<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.1 20151215//EN" "https://jats.nlm.nih.gov/publishing/1.1/JATS-journalpublishing1.dtd">
<article xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" article-type="other" dtd-version="1.0" specific-use="sps-1.7" xml:lang="en">
  <front>
    <journal-meta>
      <journal-id journal-id-type="nlm-ta">J Bras Pneumol</journal-id>
      <journal-id journal-id-type="publisher-id">jbpneu</journal-id>
      <journal-title-group>
        <journal-title>Jornal Brasileiro de Pneumologia</journal-title>
        <abbrev-journal-title abbrev-type="publisher">J. bras. pneumol.</abbrev-journal-title>
      </journal-title-group>
      <issn pub-type="ppub">1806-3713</issn>
      <issn pub-type="epub">1806-3756</issn>
      <publisher>
        <publisher-name>Sociedade Brasileira de Pneumologia e Tisiologia</publisher-name>
      </publisher>
    </journal-meta>
    <article-meta>
      <article-id pub-id-type="publisher-id" specific-use="scielo-v3">6zfcry9h4PW5CybVBKNCyKR</article-id>
      <article-id pub-id-type="publisher-id" specific-use="scielo-v2">S1806-37132018000500353</article-id>
      <article-id pub-id-type="doi">10.1590/S1806-37562018000000303</article-id>
      <article-categories>
        <subj-group subj-group-type="heading">
          <subject>CONTINUING EDUCATION: SCIENTIFIC METHODOLOGY</subject>
        </subj-group>
      </article-categories>
      <title-group>
        <article-title>Meeting the assumptions of statistical tests: an important and often forgotten step to reporting valid results</article-title>
      </title-group>
      <contrib-group>
        <contrib contrib-type="author">
          <contrib-id contrib-id-type="orcid">0000-0001-5742-2157</contrib-id>
          <name>
            <surname>Patino</surname>
            <given-names>Cecilia Maria</given-names>
          </name>
          <xref ref-type="aff" rid="aff1">
            <sup>1</sup>
          </xref>
          <xref ref-type="aff" rid="aff2">
            <sup>2</sup>
          </xref>
        </contrib>
        <contrib contrib-type="author">
          <contrib-id contrib-id-type="orcid">0000-0001-6548-1384</contrib-id>
          <name>
            <surname>Ferreira</surname>
            <given-names>Juliana Carvalho</given-names>
          </name>
          <xref ref-type="aff" rid="aff1">
            <sup>1</sup>
          </xref>
          <xref ref-type="aff" rid="aff3">
            <sup>3</sup>
          </xref>
        </contrib>
      </contrib-group>
      <aff id="aff1">
        <label>1</label>
        <institution content-type="original">. Methods in Epidemiologic, Clinical, and Operations Research-MECOR-program, American Thoracic Society/Asociaci&#243;n Latinoamericana del T&#243;rax, Montevideo, Uruguay.</institution>
        <institution content-type="orgdiv1">Clinical, and Operations Research-MECOR-program</institution>
        <institution content-type="orgname">Asociaci&#243;n Latinoamericana del T&#243;rax</institution>
        <addr-line>
          <named-content content-type="city">Montevideo</named-content>
        </addr-line>
        <country country="UY">Uruguay</country>
      </aff>
      <aff id="aff2">
        <label>2</label>
        <institution content-type="original">. Department of Preventive Medicine, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA.</institution>
        <institution content-type="normalized">University of Southern California</institution>
        <institution content-type="orgdiv2">Department of Preventive Medicine</institution>
        <institution content-type="orgdiv1">Keck School of Medicine</institution>
        <institution content-type="orgname">University of Southern California</institution>
        <addr-line>
          <named-content content-type="city">Los Angeles</named-content>
          <named-content content-type="state">CA</named-content>
        </addr-line>
        <country country="US">USA</country>
      </aff>
      <aff id="aff3">
        <label>3</label>
        <institution content-type="original">. Divis&#227;o de Pneumologia, Instituto do Cora&#231;&#227;o, Hospital das Cl&#237;nicas, Faculdade de Medicina, Universidade de S&#227;o Paulo, S&#227;o Paulo (SP) Brasil. </institution>
        <institution content-type="normalized">Universidade de S&#227;o Paulo</institution>
        <institution content-type="orgdiv2">Hospital das Cl&#237;nicas</institution>
        <institution content-type="orgdiv1">Faculdade de Medicina</institution>
        <institution content-type="orgname">Universidade de S&#227;o Paulo</institution>
        <addr-line>
