|
A '''rating scale''' is a set of categories designed to elicit information about a [[quantitative]] attribute in social science. Common examples are the [[Likert scale]] and 1-10 rating scales for which a person selects the number which is considered to reflect the perceived quality of a product.
== Task 2==
== Background ==
Task 2 is worded confusingly. It mentions the "Latin alphabet" and then mentions the "system of writing" not the "letters". Doesn't "alphabet" constitute a set of "letters"? Wouldn't "system of writing" imply the "Latin language"? [[User:Jeff schiller|Jeff schiller]] 21:55, 2004 Oct 7 (UTC)
In [[Psychometrics]], rating scales are often referenced to a statement which expresses an attitude or perception toward something. The most common example of such a rating scale is the Likert scale, in which a person is asked to select a category label from a list indicating the extent of disagreement or agreement with a statement.
sorry i'll work on changing that. however the answer is in wikipedia somewhere.--[[User:Larsie|Larsie]] 22:49, 7 Oct 2004 (UTC)
The basic feature of any rating scale is that it consists of a number of categories. These are usually assigned integers. For example, an example of the use of a Likert scale is as follows.
ok i've changed it and people should be able to find the answer by going to the latin page and looking around... try some links on that page too--[[User:Larsie|Larsie]] 15:18, 14 Oct 2004 (UTC)
:'''Statement:''' I could not live without my iPod.
i do realize that the second task may be difficult but rest assured the answer is in wikipedia, and does NOT happen to relate to any middle-earth language as the base for most of Tolkeins fictional languages were Welsh and Finnish.--[[User:Larsie|Larsie]] 18:16, 14 Oct 2004 (UTC)
:'''Response options:'''
== New Tasks ==
:*1. Strongly Disagree
Can anyone put a task/question up here? [[User:Dpen2000|dpen2000]] 10:01, 8 Oct 2004 (UTC)
:*2. Disagree
:*3. Agree
:*4. Strongly Agree
It is common to treat the numbers obtained from a rating scale directly as measurements by calculating averages, or more generally any [[arithmetic]] operations. Doing so is not however justified. In terms of the [[levels of measurement]] proposed by S.S. Stevens, the data are ordinal categorisations. This means, for example, that to agree strongly with the above statement implies a more favourable perception of iPods than does to agree with the statement. However, the numbers are not interval-level measurements in Stevens' schema, which means that equal differences do not represent equal intervals between the degree to which one values iPods. For example, the difference between strong agreement and agreement is not necessarily the same as the difference between disagreement and agreement. Strictly, even demonstrating that categories are ordinal requires empirical evidence based on patterns of responses (Andrich, 1978).
no, the winner of each round will be able to assist in the next round--[[User:Larsie|Larsie]] 16:23, 27 Oct 2004 (UTC)
More than one rating scale is required to [[measurement|measure]] an attitude or perception due to the requirement for statistical comparisons between the categories in the [[polytomous Rasch model]] for ordered categories (Andrich, 1978). In terms of [[Classical test theory]], more than one question is required to obtain an index of internal reliability such as [[Cronbach's alpha]] (Cronbach, 1951) which is a basic criterion for assessing the effectiveness of a rating scale and, more generally, a psychometric instrument.
==WTF?==
So, I completed Task 1 and my answer was deleted. Why is that? How is one supposed to know that a task is completed? [[User:RickK|Rick]][[User talk:RickK|K]] 18:57, Oct 11, 2004 (UTC)
== Rating scales used online ==
sorry about that Rickk. make sure you read the instructions above the tasks carefully. next time when you want to post an answer post it where says to in the instructions paragraph. (i meant to send a message to you but forgot). --[[User:Larsie|Larsie]] 19:34, 11 Oct 2004 (UTC)
Rating scales are used widely online in an attempt to provide indications of consumer opinions of products. Examples of sites which employ ratings scales are [[IMDb]], [[Epinions.com]], [[Internet Book List]], [[Yahoo! Movies]], [[Amazon.com]], [[BoardGameGeek]], [[TV.com]] and [[Ratings.net]]. The [[Criticker]] website uses a rating scale from 0 to 100 in order to obtain "personalised film recommendations".
== Ideas ==
In almost all cases, online rating scales only allow one rating per user per product, though there are exceptions such as ''Ratings.net'', which allows users to rate products in relation to several qualities. Most online rating facilities also provide few or no qualitative descriptions of the rating categories, although again there are exceptions such as ''Yahoo! Movies'' which labels each of the categories between F and A+ and BoardGameGeek, which provides explicit descriptions of each category from 1 to 10. Often, only the top and bottom category is described, such as on ''IMDb'''s online rating facility.
Please place any ideas you have here
With each user rating a product only once, for example in a category from 1 to 10, there is no means for evaluating internal [[reliability (statistics)|reliability]] using an index such as [[Cronbach's alpha]]. It is therefore impossible to evaluate the [[validity]] of the ratings as measures of viewer perceptions. Establishing validity would require establishing both reliability and accuracy (i.e. that the ratings represent what they are supposed to represent).
