Lesson #3: Random Assignment of 40 Subjects in Blocks of 4
In Lesson 2, 40 volunteers were randomly assigned to one of 4 experimental conditions, but the result was that only 7 participants ended up in Condition 1, whereas twice as many ended up in Condition 2. This kind of imbalance is common in random assignment, just as tossing a coin 20 times often leads to something other than exactly 10 Heads and 10 Tails.
Unfortunately, however, large differences in sample size across experimental conditions can reduce statistical power and violate the assumptions of certain statistical tests. One way around this problem is to use a "blocked design" in which participants are randomly assigned within a block of trials while keeping sample sizes equal across conditions. In the drug trial from Lesson 2, for example, we could break the 40 volunteers into 10 blocks of 4 participants each. We would then randomly assign each of the four participants within a block to one of the four experimental conditions.
In other words, if Participant #1 in the first block were randomly assigned to Condition 4, this would leave Conditions 1, 2, and 3 for the other participants in that block. Then, if Participant #2 were randomly assigned to Condition 1, that would leave Conditions 2 and 3 for the remaining participants. Finally, if Participant #3 were assigned to Condition 2, that would leave only Condition 3 for the last participant in that block. Then the process would be repeated for each of the other 4-trial blocks, until all 40 volunteers had an assigned condition.
To generate random numbers for this kind of blocked design, you would simply fill out the Randomizer form for 10 sets of 4 unique, unsorted numbers with a range from 1 to 4 (representing the condition numbers). For this example, we will also use the "Place Markers Across" viewing option to simplify interpretation of the results.
Random Sample of 50 Subjects from a Population of 643
Random Assignment of 40 Subjects to 4 Conditions
Random Assignment of 40 Subjects in Blocks of 4
Random Sample of 100 Telephone Numbers
Random Ordering (Assignment) of 25 Items on a Test