          <named-content content-type="city">S&#227;o Paulo</named-content>
          <named-content content-type="state">SP</named-content>
        </addr-line>
        <country country="BR">Brazil</country>
      </aff>
      <pub-date pub-type="epub-ppub">
        <season>Sep-Oct</season>
        <year>2018</year>
      </pub-date>
      <volume>44</volume>
      <issue>05</issue>
      <fpage>353</fpage>
      <lpage>353</lpage>
      <permissions>
        <copyright-statement>&#169; 2018 Sociedade Brasileira de Pneumologia e Tisiologia</copyright-statement>
        <copyright-year>2018</copyright-year>
        <copyright-holder>SciELO</copyright-holder>
        <license license-type="open-access" xlink:href="https://creativecommons.org/licenses/by-nc/4.0/" xml:lang="en">
          <license-p>This is an open-access article distributed under the terms of the Creative Commons Attribution License</license-p>
        </license>
      </permissions>
      <counts>
        <fig-count count="0"/>
        <table-count count="2"/>
        <equation-count count="0"/>
        <ref-count count="2"/>
        <page-count count="1"/>
      </counts>
    </article-meta>
  </front>
  <body>
    <sec>
      <title>PRACTICAL SCENARIO</title>
      <p>A secondary analysis of a randomized controlled trial was conducted to evaluate whether atopic status was associated with asthma severity and asthma control among inner-city adolescents in the USA.<xref ref-type="bibr" rid="B1"><sup>1</sup></xref> To answer this question, the authors evaluated the differences between atopic and non-atopic patients, in terms of asthma control and asthma severity scores, using a t-test, and reported the results as means &#177; SDs. The results showed that the atopic patients, when compared with non-atopic patients, had similar asthma control scores (18.1 &#177; 4.2 vs. 18.2 &#177; 3.7; p = 0.95) but worse asthma severity scores (5.5 &#177; 2.9 vs. 4.7 &#177; 2.8; p = 0.04). </p>
    </sec>
    <sec>
      <title>BACKGROUND</title>
      <p>As part of the process of answering research questions using quantitative methods, investigators select a statistical analytical approach based on various characteristics of the study, such as the nature of the variables collected (e.g., continuous, categorical, time-to-event variables), as well as the study design. Once the analysis is completed, it is expected that investigators take an additional step in the analysis process to make sure that the a priori assumptions of the statistical test selected are met in the dataset assembled for the study.</p>
      <p>All statistical tests have underlying assumptions that need to be met so that the test provides results that are valid (<italic>without unacceptable error</italic>) regarding the parameter the test is calculating (e.g., mean, proportion, odds ratio, etc.). In our example, the authors used a t-test to calculate the mean and the standard deviation of asthma control and severity asthma scores in atopic and non-atopic patients using data collected from the study population as a means to represent the truth in similar patients from the source population (adolescents with asthma in the USA). This process, called inference, is only valid if the assumptions of the statistical test are met (<xref ref-type="table" rid="t1">Table 1</xref>).</p>
      <p>
        <table-wrap id="t1">
          <label>Table 1</label>
          <caption>
            <title>Example of assumptions of a statistical test.</title>
          </caption>
          <table>
            <colgroup>
              <col/>
              <col/>
              <col/>
            </colgroup>
            <thead>
              <tr>
                <th align="center">Statistical test</th>
                <th align="center">Assumption</th>
                <th align="center">How to corroborate</th>
              </tr>
            </thead>
            <tbody>
              <tr>
                <td align="left" rowspan="4">t-Test</td>
                <td align="left">Sampling: The participants in the study are randomly sampled from the source population.</td>
                <td align="left">Check the protocol.</td>
              </tr>
              <tr>
                <td align="left">Sample size: The sample size calculated for the study is achieved. </td>
                <td align="left">Check sample size calculation in the protocol and check if sample size was reached by the number of participants included in the study.</td>
              </tr>
              <tr>
                <td align="left">Normal distribution: The scale of measurement of the outcome variable is continuous and is normally distributed (or at least symmetric).</td>
