1,655 reputation
21728
bio website
location
age
visits member for 2 years, 11 months
seen Apr 7 at 18:45

Apr
6
awarded  Self-Learner
Mar
20
accepted How many times, in expectation, am I fetching a random sample from a predefined discrete probability distribution of elements?
Mar
19
comment How many times, in expectation, am I fetching a random sample from a predefined discrete probability distribution of elements?
I see what you mean. Another question: How exactly is the expected number of trials until next success is n/(n-k)? I've been trying to derive that from first principles but don't see how we compute that...
Mar
19
comment How many times, in expectation, am I fetching a random sample from a predefined discrete probability distribution of elements?
Interesting. But a clarification: After the 499th element is added, the possible number of trials to get a number not in the set is much larger than 2. Am I missing something here?
Mar
19
asked How many times, in expectation, am I fetching a random sample from a predefined discrete probability distribution of elements?
Feb
5
awarded  Good Question
Jan
31
awarded  Good Question
Jan
19
awarded  Nice Question
Nov
18
comment When designing experiments why is it necessary to have multiple groups run in parallel?
@Glen_b - Yup. That makes sense and was what I was thinking about too. For example, trying out two different methods of teaching, in the same year, is a big resource drain on the faculty members. The costs of context switching is quite high. Does this mean one is just "stuck" and pray to the gods that it's really the difference in teaching and not anything else?
Nov
18
asked When designing experiments why is it necessary to have multiple groups run in parallel?
Oct
31
comment What is the most appropriate test for a multi-year different group/yr experiment?
So, I'm not sure what you mean. Just don't do any significance tests? Does changing the tense of the hypothesis matter? I'm not sure I understand what you're getting at. Honestly, whether it'll continue to support in the future is less of a concern than has it been so over the past? What you are suggesting seems to be a form of "believe me, here's the trend" analysis without anything substantive to back it up.
Oct
30
awarded  Promoter
Oct
27
comment What is the most appropriate test for a multi-year different group/yr experiment?
Ah! I see. I misconstrued your allusion to causality :)
Oct
27
revised What is the most appropriate test for a multi-year different group/yr experiment?
added 46 characters in body
Oct
27
comment What is the most appropriate test for a multi-year different group/yr experiment?
I don't really have causuality. A doesn't cause B. I only say B is better than A for increasing participation. Period. Also, I do have each of the measures for both tools. I've edited the question to reflect that. However, the way the class is designed it's almost impossible to have a control group since there is only so much one can do/manage. So we have to completely remove something we intend to change and replace it for the next years' class.
Oct
27
revised What is the most appropriate test for a multi-year different group/yr experiment?
edited title
Oct
27
asked What is the most appropriate test for a multi-year different group/yr experiment?
Oct
27
accepted What is the intuition behind (M)ANCOVA and when/why should one use it?
Oct
25
comment What is the intuition behind (M)ANCOVA and when/why should one use it?
Makes sense. When you say "control for it" does it mean "just add it to the equation" (e.g., as an IV on the RHS of the equation) or is there something more subtle? Sorry, I'm not a statistician by trade. I just happen to keep stumbling into using it and seek clarification of the terms so as to not confuse myself.
Oct
25
comment What is the intuition behind (M)ANCOVA and when/why should one use it?
Could you please clarify what this means: ...while controlling for a set of continuous nuisance variables? What does 'controlling' mean w.r.t. the math?