China
Africa
Explore chapters and articles related to this topic
Preparing Studies for Statistical Analysis
Published in Lynne M. Bianchi, Research during Medical Residency, 2022
Luke J. Rosielle, Lynne M. Bianchi
In contrast, inferential statistics are used to formally test a hypothesis. These methods calculate values (e.g., p-values and confidence intervals) to indicate the likelihood the data reflect true differences among groups. Analytical observational and experimental studies phrase research questions in terms of a hypothesis.
Mathematics for medical imaging
Published in Ken Holmes, Marcus Elkington, Phil Harris, Clark's Essential Physics in Imaging for Radiographers, 2021
Descriptive statistics are used to summarise the population data by describing what was observed in the sample numerically or graphically. Inferential statistics uses patterns in the sample data to draw inferences about the population represented.
The impact of treatment and other clinical and community health interventions: A ‘does it work?’ evaluation
Published in Milos Jenicek, Foundations of Evidence-Based Medicine, 2019
Once comparisons of outcomes in treatment groups are made, investigators bring their experiences to the attention of readers. Results are interpreted as being ‘significant’, ‘highly significant’ or ‘statistically significant’. P values from the statistical analysis of data are used to show the strength of evidence in analytical studies, be they observational or experimental. P values are also used to evaluate the degree of dissimilarity between two or more series of observations. Once again, remember that as a measure of the impact of treatment in clinical or epidemiological terms, p values can only ‘clear the way’ (if they are small) for the epidemiological and clinical assessment of results of clinical trials. The p value is ‘usually the probability of obtaining a result as extreme as, or more extreme than, the one observed if the dissimilarity is entirely due to variation in measurement or in subject response—that is, if it is the result of chance alone’.19 Some funding agencies or institutions may still be happy with ‘small ps’, indicating that a drug leading to different outcomes shows a very low probability of not working (null hypothesis would be true). This, however, does not indicate the magnitude of the effect. Hence, p values and significance of findings in terms of inferential statistics should be carefully interpreted and given their proper meaning.19,20
Terminalia catappa attenuates phenylhydrazine-induced anaemia and hepato-renal toxicity in male Wistar rat by boosting blood cells, modulation of lipoproteins and up-regulation of in vivo antioxidant armouries
Published in Biomarkers, 2023
Elizabeth Umoren, Jerome Ndudi Asiwe, Idara Asuquo Okon, Albert Levi Amangieka, Clement U. Nyenke, Anthony Chibuzor Nnamudi, Emmanuel U. Modo, Augustine I. L. Bassey, Gospel Nwikue, Okon E. Etim
In this study, the body weight of the animals was measured weekly as well as organ weight after euthanasia. Figure 2a–e showed the results after data had been subjected to inferential statistics. There was no significant difference in heart [F(3, 12)=2.84, p = 0.0823] and kidney [F(3, 12)=0.859, p = 0.4888] weight across groups. However, treatment with T. catappa significantly reduced the spleen weight [F(3, 12)=32.7, p < 0.0001] comparatively to the PHZ-treated group and normal group. Though PHZ-treated group observed increase was not statistically significant when compare to control group. The liver weight [F(3, 12)=8.85, p = 0.0023] was also significantly decreased in PHZ- and T. catappa – treated groups when compared to the control group. However, T. catappa could not restore the weight of the kidney comparatively to the PHZ- treated group. The total body weight {Treatment [F(3, 16)=207, p < 0.0001], Time [F(4, 64)=6.11, p = 0.0003] and Interaction [F(12, 64)=9.11, p < 0.0001]}was also observed to be progressively increased across group throughout the duration of the experiment as measured weekly.
Records request response rate and vaccination status of first-time college students at a mid-sized Midwestern university
Published in Journal of American College Health, 2022
Alexandra Larsen, Anders Cedergren
When conducting inferential statistics, a Bonferroni correction was used to modify the alpha level of significance to reduce the risk of a Type I error, as the risk for Type I error increases when multiple tests are run on the same dataset.28,33 By dividing .05 by the number of statistical tests run on the sample, which was 24, this calculation produced a much more conservative alpha level of significance of < .002. When a chi-square test indicated a significant relationship between a demographic variable and vaccination status or records returned, follow-up pairwise comparisons were conducted to evaluate column proportions.31 A Bonferroni correction was then applied within these tests to confirm significance. Results that were deemed to be statistically significant in this study were also assessed for practical significance using phi or Cramér’s V effect size tests.28,33,34
Screening and Brief Intervention for Psychiatric and Suicide Risk in the Juvenile Justice System: Findings from an Open Trial
Published in Evidence-Based Practice in Child and Adolescent Mental Health, 2021
Kathleen Kemp, Margaret Webb, Jennifer Wolff, Katelyn Affleck, Joseph Casamassima, Lauren Weinstock, Anthony Spirito
The sample was drawn from one JJS setting so feasibility of the intervention procedures in other settings is needs to be tested. Because only court-involved youth living in the community were included in the open trial, conclusions cannot be assumed to generalize to incarcerated JJS populations. Similarly, the sample overall was small, their presenting problems were varied, and there was a small percentage of participants of color. The small sample precludes drawing any conclusions regarding any adaptations that might be needed to tailor the coping plan to race and/or ethnicity. In addition, although we present inferential statistics, the small sample limits confidence in these statistics. We based our coping plan on the Brent et al. model, but there are other safety planning approaches (e.g., Asarnow et al., 2015; Czyz et al., 2019) that have core components in common but some variations that might be useful with JJ-involved youth, e.g., the emotions thermometer technique used by Asarnow et al. (2015). And finally, because adolescents were not randomized to the intervention condition, nor was there a comparison condition, changes in symptoms cannot be attributed to the intervention. Changes in symptomatology might, for example, be related to repeated assessments or regression to the mean.