                <td align="left">Conduct descriptive statistics on the outcome variable and create a graph showing the distribution which should follow a bell curve.</td>
              </tr>
              <tr>
                <td align="left">Homogeneity of variances: The variance (standard deviation) of the data collected on the continuous variable across the two comparison groups is similar. </td>
                <td align="left">Use valid statistical methods to test for homogeneity. </td>
              </tr>
            </tbody>
          </table>
        </table-wrap>
      </p>
      <p>It is good practice, as investigators, to acknowledge that the assumptions of the statistical tests used to answer their research question have been evaluated and whether they were met or not. If the assumptions of the tests are met, which should be reported in the results section of the study, this assures the scientific community that the results of the study have met one of the important criteria related to their validity. However, it has been suggested that the assumptions of statistical techniques are often not checked<xref ref-type="bibr" rid="B2"><sup>2</sup></xref> or reported. Reasons for not assessing assumptions include: 1. researchers being unaware of the assumptions of the statistical tests used in the study, such as a t-test, ANOVA, or regression analysis; 2. researchers being unaware of standard approaches used to check assumptions of statistical tests and evaluate if they are violated or not; 3. researchers being unaware of how to remedy violations of the assumptions of a statistical model or how to select a new test when violations cannot be remedied; and 4. researchers being confident in the robustness of the statistical test used and choosing not to check its assumptions.</p>
      <p>As educators and investigators, we all need to contribute to the overall goal of reporting high quality research conducted among the populations we serve. Testing the assumptions of statistical tests or models used to answer our research questions is a good start! </p>
    </sec>
  </body>
  <back>
    <ref-list>
      <title>REFERENCES</title>
      <ref id="B1">
        <label>1</label>
        <mixed-citation>1 Arroyave WD, Rabito FA, Carlson JC, Sever ML, Lefante J. Asthma severity, not asthma control, is worse in atopic compared with nonatopic adolescents with asthma. Ann Allergy Asthma Immunol 2016;116(1):18-25. <ext-link ext-link-type="uri" xlink:href="https://doi.org/10.1016/j.anai.2015.10.015">https://doi.org/10.1016/j.anai.2015.10.015</ext-link>
				</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Arroyave</surname>
              <given-names>WD</given-names>
            </name>
            <name>
              <surname>Rabito</surname>
              <given-names>FA</given-names>
            </name>
            <name>
              <surname>Carlson</surname>
              <given-names>JC</given-names>
            </name>
            <name>
              <surname>Sever</surname>
              <given-names>ML</given-names>
            </name>
            <name>
              <surname>Lefante</surname>
              <given-names>J</given-names>
            </name>
          </person-group>
          <article-title>Asthma severity, not asthma control, is worse in atopic compared with nonatopic adolescents with asthma</article-title>
          <source>Ann Allergy Asthma Immunol</source>
          <year>2016</year>
          <volume>116</volume>
          <issue>1</issue>
          <fpage>18</fpage>
          <lpage>25</lpage>
          <ext-link ext-link-type="uri" xlink:href="https://doi.org/10.1016/j.anai.2015.10.015">https://doi.org/10.1016/j.anai.2015.10.015</ext-link>
        </element-citation>
      </ref>
      <ref id="B2">
        <label>2</label>
        <mixed-citation>2 Hoekstra R, Kiers HA, Johnson A. Are assumptions of well-known statistical techniques checked, and why (not)? Front Psychol. 2012;3:137. <ext-link ext-link-type="uri" xlink:href="https://doi.org/10.3389/fpsyg.2012.00137">https://doi.org/10.3389/fpsyg.2012.00137</ext-link>
				</mixed-citation>
        <element-citation publication-type="journal">
          <person-group person-group-type="author">
            <name>
              <surname>Hoekstra</surname>
              <given-names>R</given-names>
            </name>
            <name>
              <surname>Kiers</surname>
              <given-names>HA</given-names>
            </name>
            <name>
              <surname>Johnson</surname>
              <given-names>A</given-names>
            </name>
          </person-group>
