Talk:Likelihood ratios in diagnostic testing

complexity

This is still too complex - more examples might help perhaps building up to the rather complicated example used. — Preceding unsigned comment added by 194.176.105.144 (talk) 18:31, 30 August 2014 (UTC)

This

This article now begins thus:

In evidence-based medicine, a likelihood ratio is a method of assessing the value of performing a diagnostic test.

Rather like starting an article titled Atlantic Ocean by saying

In telecommunications, the Atlantic Ocean is a body of water across which the transatlantic cable was laid.

Or an article titled Italy by writing this:

Italy is a country whose team won two gold medals in cycling in the 1948 Olympics. [Then the article could go on for a hundred paragraphs about those two events, and that would be the whole story of Italy.]

I'll be back. Michael Hardy (talk) 04:03, 9 March 2010 (UTC)

OK, I've moved the article to likelihood ratios in diagnostic testing and deleted the POV tag. Next I'll redirect likelihood ratio to a more appropriate target than this article. Michael Hardy (talk) 04:10, 9 March 2010 (UTC)

LR+ is definitely not (true positives)/(false positives). Consider the worked example where these two numbers are 2 and 18, respectively. The wrong definition implies that LR+ is 2/18 = 0.11 where it in reality is (2/3)/(1-182/200) = 7.4. Consequently I have removed (true positives)/(false positives) and (false negatives)/(true negatives) from the article. —Preceding unsigned comment added by 90.185.26.224 (talk) 09:28, 13 March 2010 (UTC)

This sentence doesn't make sense as written, and could cause unnecessary alarm in readers:

A positive result for a test with an LR of 8 adds approximately 40% to the pre-test probability that a patient has a specific diagnosis.[3]

As a counter-example, if someone has a 1% chance of a certain condition, and the test has identifies the condition 80% of the time, and falsely identifies it 10% of the time, that's a likelihood ratio of 8 but it only raises the pre-test probability from 1% to a 7.5% post-test probability. — Preceding unsigned comment added by Tunesmith (talk • contribs) 19:05, 18 November 2012 (UTC)

Excel Instructions

Hi. I removed the instructions for calculating likelihood ratios in excel, which are definitely helpful, but generally not something that is included in wikipedia articles. (See WP:NOTGUIDE.) If you'd like to make information like this available to the world (which I certainly would encourage you to do), one way to do it is to post it on another site like wikiHow or on a personal blog (which is what I usually do) and then create an External links section at the bottom of page with a link to the how-to. Some people might still object to it, but such objections are a lot less frequent. Thanks a lot to the original creator of the information for his/her contribution. mcs (talk) 20:31, 20 December 2010 (UTC)

External links modified

Hello fellow Wikipedians,

I have just modified one external link on Likelihood ratios in diagnostic testing. Please take a moment to review my edit. If you have any questions, or need the bot to ignore the links, or the page altogether, please visit this simple FaQ for additional information. I made the following changes:

• Added archive https://archive.is/20020820071706/http://www.poems.msu.edu/InfoMastery/Diagnosis/likelihood_ratios.htm to http://www.poems.msu.edu/InfoMastery/Diagnosis/likelihood_ratios.htm

When you have finished reviewing my changes, you may follow the instructions on the template below to fix any issues with the URLs.

This message was posted before February 2018. After February 2018, "External links modified" talk page sections are no longer generated or monitored by InternetArchiveBot. No special action is required regarding these talk page notices, other than regular verification using the archive tool instructions below. Editors have permission to delete these "External links modified" talk page sections if they want to de-clutter talk pages, but see the RfC before doing mass systematic removals. This message is updated dynamically through the template {{source check}} (last update: 18 January 2022).

• If you have discovered URLs which were erroneously considered dead by the bot, you can report them with this tool.
• If you found an error with any archives or the URLs themselves, you can fix them with this tool.

Cheers.—InternetArchiveBot (Report bug) 06:24, 23 December 2017 (UTC)

Wrong interpretation of LR+

In the calculaition section, the phrase:

On the other hand, an LR+ < 1 would imply that an individual with a positive test result is more likely to be non-diseased than diseased.

is factualy mistaken. Take for example:

	D+	D-
T+	0.50	0.25
T-	0.25	0.05

Which would give LR+ = 0.83 (<1), but P(D+|T+) = 0.71 > P(D-|T+) = 0.29. I will replace it with:

On the other hand, an LR+ < 1 would imply that non-diseased individuals are more likely than diseased individuals to receive positive test results.

(Indeed in the above example, P(T+|D-) = 0.80 > P(T+|D+) = 0.71. Tenthkrige (talk) 11:03, 15 July 2020 (UTC)

• Good catch. Thank you Tenthkrige! All the best   - Mark D Worthen PsyD (talk) (I'm a man—traditional male pronouns are fine.) 02:19, 16 July 2020 (UTC)