A medical researcher is concerned about mistakenly concluding that a new medication is effective when it really is not. What type of error is the researcher concerned about making (Type I or Type II)? Describe what the researcher might do to decrease the likelihood of making that type of error. Discuss ramifications of your suggested approach for other types of error in the study.

 

That is an example of Type I error or false-positive. This means that the researcher rejects the null hypothesis when in fact it is true.

To reduce the risk of committing Type I error, you can reduce the value of the significance level in your study. However, the consequence/ramification of reducing the likelihood of Type I error, a higher chance of making a Type II error is expected.

Step-by-step explanation

Null hypothesis: The new medication is not effective.

Alternative hypothesis: The new medication is effective.

There are two types of error in hypothesis testing. The first one is the Type I error. This occurs when the researcher rejects the null hypothesis when it was actually true. It was also referred as the false-positive error. In the above situation, the medical researcher have concluded the effectivity of a new medication that was not really effective.

The second type is the Type II error or false-negative. This occurs when the researcher fails to reject the null hypothesis when it was false. In an instance, the medical researcher concluded that the new medication was not effective but in fact it was effective.

You can reduced the probability of committing a Type I error when you reduce the value of significance (α) level. Significance level was the probability of making wrong judgment/decision when the null hypothesis is true. Usually, the significance level was set at α=0.05; wherein there is a 95% chance that the result is true and 5% of error can be expected. However, in the medical field, the α is set to 0.01. This means that you can expect a 99.99% chance that the result of you research is true or accurate. In addition, there is little (0.01%) to no room for error in this kind of testing because a matter of life and death was at stake.

To reduce the risk of committing Type II error, you should ensure that your test has enough power. This means that you should have a sample size large enough to detect a practical difference when one truly exist.

However, Type I and Type II error have an indirect or inverse relationship. This means that as the likelihood of committing Type I error increases, the chances of having a Type II error decreases, and vice versa. Given so, the consequence of reducing the significance level to avoid Type I error leads to increasing the chance of Type II error (concluding that the medication is not effective when it was). In addition, making a Type I error means that changes or interventions made was unnecessary, thus wasting time and resources. On the other hand, the consequence of Type II error leads to status quo (stagnation/being stuck/no change happened) when change was needed.