* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project
Download problem_set_three
Survey
Document related concepts
Compounding wikipedia , lookup
Drug design wikipedia , lookup
Polysubstance dependence wikipedia , lookup
Pharmacognosy wikipedia , lookup
Prescription drug prices in the United States wikipedia , lookup
Neuropharmacology wikipedia , lookup
Drug discovery wikipedia , lookup
Drug interaction wikipedia , lookup
Theralizumab wikipedia , lookup
Pharmaceutical industry wikipedia , lookup
Prescription costs wikipedia , lookup
Transcript
Follow-up Exercises for Session Three: EBM 811: 1. Drug A is being compared to Drug B in the treatment of malignant hypertension. The hypothesis that there is no difference in blood pressure reduction between the two agents is termed: a. the assumption b. the null hypothesis c. Type I error d. the alternate hypothesis e. the relative risk ratio 2. Drug A is being compared to Drug B in the treatment of malignant hypertension. The hypothesis that there is greater than 5 mm mercury difference in blood pressure reduction between the two agents is termed: a. the assumption b. the null hypothesis c. Type I error d. the alternate hypothesis e. the relative risk ratio 3. Drug A is found to reduce blood pressure greater than Drug B by 5 mm with p = 0.05. The p means: a. the chance is < 5% of the therapy being effective b. Drug A is 5% (i.e. 5 mm) more effective than Drug B c. the chance of seeing this result is <5% if there is no real difference d. the power of the study 4. Based on this study, we conclude that Drug A is significantly better than Drug B in reducing blood pressure. If, in fact, we are wrong and there really is no difference between the drugs we have committed: a. a type I error b. a type II error c. a null hypothesis d. an alternate hypothesis e. a mortal sin Session Three page 1 of 1 5. The risk of a Type I error is: a. the p value b. alpha c. the chance of a false positive study d. all of the above 6. Would you use Drug A or Drug B? Why _______________________________ _______________________________________________________________ 7. The smaller the treatment effect: a. the smaller the study needs to be b. the larger the study needs to be c. has no effect on study size 8. In another study, Drug A is found not to reduce blood pressure greater than Drug B. (p > 0.05) If, in fact, there is a real difference, we have committed: a. a type I error b. a type II error c. a null hypothesis d. an alternate hypothesis e. a misdemeanor 9. The risk of a Type II error is: a. the p value b. alpha c. the chance of a false negative study d. all of the above 10. Fifty male and 50 female patients were asked if they preferred a male or female nurse to assist with their care using a Likert scale as below. 1 2 3 4 5 Prefer Male Exclusively Prefer Male Some Doesn’t Matter Prefer Female Some Prefer Female Exclusively Results revealed: Male Mean = 2.93 Female Mean = 3.12 P= .75 The author concluded that patients did not care if the nurse was male or female. Do you agree? _________________________________________________________________ _________________________________________________________________ _________________________________________________________________ _________________________________________________________________ Session Three page 2 of 2 11. Drug A is found to reduce the five year mortality from MI by 45% . Drug B however in comparison is found to only reduce the actual mortality by 1%. Drug C is under investigation and is promising to save one patient life for every 100 patients treated. Which drug do you choose? Why? _________________________________________________________________ _________________________________________________________________ _________________________________________________________________ _________________________________________________________________ 12. The mean GCS of patients requiring neurosurgical operative intervention was found to be 11. In those patients not requiring intervention, the mean was 13. A Student’s ttest was used and this difference was found to be significant. (p<0.05) Do you believe this? _________________________________________________________________ _________________________________________________________________ _________________________________________________________________ _________________________________________________________________ 13. Match the statistical test and its description: a. Students t test b. Wilcoxon rank sum test (Mann-Whitney U test) c. Chi-square test d. Fisher’s exact test e. One-way ANOVA f. Kruskal-Wallis _____ Used to test whether or not the means of measurements from two groups are equal. assuming that the data are normally distributed and that the data from both groups have equal variance. _____ Used to test whether two sets of observations have the same distribution. These tests are similar in use to the t test, but do not assume the data are normally distributed. _____ Used with categoncal variables (two or more discrete treatments with two or more discrete outcomes) to test the null hypothesis that is no effect of treatment on outcome. assumes at least 5 expected observations of each combination of treatment and outcome, under the null hypothesis. _____ Used in an analogous manner to the chi-square test, this test may be used even when less than 5 observations are expected in one or more categories of treatment and Outcome. _____ Used to test the null hypothesis that three or more sets of continuous data have equal means. assuming the data are normalily distributed and that the data from all groups have identical variances. Session Three page 3 of 3 _____ This is a non-parametric test analogous to the one-wax ANOVA. No assumption is made regarding normality of the data. The test may be thought of as a Wilcoxon rank sum test for three or more groups. 