# Ch. 8) Randomized Trials: Some Further Issues Flashcards

How many subjects do we have to study? When is the best time to answer this question? And How do we answer this question?

The best time to answer this question is before the study is done. Thus, in order to determine how many people are available to be studied, we must obtain a sample size from population A and B.

What 4 possibilities can occur when testing whether or not the treatments differ from each other?

1) The treatments do not differ, and we correctly confer that they do not differ.

2) The treatments do not differ, but we conclude that that they do differ. ( This conclusion is based on our samples is in error)

3) The treatments differ, but we conclude that they do not differ. ( This conclusion is in error)

4) The treatments do differ, and we correctly conclude that they do differ.

What is the difference between a Type I and a Type II Error?

Type I: When there is no difference between the therapies, only the samples of the subjects included in the study. (cell c)

Type II: There is a difference between the therapies and but on the basis of the samples included within our study we conclude there is no difference. (cell b)

How do we know what our probability of knowing that we made a type I error?

Type I error is designated by alpha and the P-value which tells us the probability we have come to the conclusion that the therapy A differs from therapy B on the basis of sample of subjects. By chance alone.

What is the Probability of making a type II error? What is the “power of the study”?

Because the the total of all probability is equal to 1 and the probability of making a type II error is equal = ß

The Power of study = (1-ß), tells us how good our study is at correctly identifying the difference between therapies if there is one.

What factors must be specified in order to estimate the sample size needed in a randomized trail?

1) The difference in response rate to be detected

2) An estimation of the response rate in one of the groups

3) Level of statistical significance (∂)

4) The value of Desired (1-ß)

5) Whether the test should be one sided or two sided

What is Efficiency and how do we calculate it?

Efficiency can be expressed as the in terms of the rates of developing the disease in the vaccine and the placebo group.

Efficiency = (Rates those who received the placebo - Rates who received the vaccine/ Rates in those who relied the placebo)

*Tells us the extent of the reduction of disease by the use of the vaccine

How do we use the NNT formula to calculate the the number of patients who need to be treated?

NNT= ( 1/ Rate in untreated group or (mortality rate) - rate in treated group)

True or False: The Ultimate objective is to be able to generalize the results beyond the study population itself and thus if properly conducted without any methodological problems. In addition to all of the issues previously discussed the study is said to have internal validity.

True.

True or False: Generalizability or External Validity refers to the extent to which the application of the findings can be representative of all the patients whom have the disease.

True.

What are the Phases of testing a New Drug In the U.S.?

Phase 1) Studies are clinical pharmacological studies of about (20-80 patients)

Phase 2) Clinical investigations for efficacy and relative safety (100-200 patients)

Phase 3) Large scale randomized controlled trials for effectiveness and relative safety, which are often multi-centered.

Phase 4) Postmarketing surveillance, are important for monitoring new agents as they come into general use..

What are a few of the ethical considerations that you must consider when conducting a randomized trial?

1) Randomization is only ethical when we do not know whether treatment A or B is better.

2) The ethics of Randomization should be asked in both directions randomization or non randomization

3) Can informed consent truly be obtained

4) Under what circumstances should the study be ended earlier than originally designed due to positive or negative effects

What 2 major purposes can randomized controlled trials be used for?

1) To evaluate new forms of intervention before the are approved and recommended for general use.

2) To evaluate interventions that are highly controversial or have been widely used and recommended without being adequately evaluated.

True Or False. All clinical trials of medical interventions must be registered in a public registry before any participants are enrolled in the study to prevent biased publications. Such medical interventions include drugs,surgical procedures, devices,behavioral treatments, and processes of health care.

True

What is Biased Publication?

Biased Publication is the net concealment of data, resulting in the effectiveness of an agent and its safety so that regulators, physicians, and the public are prevented from making an evidence based decision.