Uso ou abuso em testes de comparações de média: conhecimento científico ou empírico?

Bertoldo, Juliano Garcia; Guidolin, Altamir Frederico; Miqueloto, Aquidauana; Toaldo, Diego

doi:10.1590/s0103-84782008000400039

Cited by 8 publications

(6 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…These results contrasted with those presented by Cardellino and Siewerdt (1992), Santos et al (1998), Bezerra Neto et al (2002), and Bertoldo et al (2008b, in which this situation was reported as being very common. This divergence suggests an observed improvement in the use of MCTs in experiments related to quantitative treatments.…”

Section: Statistical Procedures Used and The Quality Of Selection Andcontrasting

confidence: 91%

“…This situation clearly shows the importance of presenting ANOVA results. According to Bertoldo et al (2008b), in post evaluation of 226 scientific papers published in plant science in the Ciência Rural journal, most of the errors occurring in analysis of experiments in factorial designs were related to studies in which the authors did not consider interactions among the factors, testing only the marginal means. These results are only valid if the interactions are not significant because, otherwise, it becomes necessary to work within the levels of each factor (decomposition of interaction).…”

Section: Statistical Procedures Used and The Quality Of Selection Andmentioning

confidence: 99%

See 1 more Smart Citation

An Evaluation of the Use of Statistical Procedures in Soil Science

Tavares

Carvalho

Machado

2016

Rev. Bras. Ciênc. Solo

View full text Add to dashboard Cite

Experimental statistical procedures used in almost all scientific papers are fundamental for clearer interpretation of the results of experiments conducted in agrarian sciences. However, incorrect use of these procedures can lead the researcher to incorrect or incomplete conclusions. Therefore, the aim of this study was to evaluate the characteristics of the experiments and quality of the use of statistical procedures in soil science in order to promote better use of statistical procedures. For that purpose, 200 articles, published between 2010 and 2014, involving only experimentation and studies by sampling in the soil areas of fertility, chemistry, physics, biology, use and management were randomly selected. A questionnaire containing 28 questions was used to assess the characteristics of the experiments, the statistical procedures used, and the quality of selection and use of these procedures. Most of the articles evaluated presented data from studies conducted under field conditions and 27 % of all papers involved studies by sampling. Most studies did not mention testing to verify normality and homoscedasticity, and most used the Tukey test for mean comparisons. Among studies with a factorial structure of the treatments, many had ignored this structure, and data were compared assuming the absence of factorial structure, or the decomposition of interaction was performed without showing or mentioning the significance of the interaction. Almost none of the papers that had split-block factorial designs considered the factorial structure, or they considered it as a split-plot design. Among the articles that performed regression analysis, only a few of them tested non-polynomial fit models, and none reported verification of the lack of fit in the regressions. The articles evaluated thus reflected poor generalization and, in some cases, wrong generalization in experimental design and selection of procedures for statistical analysis.

show abstract

Section: Statistical Procedures Used and The Quality Of Selection Andcontrasting

confidence: 91%

Section: Statistical Procedures Used and The Quality Of Selection Andmentioning

confidence: 99%

An Evaluation of the Use of Statistical Procedures in Soil Science

Tavares

Carvalho

Machado

2016

Rev. Bras. Ciênc. Solo

View full text Add to dashboard Cite

show abstract

“…The smaller the CV, the more homogeneous the data (GARCIA, 1989). The non-use of statistical analysis due to high CV has made the performance of comparisons and results of the data of this study to be carried out by analyzing the CFU averages and their standard deviation, since average comparison tests have been frequently used by researchers (BERTOLDO et al, 2008).…”

Section: Discussionmentioning

confidence: 99%

Comparative study of the effectiveness and residual effect of preoperative antisepsis with 4% chlorhexidine gluconate associated with 70% ethyl alcohol and 0.5% alcoholic chlorhexidine gluconate in dogs

