Blocking vs Stratified Random Sample
Both terms below come up in the same part of the course, and students mix them up. Here is each one defined on its own, side by side, so you can see where they part company.
Blocking
Collecting data and study design
Blocking groups similar experimental units together before random assignment, then randomizes the treatments within each block to sharpen the comparison.
Blocking pulls a known source of extraneous variation out of the treatment comparison instead of letting it sit in the noise. For example, if you expect men and women to respond differently to a training program, block by sex and randomly assign the programs within each group so every program is tried on both. Blocking is the experimental analogue of stratifying in sampling, but the two are not the same move: you stratify a population before selecting a sample, and you block experimental units before assigning treatments. Both build groups that are similar inside, and only blocking involves random assignment.
Stratified random sample
Collecting data and study design
A stratified random sample splits the population into similar groups called strata, then takes a separate simple random sample from each stratum.
Stratifying groups individuals who resemble each other on something relevant, then samples within every group, which can give more precise estimates than a plain simple random sample. For example, you might split students into grade levels and draw a random sample from each grade so every grade is represented. The strata should be internally similar but different from one another. You then combine the results across strata to estimate the population value.