Basic Research Design:
Lynne M. Bianchi in Research during Medical Residency, 2022
Statistical analysis: Data are typically analyzed using inferential statistics that allow the investigator to formally test a hypothesis and make comparisons between groups. The statistical tests used will be determined by the types of measurements made (categorical, continuous) and the number of groups in the study. For example, when the data from each group have a normal distribution and the variables measured are continuous (interval, ratio) then parametric tests, such as Student'st test, Pearson's correlation coefficient, or analysis of variance (ANOVA), might be used. When the data are not normally distributed or the variables are categorical (nominal, ordinal), then an appropriate non-parametric test will be used, such as the Chi-squared test, Fisher's exact test, Spearman's rank correlation coefficient, or Mann-WhitneyUtest.
Statistical Analysis
Abhaya Indrayan in Research Methods for Medical Graduates, 2019
Statistical analysis of data is done in several ways. For descriptive studies and for some analytical studies, the primary objective is to find the percentage of cases that have a particular outcome, or the average level of a medical measurement. This is called estimation. This estimate is accompanied by the CI that delineates the range of values beyond which a sample summary is unlikely to lie in repeated samples. Common methods for finding this are provided in Section 11.1. The other important activity under data analysis is the test of hypothesis whereby we find whether the values obtained in our study can be a presumed value or not. This requires the concept of P-value and power. These also are discussed in Section 11.1. The basic methods for testing significance (this term seems to be on its way out), such as chi-square for qualitative data and Student’s t-test for quantitative data, are explained in Section 11.2. Section 11.3 is on regression that gives the methods to study the relationship between two or more characteristics. This includes both the ordinary least square where the dependent is a quantitative measurement and the logistic where the dependent is binary. This section also contains a brief description of correlation coefficients. The methods for assessing the cause–effect relationship and for validation of results are presented in Section 11.4. Statistical fallacies that so commonly arise in medical research are discussed in Section 11.5.
A-Z of Standardisation, Pre-Clinical, Clinical and Toxicological Data
Saroya Amritpal Singh in Regulatory and Pharmacological Basis of Ayurvedic Formulations, 2017
Childhood Bronchial Asthma: A total of 23 children (who had consented) of both sex under 12 years of age were included in the study and divided into three groups, blood samples were collected before treatment and after the completion of therapy for the metabolic markers like Hb gm%, TLC, AEC, S. Protein, S. Albumin, SGOT, SGPT, alkaline phosphatase and S. Bilirubin. SKCR was given for a total of 45 days in a dose of 4 mg/kg/dose x 12 hourly with garlic, ginger and honey in ratio of 1:2:4. Statistical Analysis Used: In the present study, SPSS software was used to get statistical data such as Mean (X-), Mean Difference (d’), Standard Deviation (SD) and Student’s “t” test, etc. (Kumar, Singh and Gupta 2014).
Lack or insufficient predialysis nephrology care worsens the outcomes in dialyzed patients – call for action
Published in Renal Failure, 2022
Andrzej Milkowski, Tomasz Prystacki, Wojciech Marcinkowski, Teresa Dryl-Rydzynska, Jacek Zawierucha, Jacek S. Malyszko, Pawel Zebrowski, Konrad Zuzda, Jolanta Małyszko
Data was collected for each patient prior to the first visit: vascular access (temporary CVC permanent catheter, AV fistula, and graft), age, BMI, systolic and diastolic arterial pressure, laboratory tests: eGFR, urea concentration, 50 Hb, phosphate, albumin, PTH, glucose, accompanying diseases: diabetes, hypertension, malignancy, Charlson comorbidity index, and dose of ESA determined in the first month of dialysis (darbopoetin doses converted to erythropoietin alfa). During 13-month observation the following data was collected: number of hospitalizations and length of stay, patients’ outcomes, i.e., survival, kidney transplantation, and mortality. The collected data was subjected to statistical analysis. Since only the available data from the EUCLiD system was analyzed, written consent was not needed in accordance with the regulations in force at Fresenius Nephrocare in Poland and Ethics Committee at the Warsaw Medical University.
Enhancement of diagnostic performance in lung cancers by combining CEA and CA125 with autoantibodies detection
Published in OncoImmunology, 2019
Ruochuan Zang, Yuan Li, Runsen Jin, Xinfeng Wang, Yuanyuan Lei, Yun Che, Zhiliang Lu, Shuangshuang Mao, Jianbing Huang, Chengming Liu, Sufei Zheng, Fang Zhou, Qian Wu, Shugeng Gao, Nan Sun, Jie He
In our study, the levels of two well-investigated biomarkers (CEA and CA125) and seven autoantibodies were separately measured in two randomly divided cohorts to establish a well-optimized model with strong predictive value. Significant differences were observed for each biomarker in the training cohort, but the mean values and standard deviations of single biomarkers were not used for further analysis in our study. Proper statistical analysis is important for data evaluation. Instead of defining positive results based on a single biomarker, a multiple logistic regression analysis was performed to select biomarkers for a mixed model and to generate the ROCs. Furthermore, pairwise comparisons of the ROCs of our primary model and each single protein biomarker were applied to assess significant differences. Unsurprisingly, statistical analysis confirmed that the single biomarkers had relatively low diagnostic performance in the training group, with AUCs ranging from 0.619 to 0.835. While the autoantibody against PGP 9.5 demonstrated the best predictive ability among the seven autoantibodies in both the training and validation groups (AUC: 0.743 (95%CI: 0.662–0.824) and AUC: 0.687 (95%CI: 0.604–0.770), respectively), it was not included in the mixed panel according to the results of the multiple logistic analysis.
Risk factors for work-related musculoskeletal disorders among workers in the footwear industry: a cross-sectional study
Published in International Journal of Occupational Safety and Ergonomics, 2021
Wilza Karla dos Santos Leite, Anísio José da Silva Araújo, Jonhatan Magno Norte da Silva, Leila Amaral Gontijo, Elamara Marama de Araújo Vieira, Erivaldo Lopes de Souza, Geraldo Alves Colaço, Luiz Bueno da Silva
Regarding the validity of the generalized linear and ordinal logistic regression models, verifying the quality of the fit measures is always useful to determine how well a model describes the relationships between dependent and independent variables. Model accuracy is a measure that can be used for this purpose. Given the values of independent variables, this measure classifies observations and compares the observed responses to those predicted by the model. The percentage of correct classifications expresses the model accuracy. However, in the case of ordinal logistic regression models, this measure should be carefully analyzed, because although high accuracy indicates that the model is truly adequate to assess the relationships between variables, low accuracy does not necessarily indicate the opposite situation [26]. Figure 1 summarizes the statistical analysis steps.
Related Knowledge Centers
- Bayesian Inference
- Biostatistics
- Cluster Analysis
- Proportional Hazards Model
- Statistical Hypothesis Testing
- Sampling
- Hodges–Lehmann Estimator
- Empirical Distribution Function
- Sample Mean & Covariance
- Hellinger Distance