14. Drug A is found to reduce blood pressure greater than Drug B by 20.0 mm with 95% confidence interval 5.4-28.2. This means: a. Drug A is equivalent to Drug B b. the p value is between 5.4 and 28.2 c. the true range of blood pressure reduction might be 5.4 to 28.2 mm Hg d. a type I error has occurred 15. A 95% confidence interval that includes zero treatment difference implies that a. there is a statistical but not clinical difference b. there is a clinical but not statistical differnece c. there probably is no statistical differece in the two groups d. there is a clear advantage to one treatment over the other 16. One study finds a 20% absolute improvement in mortality for a treatment compared to placebo with 95% confidence intervals -5% to 35%. The Study had a p > 0.05. What do you conclude? _________________________________________ _______________________________________________________________ _______________________________________________________________ _______________________________________________________________ 17. Another study finds a 20% absolute improvement in mortality for a treatment compared to placebo with 95% confidence intervals 15% to 28%. . What do you conclude? ______________________________________________________ _______________________________________________________________ _______________________________________________________________ _______________________________________________________________ 18. A third study finds a 0% absolute improvement in mortality for a treatment compared to placebo with 95% confidence intervals -5% to 5%. The Study had a p > 0.05. What do you conclude? ________________________________________ _______________________________________________________________ _______________________________________________________________ _______________________________________________________________ 19. Drug A is found to reduce blood pressure greater than Drug B by 2 mm Hg with 95% C.I. of 1.8 to 2.1 mm. a. there is a statistical but not clinical difference b. there is a clinical but not statistical differnece c. there probably is no statistical differece in the two groups d. there is a clear advantage to one treatment over the other Session Three page 4 of 4 20. In a study to determine antibiotic effectiveness, 200 patients are given either A or B antibiotic randomly assigned. Of those 100 patients taking A, 100 completed the course and 50 improved resulting in a 50% treatment effectiveness. Of those 100 patients taking B, 50 completed the course and 25 improved resulting in a 50% treatment effectiveness in those that took the drug. The authors conclude that the drugs are equally effective. Do you agree? Why? _________________________ _______________________________________________________________ _______________________________________________________________ _______________________________________________________________ 21. Discuss the difference between a therapy “A” that reduces mortality from 2% to 1%. (a 50% relative risk reduction) and a therapy “B” that reduces mortality from 50% to 25% ( a 50% relative risk reduction). __________________________________ ________________________________________________________________ ________________________________________________________________ ________________________________________________________________ 22. The Absolute risk reduction for therapy A is 2% - 1% = 1%. You would have to treat how many patients to benefit one patient? a. 1 b. 4 c. 100 d. 1000 23. The Absolute Risk Reduction for therapy B is 50% - 25% = 25%. You would have to treat how many patients to benefit one patient? a. 1 b. 4 c. 100 d. 1000 24. If you are selling Drug A, how do you “spin” the results of the above study? ________________________________________________________________ ________________________________________________________________ ________________________________________________________________ 25. We found a correlation between blood pressure and mortality with R = 0.5. The increased mortality accounted for by this blood pressure elevation was: a. 5% b. 25% c. 50% d. 75% e. not enough information Session Three page 5 of 5 26. The degree of correlation found (0.5) is: a. strong b. moderate c. weak d. negligible 27. Due to the correlation found in problem # 25, we can say that elevated blood pressure is the cause of increased mortality. a. true b. false 28. Data from a new drug indicate: Placebo Drug Death Rate 20% 10% The baseline death rate without the drug is ________% The RRR for death is _______________ % The ARR for death is _______________ The NNT for death is _______________ 29. Data from the same drug indicate: Placebo Drug Hair Loss Rate 10% 50% The baseline hair loss rate without the drug is ________% The “RRR“ for hair loss is _______________ % ** note the sign!!** The “ARR” for hair loss is _______________ The “NNT” for hair loss is _______________ When the sign is NEGATIVE this implies that the therapy has risk and we rename the RRR to RRI (relative risk increase) and ARR to ARI (absolute risk increase) The NNT becomes NNH (number needed to harm. For the above, we need to treat 10 to save one from death with the risk of causing hair loss in every 2.5 persons treated Session Three page 6 of 6