the sample is large enoLugh to nmake the trial definitive. If the lower bouindary of a confi- dence interval is above the threshold considered clinically significant, theni the trial is positive and definitive; if the lower boundary is somewhat below the threshold, the trial is positive, but stuLdies with larger samples are needed. Sinmi- larly, if the upper bouLndary of a confidenice interval is below the threshold considered significanit, the trial is negative and definitive. However, a negative result with a confidence in- terval that crosses the threshold means that trials with larger samples are needed to make a definitive determination of clin1ical importance. n our first article in this series we explained hypothesis test- ing, which involves estimating the likelihood that observed results of an experiment would have occurred by chance if a null hypothesis - that there was no difference between the effects of a treatment and a control condition -were true. The limitations of hypothesis testing have been increasingly recognized, and an altemative approach, called estimation, is becoming more popular. Several authors,- have outlined the concepts that we will introduce in this article, and their dis- cussions may be read to supplement our explanation. l)ans le deuxi&me article d'lne s&rie de qJuatre, les autcurs dis- cutent de la faqon "estimative" d'interprter les rSol[tats des CtLudes. M&ieme si, dans oLn test d'hypothese, les rasultats de 1'ftude m&nent le lecteur a rejeter ou a accepter une hypoth&se mLiule, dans unc estlimationi, le lecteur petit 6valuer si Llii rstilItat est fort oL0 faible, concloLanit oLI nlon. On calcule oin intervalle de confiance d'apr&s les resultats observes et la taille de l'6chantillon. Cet Intenralle fOuErn-it LIIC gamme de probabilit6s qui comprendrait la prohabilit6 reelle dans 95 % ou 90 '91 du temps, selon le degr6 de precision desire. 11 fournit egalemnent tine faqon de d6terminer si la taille de l'chantillon est assez grande pOUr que l'essai soit concluant. Si la limite infirieolre d'un intervalle de conifiance se situLe au-dessus do seuil consi- d6r6 comme significatif du point de vLue clinique, l'essai est alors positil et conCltLiantt; si la limite inf6rieore se
Image of page 1

Info icon This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Image of page 2
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

What students are saying

  • Left Quote Icon

    As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

    Student Picture

    Kiran Temple University Fox School of Business ‘17, Course Hero Intern

  • Left Quote Icon

    I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

    Student Picture

    Dana University of Pennsylvania ‘17, Course Hero Intern

  • Left Quote Icon

    The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

    Student Picture

    Jill Tulane University ‘16, Course Hero Intern