Another fundamental issue is that online ratings usually involve convenience [[sampling (statistics)|sampling]] much like television polls, i.e., they represent only the conglomeration of those inclined to submit ratings.
== Task 2 (Round 2) removed ==
Sampling is one factor which can lead to results which have a specific bias or are only relevant to a specific subgroup. To illustrate the importance of such factors, consider an example. Suppose that a film's marketing strategy and reputation is such that 90% of its audience are attracted to the particular kind of film; i.e. it does not appeal to a broad audience. Suppose also that the film is very popular among the audience that does see the film and, in addition, that those who feel most strongly about the film are inclined to rate the film online. This combination may lead to very high ratings of the film which do not generalize beyond the people who actually see the film (or possibly even beyond those who actually rate it).
I don't like the removal of task 2 just because it was posted by someone else than Larsie or Ravn. Rmhermen's question wasn't bad at all, and the answer wasn't that easy to find. This is a Wiki after all, so you'll have to deal gracefully with some third party posting questions. If you don't want that, move this "Wikifun" thing to your own user space: ''there'', you can enforce such rules. But here, in general Wikipedia: space, you really should be a bit more open-minded. [[User:Lupo|Lupo]] 06:39, 28 Oct 2004 (UTC)
Qualitative description of categories is an important feature of a rating scale. For example, if only the points 1-10 are given without description, some people may select 10 rarely whereas other may select the category often. If, instead, "10" is described as "near flawless", the category is more likely to mean the same thing to different people. This applies to all categories, not just the extreme points. Even with category descriptions, some may be harsher raters than others. Rater harshness is also a consideration in marking essays in educational contexts. [http://66.102.7.104/search?q=cache:o1l_qRDI9QwJ:www.cambridgeesol.org/rs_notes/rs_nts13.pdf+rater+harshness+references&hl=en&ct=clnk&cd=4].
:I understand that, and that's why I left Rmhermen's question there at first. However, open posting of tasks could spoil some of the fun in wikifun. On the one hand, it will become difficult to keep a slower pace in posting new tasks with everyone participating. On the other hand it is an extra incentive to win the round, at least for the average wikinerd ;) I am not against the idea of an open game, but I think it collides with the ten-task round-based concept. [[User:Ravn|Ravn]] 08:46, 28 Oct 2004 (UTC)
These issues are also compounded when aggregated statistics such as averages are used for lists and rankings of products. User ratings are at best [[levels of measurement|ordinal]] categorizations. While it is not uncommon to calculate averages or means for such data, doing so cannot be justified because in calculating averages, equal intervals are required to represent the same difference between levels of perceived quality. The key problems with aggregate data based on the kinds of rating scales commonly used online are as follow:
::I don't quite see why it would spoil the fun - I had fun trying to find the answer to both questions :-) [[User:Lupo|Lupo]] 09:04, 28 Oct 2004 (UTC)
*Averages should not be calculated for data of the kind collected.
*It is usually impossible to evaluate the reliability or validity of user ratings.
*Products are not compared with respect to explicit, let alone common, criteria.
*Only users inclined to submit a rating for a product do so.
*Data are not usually published in a form that permits evaluation of the product ratings.
==References==
::: There will be more to come ;-) The point is, when we had posted ten tasks at a time, you'd have had your fun answering the ten, but other people in different time zones would be left with no chance. That's why Larsie had the intention to control the posting interval. [[User:Ravn|Ravn]] 10:36, 28 Oct 2004 (UTC)
* Cronbach, L. J. (1951). Coefficient alpha and the internal structure of tests. ''Psychometrika, 16'', 297-333.
the main goal of wikifun is for a person to try and get as many correct answers as possible so that they win the chance to be able to post the tasks for the next round. if one wants to post tasks freely they have to win the chance. so therefor it is not only as controlled as you may think. ravn will have to give up his so called 'control' to the winner of the round, and then if he wants it back, he must win again. in that regard technically anyone does have the ability to post tasks. --[[User:Larsie|Larsie]] 21:43, 31 Oct 2004 (UTC)
* Andrich, D. (1978). A rating formulation for ordered response categories. ''Psychometrika'', 43, 357-74.
