Timeline for Calculating the probability of someone winning from a poll
Current License: CC BY-SA 3.0
13 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Sep 6, 2017 at 23:40 | comment | added | Tom | After reading the last answer, which is certainly impressive, I have to say I never saw an answer! The response is so statistically sophisticated that to comprehend it implies an understanding of statistics that would have avoided the question at the start. Does that actually help the questioner? It seems to me far less practical to posit an explanation without answer than to posit an answer without an explanation. Here providing a correct answer is -1, but providing an answer unusable to the questioner is 1. It must be in the statistics! | |
| Sep 6, 2017 at 22:58 | comment | added | Kodiologist | (-1) I have to agree that an answer isn't complete without some sort of argument why it's true, when that isn't obvious. | |
| Sep 6, 2017 at 22:54 | comment | added | whuber♦ | I would like to refer you to stats.stackexchange.com/help/how-to-answer (which is not quite as prominent as I remember it). The best advice I have gotten about using this site came from reading and emulating admirable work, such as the answers posted by chl, gung, and others. Some additional guidance can be found at stats.stackexchange.com/help/on-topic, which links to stats.meta.stackexchange.com/questions/1390. I appreciate your patience and thoughtful replies! | |
| Sep 6, 2017 at 22:48 | comment | added | Tom | I read the question and scanned the help and didn't see anything about answers having to explain how the answer was obtained. If that is so, it should be more prominently displayed. I saw an interesting question that led me to construct a simulation, test and report my findings in the interest of helping someone find an answer ("What is the probability for each of the candidates winning..? ") The questioner did not, but could have asked HOW to answer the question. Sounds like you are a moderator. I enjoyed the give and take. | |
| Sep 6, 2017 at 22:29 | comment | added | whuber♦ | The introduction to the question, "Say I had..." shows that the numbers are hypothetical. The OP doesn't want an answer for these numbers: they--and this site--want an explanation of how to obtain and interpret an answer to this kind of problem. The important thing in communicating a good answer is to explain what you are doing and to support your work with reasoning or, at least, a good reference. Stating that you have an answer, without such support, is worthless even if it happens to correct (which it does not seem to be in this case). | |
| Sep 6, 2017 at 20:31 | comment | added | Tom | MOE assumes a population of 1000 and CI of 95%. I didn't add any facts, just made some reasonable assumptions to provide a reasonable result. Since the questioner had 3 candidates, rather than 2 the calculations became more difficult to answer and express reasonably. Simulations are great for dealing with multiple variables. Again, the questioner wanted an answer, not a philosophical discussion about the approach to the answer. | |
| Sep 6, 2017 at 20:25 | comment | added | whuber♦ | This is not a concern about approximation: it's a matter of revealing what additional facts you might have assumed in order to do a simulation in the first place and of demonstrating that the results can reasonably be expected to tell us anything useful about reality. If you require the reader to guess what those facts might be, then your answer can scarcely be viewed as objective or even correct. | |
| Sep 6, 2017 at 20:17 | comment | added | Tom | Of course it can be correct, you just need to plug-in the assumptions, which can be implied from the result. Since it is a simulation there is no claim that the answer is exact, just that it is likely close to the "true" result. The questioner seemed to want a reasonable answer (hence the qualifier "approx"), not the specifics of the math that produced the answer. The simulation provided that. The questioner is free to assess the validity of the answer. | |
| Sep 6, 2017 at 14:24 | comment | added | whuber♦ | This answer cannot possibly be correct for the simple reason that the question itself has no definite answer unless you add more information to it, such as your (Bayes) prior distribution for the voting. Moreover, we have no way of knowing what implicit assumptions you have made in order to arrive at this answer because you haven't provided the details of the simulation. | |
| S Sep 6, 2017 at 0:23 | review | Low quality posts | |||
| Sep 6, 2017 at 0:44 | |||||
| S Sep 6, 2017 at 0:23 | review | Late answers | |||
| Sep 6, 2017 at 3:15 | |||||
| Sep 6, 2017 at 0:05 | review | First posts | |||
| Sep 6, 2017 at 0:23 | |||||
| Sep 6, 2017 at 0:02 | history | answered | Tom | CC BY-SA 3.0 |