In the context of a lab experiment, what is done to extraneous variables?

In the context of a lab experiment, what is done to extraneous variables?

• A. The dependent variable is held constant
• B. All other variables that might influence results are held constant or eliminated
• C. The sample size is increased to reduce extraneous effects
• D. The randomization procedure eliminates extraneous variables

Answer: (B)

Controlling extraneous variables means keeping all other factors that could influence the outcome constant or removing them entirely. In a lab experiment, this standardization is what allows you to see whether changes in the dependent variable really come from the manipulated variable. By keeping conditions the same—such as room temperature, time of day, instructions, equipment, and procedures—you reduce alternative explanations for any observed effects, which strengthens internal validity. Holding the dependent variable constant would erase what you’re trying to measure, so that isn’t appropriate. Merely increasing the sample size helps with precision and reducing sampling error, but it doesn’t address other variables that could skew results. Randomization helps distribute extraneous variables across conditions, reducing systematic bias, but it doesn’t eliminate those variables entirely. The aim is to hold constant or eliminate extraneous variables to isolate the effect of the manipulation.

Controlling extraneous variables means keeping all other factors that could influence the outcome constant or removing them entirely. In a lab experiment, this standardization is what allows you to see whether changes in the dependent variable really come from the manipulated variable. By keeping conditions the same—such as room temperature, time of day, instructions, equipment, and procedures—you reduce alternative explanations for any observed effects, which strengthens internal validity.

Holding the dependent variable constant would erase what you’re trying to measure, so that isn’t appropriate. Merely increasing the sample size helps with precision and reducing sampling error, but it doesn’t address other variables that could skew results. Randomization helps distribute extraneous variables across conditions, reducing systematic bias, but it doesn’t eliminate those variables entirely. The aim is to hold constant or eliminate extraneous variables to isolate the effect of the manipulation.