==See Round 2 also==
*[[Voting system]]
*[[Rotten Tomatoes]]
*[[Metacritic]]
==External links==
Erm—is anybody else participating in this contest? I feel lonely... :-/ Maybe you should have advertised it more widely, e.g. on [[Wikipedia:Recentchanges]]. Something to consider for the next time. [[User:Lupo|Lupo]] 16:14, 2 Nov 2004 (UTC)
[http://www.rasch-analysis.com/ How to apply Rasch analysis]
[[Category:Psychometrics]]
== Rearanged answer section to prevent accidentally seeing previous answers ==
I moved the answer's to separate sub pages so that I could change the "answer this question" links below the tasks to bring up "comment" type edit boxes on for each task, so tasks can be answered without seeing other answers. It also has the helpful benefit of requireing two clicks from Wikifun to reach anctual answers, rather than one. Hope you like it. [[User:JesseW|JesseW]] 07:51, 3 Nov 2004 (UTC)
:I do. [[User:Ravn|Ravn]] 10:10, 3 Nov 2004 (UTC)
== Round 5 ==
Hi, I think Lupo is still away or something, could some kind soul, who has free time start round 5 of wikifun, it's long overdue... meanwhile, we could try to archive round 4. thanks loads! - [[User:Fiveless|fiveless]] 15:47, Feb 6, 2005 (UTC)
:Archived... somewhat. New round up. --[[User:AllyUnion| AllyUnion]] [[User talk:AllyUnion|(talk)]] 11:28, 14 Mar 2005 (UTC)
== King Williams College Quiz ==
Just for those who are interested, the answers to the [[King William's College quiz|King William's College Quiz]] are released, in case you didn't know yet. [http://www.guardian.co.uk/g2/story/0,,1390100,00.html]
== Wikipedia:Wikifun/Template ==
A template has been created to make the rounds for the game. Please remember to use <nowiki>{{subst:Wikipedia:Wikifun/Template|num=#ofround}}</nowiki> instead of just <nowiki>{{Wikipedia:Wikifun/Template}}</nowiki>. --[[User:AllyUnion| AllyUnion]] [[User talk:AllyUnion|(talk)]] 18:24, 14 Mar 2005 (UTC)
* I changed it so the links to answers point to the corresponding section, like ...Wikifun/Answers/Round X/Question Y. [[User:Grue|Grue]] 20:04, 27 Mar 2005 (UTC)
*: PAGENAME = Wikifun when you use the template on Wikifun/Round_X. Plus, I've noticed that related changes doesn't work when you subpage the pages several levels deep. When I used it as Wikifun/Round X/Question Y, it was a lot easier and it showed up in the Related changes. Wikifun/Answers/Round X/Question Y is unusually complex. For your round, all the pages went to Wikifun/Round X/Answers/Round X/Question Y. I reverted your changes because of that. --[[User:AllyUnion| AllyUnion]] [[User talk:AllyUnion|(talk)]] 11:24, 28 Mar 2005 (UTC)
*: [[Wikipedia:Wikifun/Round 6/Answers/Round 6/Question 11]] for example. I don't know how my subpage include worked differently, but when you archive the round, the page is different. --[[User:AllyUnion| AllyUnion]] [[User talk:AllyUnion|(talk)]] 11:32, 28 Mar 2005 (UTC)
Now I see Round 5 links to Wikifun/Round 5/Answers/ and Round 6 links to Wikifun/Answers/Round 6/. Very interesting... That probably confused me. And I didn't realize Wikifun/Round X is inserted in the main page as template. [[User:Grue|Grue]] 12:13, 28 Mar 2005 (UTC)
The problem is that links in [[Wikipedia:Wikifun]] and Wikipedia:Wikifun/Round X point to different places, because PAGENAME is different. I suggest dropping these fancy schmancy variables and make all links fixed, it's not like this template would be used in other languages Wikipedias. [[User:Grue|Grue]] 14:22, 4 Apr 2005 (UTC)
== Wikifun Watchlist ==
[http://en.wikipedia.org/w/index.php?title=Special:Recentchangeslinked&target=User:Alterego/Wikfun&hideminor=0&days=365&limit=500 link] --[[User:Alterego|Alterego]] 21:43, Apr 5, 2005 (UTC)
== [[Wikipedia:Wikifun/Round 8|Round 8]]: we have a tie ==
Now that my twenty questions have been answered, there's a three-way tie:
*[[User:Alphax|Alphax]] - 6 points
*[[User:Thejesterx|Thejesterx]] - 6 points
*[[User:FreplySpang|FreplySpang]] - 6 points
How are we going to solve this? Would you three accept a joint victory? Or do you want to fight on, with a tie breaker question? I don't have one yet, but I'm willing to write one. [[User:Eugene van der Pijll|Eugene van der Pijll]] 17:13, 13 May 2005 (UTC)
: A joint victory is fine with me. Thanks, Eugene, for an excellent round of Wikifun! [[User:FreplySpang|FreplySpang]] [[User talk:FreplySpang|(talk)]] 19:44, 13 May 2005 (UTC)
: I'm happy with a joint victory, unless Alphax really wants a tie-breaker. And yeah, great job Eugene, thanks for putting in the effort to provide us all with some quality entertainment (not to mention education ;) ). -- [[User:Thejesterx|Thejesterx]] 03:35, 14 May 2005 (UTC)
: I too am happy with a joint victory. Thanks for writing such interesting questions! -- [[User:Alphax|Alphax]] <sup >[[User talk:Alphax|τ]][[Special:Emailuser/Alphax|ε]][[Special:Contributions/Alphax|χ]]</sup > 06:54, 14 May 2005 (UTC)
| 