What does the alpha level control in hypothesis testing?

• A. Controlling the alpha level in a study primarily limits the risk of a Type I error.
• B. The alpha level determines the probability of a Type II error.
• C. The alpha level affects the p-value directly.
• D. The alpha level controls the sample size.

Answer: (A)

The alpha level is the significance threshold you set before collecting data. It directly controls the probability of making a Type I error—rejecting a true null hypothesis. For example, with an alpha of 0.05, you’re accepting a 5% chance of a false positive across many repeated tests. The other ideas aren’t what alpha controls: Type II error relates to failing to detect a real effect and depends on power, sample size, and true effect size (alpha can influence power, but it doesn’t directly set Type II error). The p-value comes from the data itself, and alpha is simply the cutoff used to decide significance, not a factor that changes the p-value. Sample size is determined by power considerations and practical constraints, not by the alpha level alone.