+ Reply to Thread
Page 3 of 3 FirstFirst 1 2 3
Results 31 to 42 of 42

Thread: Practical significance

  1. #31
    Pirate
    Points: 15,159, Level: 79
    Level completed: 62%, Points required for next Level: 191
    victorxstc's Avatar
    Posts
    875
    Thanks
    229
    Thanked 332 Times in 297 Posts

    Re: Practical significance




    The slides you provided talk about statistical significance and zone of equivalence. The question is about _practical significance_. Your comment is not applicable to the concept of practical significance. Not according to the academic literature. If you are not sure or you cannot substantiate your claim it's best not to mislead other people.
    1. Please recheck the slides to better understand their points, as they didn't talk about statistical significance only.
    2. I'm sure but no need to prove it.
    3. You are here at your own risk. Nobody has guaranteed that you will get the right answer (although I think my answer is OK, and Dason reframed it the best).
    4. The forum rules/guidelines ask that "search before posting".
    5. edited: Rules indicate that "solving homework problems is not preferred" and "only those are helped who show effort".

    Even if you find one or two journal articles they wouldn't provide compelling evidence because the concept needs be widely accepted in the literature.
    1. OK. So please go ahead and put 10 minutes to search, and find at least one article against my word. Then come back and degrade my "a couple of journal articles".

  2. #32
    Pirate
    Points: 15,159, Level: 79
    Level completed: 62%, Points required for next Level: 191
    victorxstc's Avatar
    Posts
    875
    Thanks
    229
    Thanked 332 Times in 297 Posts

    Re: Practical significance

    Quote Originally Posted by Dason View Post
    Also note that the way the problem is worded makes it sound like homework and that: "Would the mean difference be practically significant for the given difference between two mean values and confidence interval?" makes me think that they do care about the confidence interval (although it doesn't seem worded very well).
    I agree that they have emphasized the CI, and it plays some role in this homework question.

  3. #33
    Points: 1,589, Level: 22
    Level completed: 89%, Points required for next Level: 11

    Posts
    61
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Re: Practical significance

    Quote Originally Posted by victorxstc View Post
    1. Please recheck the slides to better understand their points, as they didn't talk about statistical significance only.
    2. I'm sure but no need to prove it.
    3. You are here at your own risk. Nobody has guaranteed that you will get the right answer (although I think my answer is OK, and Dason reframed it the best).
    4. The forum rules/guidelines ask that "search before posting".
    5. edited: Rules indicate that "solving homework problems is not preferred" and "only those are helped who show effort".



    1. OK. So please go ahead and put 10 minutes to search, and find at least one article against my word. Then come back and degrade my "a couple of journal articles".
    I don't need to re-check it. Your slides do not mention practical significance. If there was something on the web to support your claim I would not be asking questions and you would have provided many references by now. I am aware I am here at my own risk but you are arguing just for the sake of it. Frankly, I don't think you understand the concept of practical significance. Maybe you have, since three users in this topic pointed to you, but you are still arguing.

    Stop flooding the topic with useless comments. You are not providing any useful information.

  4. #34
    Devorador de queso
    Points: 95,754, Level: 100
    Level completed: 0%, Points required for next Level: 0
    Awards:
    Posting AwardCommunity AwardDiscussion EnderFrequent Poster
    Dason's Avatar
    Location
    Tampa, FL
    Posts
    12,932
    Thanks
    307
    Thanked 2,629 Times in 2,245 Posts

    Re: Practical significance

    Quote Originally Posted by _joey View Post
    I don't need to re-check it. Your slides do not mention practical significance.
    victorxstc's slides don't mention it explicitly but it is discussed. The sections where they discuss the "range of equivalence" is very heavily connected to the idea of practical significance.


    Frankly, I don't think you understand the concept of practical significance. Maybe you have, since three users in this topic pointed to you, but you are still arguing.
    I believe victorxstc does understand practical significance. Like I said before... I believe that there was a minor misunderstanding and victorxstc is coming from the viewpoint of equivalence testing (which relies heavily on the idea of practical significance). In coming from that viewpoint some of the ideas and terminology isn't directly the same so you might have thought they were talking about something else.
    Stop flooding the topic with useless comments. You are not providing any useful information.
    I believe they were providing some useful information and their comments weren't useless.