          <article-title>Are assumptions of well-known statistical techniques checked, and why (not)</article-title>
          <source>Front Psychol</source>
          <year>2012</year>
          <volume>3</volume>
          <fpage>137</fpage>
          <lpage>137</lpage>
          <ext-link ext-link-type="uri" xlink:href="https://doi.org/10.3389/fpsyg.2012.00137">https://doi.org/10.3389/fpsyg.2012.00137</ext-link>
        </element-citation>
      </ref>
    </ref-list>
  </back>
  <sub-article article-type="translation" id="s1" xml:lang="pt">
    <front-stub>
      <article-categories>
        <subj-group subj-group-type="heading">
          <subject>EDUCA&#199;&#195;O CONTINUADA: METODOLOGIA CIENT&#205;FICA</subject>
        </subj-group>
      </article-categories>
      <title-group>
        <article-title>Atender as premissas dos testes estat&#237;sticos: um passo importante e muitas vezes negligenciado na comunica&#231;&#227;o de resultados v&#225;lidos</article-title>
      </title-group>
      <contrib-group>
        <contrib contrib-type="author">
          <contrib-id contrib-id-type="orcid">0000-0001-5742-2157</contrib-id>
          <name>
            <surname>Patino</surname>
            <given-names>Cecilia Maria</given-names>
          </name>
          <xref ref-type="aff" rid="aff01">
            <sup>1</sup>
          </xref>
          <xref ref-type="aff" rid="aff02">
            <sup>2</sup>
          </xref>
        </contrib>
        <contrib contrib-type="author">
          <contrib-id contrib-id-type="orcid">0000-0001-6548-1384</contrib-id>
          <name>
            <surname>Ferreira</surname>
            <given-names>Juliana Carvalho</given-names>
          </name>
          <xref ref-type="aff" rid="aff01">
            <sup>1</sup>
          </xref>
          <xref ref-type="aff" rid="aff03">
            <sup>3</sup>
          </xref>
        </contrib>
      </contrib-group>
      <aff id="aff01">
        <label>1</label>
        <institution content-type="original">. Methods in Epidemiologic, Clinical, and Operations Research-MECOR-program, American Thoracic Society/Asociaci&#243;n Latinoamericana del T&#243;rax, Montevideo, Uruguay.</institution>
      </aff>
      <aff id="aff02">
        <label>2.</label>
        <institution content-type="original"> Department of Preventive Medicine, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA.</institution>
      </aff>
      <aff id="aff03">
        <label>3</label>
        <institution content-type="original">. Divis&#227;o de Pneumologia, Instituto do Cora&#231;&#227;o, Hospital das Cl&#237;nicas, Faculdade de Medicina, Universidade de S&#227;o Paulo, S&#227;o Paulo (SP) Brasil. </institution>
      </aff>
    </front-stub>
    <body>
      <sec>
        <title>CEN&#193;RIO REAL</title>
        <p>Foi realizada uma an&#225;lise secund&#225;ria de um estudo randomizado controlado para avaliar se o status de atopia estava associado &#224; gravidade e ao controle da asma entre adolescentes urbanos nos EUA. <sup>(</sup><xref ref-type="bibr" rid="B1"><sup>1</sup></xref> Para responder essa pergunta, os autores avaliaram as diferen&#231;as entre pacientes at&#243;picos e n&#227;o at&#243;picos, em termos de escores de controle da asma e de gravidade da doen&#231;a, usando um teste t, e relataram os resultados como m&#233;dia &#177; dp. Os resultados mostraram que os pacientes at&#243;picos, quando comparados aos n&#227;o at&#243;picos, tiveram escores de controle da asma similares (18,1 &#177; 4,2 vs. 18,2 &#177; 3,7; p = 0,95), mas escores de gravidade piores (5,5 &#177; 2,9 vs. 4,7 &#177; 2,8; p = 0,04).</p>
      </sec>
      <sec>
        <title>CONTEXTO</title>
        <p>Como parte do processo de responder as perguntas de estudo usando m&#233;todos quantitativos, os pesquisadores selecionam um m&#233;todo estat&#237;stico anal&#237;tico baseado em v&#225;rias caracter&#237;sticas do estudo, como a natureza das vari&#225;veis coletadas (por exemplo, vari&#225;veis cont&#237;nuas, categ&#243;ricas e <italic>time-to-event</italic>), bem como no desenho do estudo. Uma vez conclu&#237;da a an&#225;lise, espera-se que os investigadores deem um passo adicional no processo anal&#237;tico certificando-se de que as premissas iniciais do teste estat&#237;stico selecionado tenham sido atendidas no banco de dados montado para o estudo.</p>
