If you're seeing this message, it means we're having trouble loading external resources on our website.

If you're behind a web filter, please make sure that the domains *.kastatic.org and *.kasandbox.org are unblocked.

Main content

The language of experiments

Karina wants to determine if kale consumption has an effect on blood pressure. She recruits 100 households and randomly assigns each household to either a kale-free diet plan or a kale-based diet. At the end of two months, she plans to record the original and final blood pressures for members of each household.
Problem 1
What is the explanatory variable?
Choose 1 answer:

problem 2
What is the response variable?
Choose 1 answer:

Problem 3
What are the treatments?
Choose 1 answer:

problem 4
Who or what are the experimental units?
Choose 1 answer:

Want to join the conversation?

  • starky seedling style avatar for user caitlyn.leclair
    Why wouldn't the answer for problem 4 be the members of each household?
    (35 votes)
    Default Khan Academy avatar avatar for user
  • spunky sam blue style avatar for user Mircea Nemteanu
    Words are slippery. The last question expects as correct answer the households, not their members. Makes me scratch my head and and ironically conclude: "Aha! So it is the households who eat (or not) the kale, not the household members".
    (12 votes)
    Default Khan Academy avatar avatar for user
  • aqualine seed style avatar for user samuel_arena
    why didnt seattle just run the ball..
    (12 votes)
    Default Khan Academy avatar avatar for user
  • blobby green style avatar for user bongiinnocentia17
    If the household members are not the experimental units, then what are they?
    (10 votes)
    Default Khan Academy avatar avatar for user
    • blobby green style avatar for user daniella
      If the household members are not considered the experimental units, then they are the subjects or participants of the experiment. In this study, the household members are the individuals whose blood pressure measurements are being recorded before and after the two-month period. Therefore, they are the subjects or participants of the study.
      (2 votes)
  • blobby green style avatar for user 120738
    The voices are getting louder the voices are getting louder the voices are getting louder the voices are getting louder the voices are getting louder the voices are getting louder the voices are getting louder the voices are getting louder the voices are getting louder the voices are getting louder the voices are getting louder the voices are getting louder the voices are getting louder the voices are getting louder the voices are getting louder the voices are getting louder the voices are getting louder the voices are getting louder the voices are getting louder the voices are getting louder the voices are getting louder the voices are getting louder the voices are getting louder the voices are getting louder the voices are getting louder the voices are getting louder the voices are getting louder the voices are getting louder the voices are getting louder the voices are getting louder the voices are getting louder the voices are getting louder the voices are getting louder the voices are getting louder
    (5 votes)
    Default Khan Academy avatar avatar for user
  • boggle purple style avatar for user Muhammad Amaanullah
    What can be the possible source of bias here ?
    (4 votes)
    Default Khan Academy avatar avatar for user
    • blobby green style avatar for user daniella
      Possible sources of bias in the study could include:

      Selection bias: if households are not randomly selected or assigned to treatment groups.
      Measurement bias: if blood pressure measurements are inaccurate or inconsistent.
      Non-response bias: if participants drop out or refuse to participate.
      Reporting bias: if participants do not accurately report their adherence to the diet plan.
      Observer bias: if individuals recording blood pressure are aware of the assigned treatment group and this influences their measurements.
      (2 votes)
  • starky seedling style avatar for user tsorcinelli
    number 4 should it be all of the people in the house and not just say it was a household?
    (2 votes)
    Default Khan Academy avatar avatar for user
    • blobby green style avatar for user daniella
      Yes, in Problem 4, it could be argued that the experimental units should encompass all the people in the house rather than just referring to the household. This distinction is crucial because the treatment (kale-based or kale-free diet) is applied at the household level, but the responses (changes in blood pressure) may vary among individual members within each household. Therefore, specifying the experimental units as "the members of each household" would provide a more comprehensive understanding of who or what is being studied in relation to the treatments and responses.
      (1 vote)
  • blobby green style avatar for user Andrew Baxley
    Isn't number 4 each individual member?
    (1 vote)
    Default Khan Academy avatar avatar for user
    • blobby green style avatar for user daniella
      In Problem 4, the experimental units are correctly identified as "The households." However, it's essential to note that while the households are the experimental units in this study design, the analysis of the data collected (such as changes in blood pressure) may involve individual members within each household. So, each individual member could be considered a unit of analysis within the households.
      (1 vote)
  • leaf green style avatar for user jmxxvi26
    what does confounding mean
    (1 vote)
    Default Khan Academy avatar avatar for user
    • blobby green style avatar for user daniella
      Confounding refers to a situation in which the effect of one variable on the outcome of interest (the dependent variable) is mixed with the effect of another variable that is not accounted for in the analysis. Essentially, a confounding variable is a third variable that is related to both the independent variable (the variable being studied or manipulated) and the dependent variable (the outcome of interest).
      (1 vote)
  • blobby green style avatar for user Renzo ChaseC
    this was very easy
    (1 vote)
    Default Khan Academy avatar avatar for user