Why to know statistics
- 1. Why to know statistics
- 3. Example One of your colleague is an oncology surgeon 60% of his cases died Does this mean that he is a looser!!
- 4. We should ask what are the results of his colleagues in similar patients How many patients he operated upon e.g 2/3!!!!
- 6. Example Diastolic Blood pressure 80,70,65,90,74,80,60,90,60,75,80,90,100,100,100,95 Age 24,30,26,40,28,21,26,31,32,36,27,45,62,58,52,50,60
- 7. Vital for research Without the use of statistics it would be very difficult to make decisions based on the data collected from a research project
- 8. Statistical steps in research Collect data Organise data Analyse data Interpret the data Present the data
- 9. How to read the results An understanding of basic statistics will provide you with the fundamental skills necessary to read and evaluate results section in published papers
- 10. Are groups comparable!!! the baseline characteristics of the groups being studied should be comparable If not, they should be adjusted for differences
- 11. statistical tests Are they frequently used tests!! If not, why!!
- 12. Are the data analysed according to the original protocol?
- 13. Was follow- up complete? Patients lost to follow-up ……… loss of subjects bias > 10% - 15 % ………………… ..invalid results
- 14. P value A P value of <0.05 means that this result would have arisen by chance on less than one occasion in 20
- 15. Standardization of measures of outcome: Odds and odds ratio The odds is the number of patients who fulfil the criteria for a given endpoint divided by the number of patients who do not.
- 16. For example the odds of diarrhoea during treatment with an antibiotic in a group of 10 patients may be 4 to 6 (4 with diarrhoea divided by 6 without, 0.66); in a control group the odds may be 1 to 9 (0.11). The odds ratio of treatment to control group would be 6 (0.66÷0.11).
- 17. Risk and relative risk The risk is the number of patients who fulfil the criteria for a given end point divided by the total number of patients.
- 18. For example, the risk of diarrhoea during treatment with an antibiotic in a group of 10 patients may be 4 to 10; in the control group the risks may be 1 to 10. The relative risk of treatment to control group would be 4 (0.4÷0.1).
- 19. C.I The confidence interval around a result in a clinical trial indicates the limits within which the "real" difference between the treatments is likely to lie, hence the strength of the inference that can be drawn from the result
- 20. Example: 95 % CI for RRR 25 % : sample size 100 …………… .= -- 38 % to 59 % Sample size 1000 ………… .= 9 % to 41 % The larger the sample size , the narrower and more precise the CI , and the greater our confidence that the true RRR is closer to what we have observed .
- 21. OR = 0.34, 95% CI 0.23 - 0.52 Odds Ratio < 1 decreased risk Confidence Interval does not cross 1 statistically significant
- 22. A statistically significant result may not be clinically significant.
- 23. The results of intervention trials should be expressed in terms of the likely benefit an individual could expect (for example, the absolute risk reduction)
- 24. How large was the treatment effect ? Treatment effect …………… .. Adverse outcome e.g.; Risk of outcome without therapy ( baseline risk ) X ( = 20 % or 0.20 ) Risk of outcome with therapy Y ( = 15% 0r 0.15)
- 25. Absolute risk reduction= X -- Y 0.20-0.15= 0.05 Relative risk ( RR )= Y / X = 0.15 /0.20 = 0.75 Relative risk reduction ( RRR ) = { X -- Y/ X } x 100 % = 0.05 / 0.2 x 100%= 25 % i.e : therapy reduced the risk of the outcome by 25 % relative to that occurring among the controls
- 26. the greater the RRR, the more effective the therapy.
- 27. Example: M.I patients receiving medical treatment have a chance of 404/1324=0.305 or 30.5% of being dead at 10 years. Let us call this risk x . Patients randomised to coronary artery bypass grafting have a chance of 350/1325=0.264 or 26.4% of being dead at 10 years. Let us call this risk y .
- 28. RR The relative risk of death — that is, the risk in surgically treated patients compared with medically treated controls — is y/x or 0.264/0.305=0.87 (87%).
- 29. RRR The relative risk reduction — that is, the amount by which the risk of death is reduced by the surgery — is 100%-87% (1- y / x )=13%.
- 30. ARR The absolute risk reduction (or risk difference) — that is, the absolute amount by which surgical treatment reduces the risk of death at 10 years — is 30.5%-26.4%=4.1% (0.041).
- 31. NNT The number needed to treat — how many patients need coronary artery bypass grafting in order to prevent, on average, one death after 10 years — is the reciprocal of the absolute risk reduction: 1/ARR=1/0.041=24.
- 32. Conclusion to be able to effectively conduct research to be able to read and evaluate journal articles to further develop critical thinking and analytic skills to know when you need to hire outside statistical help