Bio statistical analysis in clinical research
Download as PPTX, PDF0 likes432 views
The document outlines the fundamentals of biostatistics, covering key concepts such as data variables, normal distribution, p-values, and methods for sample size calculation in clinical research. It provides guidelines for determining statistical significance, comparing parametric and non-parametric tests, and evaluating diagnostic performances using metrics like sensitivity and specificity. Additionally, it emphasizes the importance of sample size for ensuring valid results in studies, with specific examples given for calculating sizes based on different tests and conditions.
Bio statistical analysis in clinical research
- 1. 1
- 2. Sample size calculations Dr. Mohamed M. Omran Associated prof. of Biochemistry Biochemistry department Faculty of science Helwan University Bio-statistical analysis in Clinical Research Sample size calculation
- 3. Outlines 1. What is biostatics? 2. Types of data variables 3. Data inputs 4. Normal distribution 5. P value 6. Biostatics tests 7. 95 % confidence interval 8. Correlation 9. Diagnostic performances 10. sample size calculation
- 11. The null hypothesis that there is no significant difference between specified populations, any observed difference being due to sampling or experimental error.
- 14. P Values • The probability that any observation is due to chance alone assuming that the null hypothesis is true • Typically, an estimate that has a p value of 0.05 or less is considered to be “statistically significant” or unlikely to occur due to chance alone. • The P value used is an arbitrary value • P value of 0.05 equals 1 in 20 chance • P value of 0.01 equals 1 in 100 chance • P value of 0.001 equals 1 in 1000 chance.
- 15. Normal distribution (when group individuals less than 30 ) • Most of the biological variables usually cluster around a central value, with symmetrical positive and negative deviations about this point. The standard normal distribution curve is a symmetrical bell-shaped. • In a normal distribution curve, about 68% of the scores are within 1 SD of the mean. • Around 95% of the scores are within 2 SDs of the mean and 99% within 3 SDs of the Mean.
- 18. Comparison between parametric and nonparametric tests
- 22. One way ENOVA 1. Bonferroni is the powerful tests (Equal and non equal groups) 2. Tukey (equal groups) 3. Scheffe (unequal groups)
- 23. McHugh, M. L. (2011). Multiple comparison analysis testing in ANOVA. Biochemia medica: Biochemia medica, 21(3), 203-209.
- 27. Comparing the two OR and RR are usually comparable in magnitude when the disease studied is rare (eg, most cancers). However, an OR can overestimate and magnify risk, especially when the disease is more common (eg, hypertension) and should be avoided in such cases if RR can be used https://www.mappingccs.com/biostatistics
- 28. Correlation
- 30. Correlation
- 31. Statistical box plot Box plots graphically depict numerical data using their descriptive statistics, 0 Mean extreme value , must delete ; * outline value, not delet
- 32. Evaluation of diagnostic performances of markers AUC equal to 1.0 is characteristic of an ideal test, whereas 0.5 indicates a test without diagnostic value. The nearer a curve shifts to the top left and corner of the graph, the more useful the marker is for the diagnosis. Receiver Operating Curve (ROC), Sensitivity , Specificity Positive predictive value (PPV) Negative predictive value (NPV)
- 38. Editor and reviewer comments shock Insufficient sample size !!!!!!!!!
- 40. What do you need prior to sample size calculation?
- 46. Software used for sample size calculation. • Calculation of sample size by medcalc • https://www.medcalc.org/manual/sampling_menu.php
- 47. For TNF The minimal sample size is 68, (34/group)To have a power of 80% to assess whether the TNF is significantly higher in HCV- HCV of ~20.4 (11.6) compared to HCV ass significant fibrosis ~12.6 (11), using a 2 samples means test and a significance level of 0.05 Sample size for difference between two independent means.
- 48. Anther example • For Il10The minimal sample size is 178 (89 per group)To have a power of 80 % to assess whether IL-10 is significantly lower in HCC (of ~14.2 (13)) compared to patients with significant liver fibrosis... (19.7 (13)), using a 2 samples means test and a significance level of 0.05
- 50. Sample size calculation using ROC
- 51. Sample size for sensitivity & specificity. For calculation sensitivity , for a marker for example 70 , CI = 10, sample is 123
- 52. Sample size for correlation analysis.