        <p>Todos os testes estat&#237;sticos t&#234;m premissas de base que precisam ser atendidas para que o teste forne&#231;a resultados v&#225;lidos (<italic>sem erros inaceit&#225;veis</italic>) em rela&#231;&#227;o ao par&#226;metro que o teste est&#225; calculando (por exemplo, m&#233;dia, propor&#231;&#227;o, raz&#227;o de chances, etc.). Em nosso exemplo, os autores usaram um teste t para calcular a m&#233;dia e o desvio-padr&#227;o dos escores de controle e de gravidade da asma em pacientes at&#243;picos e n&#227;o at&#243;picos usando dados coletados da popula&#231;&#227;o do estudo como um meio de representar a verdade em pacientes similares da popula&#231;&#227;o de origem (adolescentes com asma nos EUA). Esse processo, denominado infer&#234;ncia, s&#243; &#233; v&#225;lido se as premissas do teste estat&#237;stico forem atendidas (<xref ref-type="table" rid="t01">Tabela 1</xref>).</p>
        <p>
          <table-wrap id="t01">
            <label>Tabela 1</label>
            <caption>
              <title>Exemplo de premissas de um teste estat&#237;stico.</title>
            </caption>
            <table>
              <colgroup>
                <col/>
                <col/>
                <col/>
              </colgroup>
              <thead>
                <tr>
                  <th align="center">Teste estat&#237;stico</th>
                  <th align="center">Premissas</th>
                  <th align="center">Como corroborar</th>
                </tr>
              </thead>
              <tbody>
                <tr>
                  <td align="left" rowspan="4">Teste t</td>
                  <td align="left">Amostragem: Os participantes do estudo s&#227;o amostrados aleatoriamente da popula&#231;&#227;o de origem.</td>
                  <td align="left">Verificar o protocolo</td>
                </tr>
                <tr>
                  <td align="left">Tamanho da amostra: O tamanho da amostra calculado para o estudo &#233; alcan&#231;ado.</td>
                  <td align="left">Verificar o c&#225;lculo do tamanho da amostra no protocolo e verificar se o tamanho da amostra foi atingido pelo n&#250;mero de participantes inclu&#237;dos no estudo.</td>
                </tr>
                <tr>
                  <td align="left">Distribui&#231;&#227;o normal: A escala de medi&#231;&#227;o da vari&#225;vel de desfecho &#233; cont&#237;nua e sua distribui&#231;&#227;o &#233; normal (ou pelo menos sim&#233;trica).</td>
                  <td align="left">Realizar estat&#237;sticas descritivas sobre a vari&#225;vel de desfecho e criar um gr&#225;fico mostrando a distribui&#231;&#227;o, que deve seguir uma curva em forma de sino.</td>
                </tr>
                <tr>
                  <td align="left">Homogeneidade de vari&#226;ncias: A vari&#226;ncia (desvio-padr&#227;o) dos dados coletados sobre a vari&#225;vel cont&#237;nua entre os dois grupos de compara&#231;&#227;o &#233; similar.</td>
                  <td align="left">Usar m&#233;todos estat&#237;sticos v&#225;lidos para testar a homogeneidade.</td>
                </tr>
              </tbody>
            </table>
          </table-wrap>
        </p>
        <p>&#201; uma boa pr&#225;tica, como investigadores, saber se as premissas dos testes estat&#237;sticos usados para responder suas perguntas foram avaliadas e se foram ou n&#227;o atendidas. Se as premissas dos testes tiverem sido atendidas, o que deve ser relatado na se&#231;&#227;o de resultados do estudo, isso garante &#224; comunidade cient&#237;fica que os resultados do estudo atenderam um dos crit&#233;rios importantes relacionados a sua validade. Contudo, foi sugerido que as premissas de t&#233;cnicas estat&#237;sticas n&#227;o s&#227;o frequentemente verificadas<xref ref-type="bibr" rid="B2"><sup>2</sup></xref><sup>)</sup> nem relatadas. As raz&#245;es para n&#227;o se avaliarem as premissas incluem: 1. os pesquisadores desconhecem as premissas dos testes estat&#237;sticos utilizados no estudo, como as do teste t, da ANOVA ou de uma an&#225;lise de regress&#227;o; 2. os pesquisadores desconhecem os m&#233;todos padronizados utilizados para verificar as premissas dos testes estat&#237;sticos e avaliar se elas foram violadas ou n&#227;o; 3. os pesquisadores n&#227;o sabem como remediar as viola&#231;&#245;es &#224;s premissas de um modelo estat&#237;stico ou como escolher um novo teste quando as viola&#231;&#245;es n&#227;o podem ser remediadas; e 4. os pesquisadores confiam na robustez do teste estat&#237;stico utilizado e optam por n&#227;o checar suas premissas.</p>
        <p>Como educadores e pesquisadores, todos precisamos contribuir para o objetivo maior de relatar pesquisas de alta qualidade realizadas nas popula&#231;&#245;es que servimos. Testar as premissas dos testes ou os modelos estat&#237;sticos usados para responder nossas perguntas de estudo &#233; um bom come&#231;o!</p>
      </sec>
    </body>
  </sub-article>
</article>