Boeing

Pires

Lavelli

et al. 2021

AVB

View full text Add to dashboard Cite

The effectiveness of antisepsis of surgical sites in 20 animals (canine species) was compared and subdivided into two groups, using 4% chlorhexidine gluconate associated with alcohol (group 1) and 0.5% chlorhexidine gluconate (group 2). The samples were collected through skin swab after trichotomy (T1), after definitive antisepsis (T2) and one hour after the use of antiseptic (T3), and then submitted to the count of colony forming units (CFU). In both groups, bacterial growth occurred in T1; in T2, the reduction of CFUs was significant for both groups (G1 and G2); however, if we consider absolute values, we can see in T1 a greater amount of CFUs in G2, and when evaluating the results of T2, we can see values which are very similar between G1 and G2, which may suggest greater efficiency of G2 in initial times after antisepsis. In T3, the reduction of CFUs was more effective for G1, suggesting a greater residual effect when compared to G2. Both antiseptic protocols were effective as they significantly reduced the number of skin bacteria, both in T2 and T3.

show abstract

“…Among the possible factors related to the low publication rate, the methodological limitations of the research presented in Brazilian scientific events should be highlighted 13,22 . These deficiencies end up being perpetuated in the respective scientific publications, and some reviews indicate that up to 75% of the articles published in certain journals have some f law in the statistical analysis 23 . In the current study, this could be associated with the predominance of presentations in poster format, which generally correspond to studies with less scientific impact, and the predominance of publications in journals classified as Qualis B5, the lowest category among indexed journals.…”

Section: Discussionmentioning

confidence: 99%

Publication rate of abstracts on breast cancer presented at different scientific events in Brazil

et al. 2020

View full text Add to dashboard Cite

Introduction: Medical congresses allow scientific production to be appropriately disseminated and discussed. However, most of the scientific papers presented at medical congresses do not go on to be published in indexed journals. The present study aimed to characterize the abstracts presented at three different congresses on breast cancer held in Brazil, and to determine the publication rate of these three events. Methods: Observational, retrospective study, where the observation unit consisted of the scientific papers presented at the Brazilian Congress of Mastology (CBM), Jornada Paulista de Mastologia (JPM) and Brazilian Breast Cancer Symposium (BBCS) in 2017. Initially, we recorded all the abstracts of works presented at the event. Subsequently, the works were searched in digital databases (BIREME/LILACS and MEDLINE/PubMed) and in the respective resumes of the authors on the Lattes platform. Results: The study included 266 abstracts of scientific papers presented in the three selected events, of which 21 (7.9%) were published in an indexed journal. Most of these studies were conducted predominantly in public institutions (71.1%), located in the State of São Paulo (30.5%) and were presented in the form of a poster (77.8%). The publication rate from the BBCS, CBM and JPM was 13.4, 5.4 and 3.4%, respectively (p = 0.03). Considering the published articles, there was no difference in journal impact factor between the congresses (p = 0.49). “Mastology” was the journal that received the largest number of publications (n = 8; 38.1%). Conclusion: In 2017, less than 10% of the abstracts on breast cancer presented at Brazilian congresses were published in an indexed journal. Among the main specialty events in the country, the Brazilian Breast Cancer Symposium has a significantly higher publication rate.

show abstract

Uso ou abuso em testes de comparações de média: conhecimento científico ou empírico?

Abstract: RESUMO O objetivo deste trabalho foi identificar quais os principais erros e acertos na aplicação de testes de comparação de médias em trabalhos científicos, demonstrando alternativas

Cited by 8 publications

References 3 publications

An Evaluation of the Use of Statistical Procedures in Soil Science

An Evaluation of the Use of Statistical Procedures in Soil Science

Comparative study of the effectiveness and residual effect of preoperative antisepsis with 4% chlorhexidine gluconate associated with 70% ethyl alcohol and 0.5% alcoholic chlorhexidine gluconate in dogs

Publication rate of abstracts on breast cancer presented at different scientific events in Brazil

Contact Info

Product

Resources

About