What are four possibilities in testing whether the treatments differ?

- The treatments do not differ, and we correctly conclude that they do not differ.
- The treatments do not differ, but we conclude that they do differ.
- The treatments differ, but we conclude that they do not differ.
- The treatments do differ, and we correctly conclude that they do differ.

What is a type I error?

Concluding that there is a difference between two treatments when there actually is NO difference.

What is a type II error?

Concluding that two therapies do not differ when they actually DO differ.

∝

symbol for the probability of making a type one error.

Is also called a P value (P<0.5)

β

symbol for the probability of making a type II error.

What does P< 0.5 mean?

It tells us that we have concluded that therapy A differs from therapy B on the basis of the sample of subject included in our study.

The probability that such a difference could have arisen by chance alone and that this difference between our groups does not reflect any true difference between therapies A and B is only .05 or 1in 20.

what is 1-β?

This is a probability that a study will determine if there is a difference between therapies. It is called the POWER of the study. It tells us how good our study is at determining a difference.

What must be specified to estimate the sample size needed in a randomized trial?

- The difference in response rates to be detected.
- An estimate of the response rate in one of the groups.
- The level of statistical significance (alpha)
- The value of the power desired (1-β)
- Whether the test should be one-sided or two-sided.

What does a one sided test do?

A one sided test only tests for the difference in treatments for one direction. Such as only looking for improvements.

What does a two sided test do?

It is a study that is just looking at the difference between treatments (direction does not matter).

What is a benefit of a one-sided test?

It requires a smaller sample size.

What is a drawback of a one-sided test?

Sometimes treatments have the opposite effect that is not being studied (harms when the study only looks at improvement).

What is the formula for Efficacy of an agent (treatment) ?

Efficacy= (rate in those on placebo)-(rate in those who received treatment) / rate in those who received the placebo

The formula of efficacy tells us what?

The formula tells us the extent of the reduction in disease by use of the treatment.

In order to make RCT relevant to practice that results are used to estimate the number of patients who would need to be treated (NNT) to prevent one adverse outcome such as death.

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

The example is that the mortality rate in the untreated group is 17%and mortality in the treated group is 12% we would need to treat

1/17%-12% or 1/0.05=20

What is internal validity?

A study properly randomized. It is designed without major methodological problems and takes into account all the issues discussed that outline problems with studies.

What is external validity?

Also known as generalizability. The ability of a study to work no matter where it is conducted. Able to generalize findings to all patients with the disease.

What are the phases of drug trials?

Phase I studies are clinical pharmacologic studies- small studies of 20 to 80 people

PhaseII clinical investigations of 100-200 patients for efficacy and relative safety.

Phase III is large scale randomized controlled trials for effectiveness and relative safety. After phase III a drug can be licensed for marketing.

Phase IV Is postmarketing surveillance that examines the long term effect of a drug on large populations.

Randomized controlled trials can be used for two major purposes:

- To evaluate new forms of intervention before they are approved and recommended for general use.
- to evaluate interventions that are highly controversial or that have been widely used or recommended without having been adequately evaluated.

When are randomization studies ethical?

Only when we do not know whether drug A is better then drug B.