- This topic has 4 replies, 3 voices, and was last updated 12 years, 5 months ago by
.
-
Posts
-
My burning question at this moment:
S-IC-5: Use data from a randomized experiment to compare two treatments
Are we talking about what could be a formal significance test? Would a task that asked students to conduct a significance test assess this standard? Should it be more open ended, just getting them to think about how sampling distributions behave?
No, I would say this does not included formalized significance tests, but is more a matter of understanding how sampling works through simulations of sampling distributions, for example. There are some examples in the high school statistics progression, for example the relation between caffeine and finger-tapping (an experiment I find particularly relevant as I type this).
We broke down Standard S.IC.5 in the following way:
-Compare two treatments means/proportions with a resampling technique (simulation software) to test whether results are random or significant.
What are your thoughts?
We are breaking down S-IC-5 and interpreted it to the following statement
– compare two treatment means with a re-sampling technique(with computer software) to test whether results are random or significant.
What are your thoughts on that interpretation?
This captures most of the standard, namely comparing the means of two treatments and deciding whether the difference is significant. The standard talks about comparing parameters, and the mean is just one parameter. But it is probably the one you will most often look at when comparing to treatments. You might, however, see a difference in standard deviations, or one of the quartiles, and want to know if that difference is significant as well. Also, I’m not completely sure what you mean by a resampling technique, but I suppose it is the same as as a simulation, which is the word the standard uses.
- You must be logged in to reply to this topic.