What are the top 20 useful (but simple) analytic tools that John Tukey proposed. Especially ones you have applied and found really useful. I will suggest: - smoothing - ladders of powers - outside and far out values ......


closed as primarily opinion-based by Glen_b Feb 8 '17 at 22:22

Many good questions generate some degree of opinion based on expert experience, but answers to this question will tend to be almost entirely based on opinions, rather than facts, references, or specific expertise. If this question can be reworded to fit the rules in the help center, please edit the question.

  • 5
    $\begingroup$ Not only opinion-based but too broad/ a big-list type question. See the section of the help on types of questions to avoid, particularly the first three items in the list of things to avoid. If it were to be edited to refocus it enough to reopen the title would in need of alteration as well as it is not indicative of the nature of the question. $\endgroup$ – Glen_b Feb 8 '17 at 22:23
  • $\begingroup$ @Glen_b Understood but how can It be narrowed down I think it would be a very useful reference list if it could be created. $\endgroup$ – James65 Feb 8 '17 at 22:33
  • 3
    $\begingroup$ "Reference list" type questions are not suited to the stackexchange model. See for example, the answer here which comes from a blue-diamond mod (i.e. a StackExchange employee). It says things like "we specifically forgo asking these types of questions because they are not a good fit for this type of Q&A site" and "the Big List breaks down the whole premise of why we created these sites in the first place". We did have a few of that type of question early on but if they were asked now they would close. $\endgroup$ – Glen_b Feb 8 '17 at 22:37
  • 2
    $\begingroup$ There's something of a grey area where we can sometimes tolerate something that may become a list -- e.g. where it's not clear if there are any instances of some object ("can this ever happen?" or "does this always happen" may be legitimate sorts of questions that might lead to people posting examples or counterexamples respectively), so some things that end up having lists may be more-or-less okay, but in general a call like this one is simply not suited to the stackexchange model. $\endgroup$ – Glen_b Feb 8 '17 at 22:43
  • 2
    $\begingroup$ Many fine posts don't fit the model here. If asked here, it would be a suitable question for chat, either in Ten Fold or in its own room. If you wish to discuss the policy as applied here in crossvalidated, meta would be a good place for that (but we're not likely to be able to do more than perhaps discuss the placement of the dividing line, the policy is pretty solid). $\endgroup$ – Glen_b Feb 8 '17 at 22:47

Among the achievements of the late John Tukey are boxplots stem and leaf plots and many other methods that can be found in his exploratory data analysis book.


Not the answer you're looking for? Browse other questions tagged or ask your own question.