    I don't want to see any more bickering in this thread. Now I made mention that it sounded like this was a homework problem and I provided my opinion that the confidence interval needs to be included in the answer. If you still don't agree with that then that's fine but I think there has been some good discussion in this thread so far and I don't want to have to close it so let's just express our views as professionally as possible.
    I don't have emotions and sometimes that makes me very sad.

  5. The Following 4 Users Say Thank You to Dason For This Useful Post:

    bryangoodrich (08-08-2012), CowboyBear (08-07-2012), GretaGarbo (08-08-2012), victorxstc (08-07-2012)

  6. #35
    Points: 1,589, Level: 22
    Level completed: 89%, Points required for next Level: 11

    Posts
    61
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Re: Practical significance

    If he did understand the concept he wouldn't have bragged on 'equivalence'. He has done some work on 'equivalence' in the past. There is a saying when you have a hummer everything looks like a nail.
    I agree about CI should be posted along with p-value. The question is not about CI, p-value or 'equivalence'. It's on practical significance and generally there is nothing in the literature about a value should be outside of CI bounds to be practically significant as he insists. His slides are not mentioning practical significance explicitly either. There may some value in the information he provided; however, I founded it misleading.

    Here is a good start on practical significance for victorxstc
    http://en.wikipedia.org/wiki/Clinical_significance
    Last edited by _joey; 08-07-2012 at 09:31 PM.

  7. #36
    TS Contributor
    Points: 18,889, Level: 87
    Level completed: 8%, Points required for next Level: 461
    CowboyBear's Avatar
    Location
    New Zealand
    Posts
    2,062
    Thanks
    121
    Thanked 427 Times in 328 Posts

    Re: Practical significance

    Quote Originally Posted by _joey View Post
    If he did understand the concept he wouldn't have bragged on 'equivalence'. He has done some work on 'equivalence' in the past. There is a saying when you have a hummer everything looks like a nail.
    Like Dason said, enough with the bickering! This is getting silly.

    (Also: The concepts of equivalence testing and practical significance are very closely related - I feel like you're arguing over nothing worthwhile here)

  8. The Following 2 Users Say Thank You to CowboyBear For This Useful Post:

    Dason (08-07-2012), victorxstc (08-08-2012)

  9. #37
    Probably A Mammal
    Points: 31,087, Level: 100
    Level completed: 0%, Points required for next Level: 0
    bryangoodrich's Avatar
    Location
    Sacramento, California, United States
    Posts
    2,564
    Thanks
    398
    Thanked 618 Times in 551 Posts

    Re: Practical significance

    Quote Originally Posted by _joey View Post
    Stop flooding the topic with useless comments. You are not providing any useful information.
    Wow, Joey. Do you think you're in charge of this thread because you made it? As has been pointed out by people I am well aware are brilliant with statistics here, victorxstc has talked about a concept that is important to the topic of the original post. Like the above quote, all you've done to retaliate is attack victorxstc to substantiate his statements. Frankly, I would have told you to go **** yourself. If you don't think what someone says is correct, then ignore it. This forum is public and the advice can well be useful to someone 2 years from now that stumbles across it. Just because you either don't understand it, don't understand its significance, or just don't care about the perspective doesn't put you in a position to start telling people they're wrong until they prove its methodological significance in academia.

  10. The Following User Says Thank You to bryangoodrich For This Useful Post:

    victorxstc (08-08-2012)

  11. #38
    Probably A Mammal
    Points: 31,087, Level: 100
    Level completed: 0%, Points required for next Level: 0
    bryangoodrich's Avatar
    Location
    Sacramento, California, United States
    Posts
    2,564
    Thanks
    398
    Thanked 618 Times in 551 Posts

    Re: Practical significance

    Quote Originally Posted by _joey View Post
    The difference between two mean values is 103 units
    p-value is 0.00001 at alpha=0.05
    95% confidence interval is (50, 150)
    difference of 100 units is of practical importance.
    Would the mean difference be practically significant for the given difference between two mean values and confidence interval?

    Thanks!
    Your question is pretty ill described. What was the test for which this p-value is stated? What was your hypothesis? That the difference in means is greater than 0? Greater than 100? That's a pretty large CI for such a small p-value. In any case, what if your interval was (-50, 50) and you observed a difference of means of 3. You say a difference greater than 0 is of practical importance. Would you conclude that since 3 is positive that it is of practical importance? By definition, that seems to be true, but I would think the question would be about the population. So in your case, if the experiment was repeated, you might get a mean difference of 50. Sometimes you might get 150. To make a general inference from this sample, you would need to have had a result that is greater than this "margin of equivalence," basically. As victorxstc indicated in his first reply to you, "the results are not conclusive in terms of practical significance." But like I said, your question doesn't seem to be clear to me.

  12. The Following User Says Thank You to bryangoodrich For This Useful Post:

    victorxstc (08-08-2012)

  13. #39
    R purist
    Points: 35,103, Level: 100
    Level completed: 0%, Points required for next Level: 0
    TheEcologist's Avatar
    Location
    United States
    Posts
    1,921
    Thanks
    303
    Thanked 607 Times in 341 Posts

    Re: Practical significance

    Quote Originally Posted by _joey View Post
    I don't need to re-check it. Your slides do not mention practical significance. If there was something on the web to support your claim I would not be asking questions and you would have provided many references by now. I am aware I am here at my own risk but you are arguing just for the sake of it. Frankly, I don't think you understand the concept of practical significance. Maybe you have, since three users in this topic pointed to you, but you are still arguing.

    Stop flooding the topic with useless comments. You are not providing any useful information.
    The flagging of this post as rude, has awakened me from my slumber. I do not like to be awakened.
    I stand with the other mods on this. Please remain friendly, remember that people here are providing you with free help. Oh and M.V.C.'s should really know better. ;
    Quote Originally Posted by bryangoodrich View Post
    Frankly, I would have told you to go **** yourself

    On topic:

    I generally agree with R.E. Kirk (in his paper "Practical Significance: A Concept Whose Time Has Come") there are better measures, like various effect magnitudes (e.g http://sportsci.org/resource/stats/effectmag.html) which, If I am not mistaken are the concepts that victorxstc was hinting towards. This may not truly help you if your homework is specifically concerned with practical significance. However if you want to know more. Look at the work of R.E. Kirk, as he has been an authority on the topic for many years (you will likely see that victorxstc and him are mostly in agreement);

    http://www.sciencedirect.com/science...78375806002424

    Cheers and be good.

    Off topic:

    I wish I could have returned to talk-stats on a friendlier topic.

    This thread would have been locked, but I will not rule against the other mods.

    On a lighter note: Great to be back btw (no more jungle insects!).

    I will give an update soon
    The true ideals of great philosophies always seem to get lost somewhere along the road..

  14. The Following 4 Users Say Thank You to TheEcologist For This Useful Post:

    Dason (08-08-2012), GretaGarbo (08-08-2012), quark (08-08-2012), victorxstc (08-08-2012)

  15. #40
    Human
    Points: 12,676, Level: 73
    Level completed: 57%, Points required for next Level: 174
    Awards:
    Master Tagger
    GretaGarbo's Avatar
    Posts
    1,362
    Thanks
    455
    Thanked 462 Times in 402 Posts

    Re: Practical significance

    I want to thank viktorxstc for the post and link about equivalence testing. (And there is no irony in that.)

    (link )

    The post and the ppt-file taught me things I didn’t know and showed aspect that I was not aware of. Actually I think that link was the must useful in the whole thread.

    (I regret the tone this thread has taken. I think someone somewhere talked about the “nice and friendly atmosphere we should have on the forum”.) (And now I just noticed The Ecologists comment.)

  16. The Following User Says Thank You to GretaGarbo For This Useful Post:

    victorxstc (08-08-2012)

  17. #41
    Pirate
    Points: 15,159, Level: 79
    Level completed: 62%, Points required for next Level: 191
    victorxstc's Avatar
    Posts
    875
    Thanks
    229
    Thanked 332 Times in 297 Posts

    Re: Practical significance

    I think putting the address of this thread (click here) would also help. [edited] My comments in that thread are also a reference to noetsi's kind points in this thread and show my agreement with him.
    Last edited by victorxstc; 08-08-2012 at 12:41 PM.

  18. #42
    Cookie Scientist
    Points: 13,431, Level: 75
    Level completed: 46%, Points required for next Level: 219
    Jake's Avatar
    Location
    Austin, TX
    Posts
    1,293
    Thanks
    66
    Thanked 584 Times in 438 Posts

    Re: Practical significance


    The sleeper has awakened !
    “In God we trust. All others must bring data.”
    ~W. Edwards Deming

+ Reply to Thread
Page 3 of 3 FirstFirst 1 2 3

           




Tags for this Thread

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts






Advertise on Talk Stats