Siteadmin, Bureaucrats, Check users, nsAm_Govt_101RO, nsAm_Govt_101RW, nsAm_Govt_101_ta, nsJudgesRO, nsJudgesRW, nsJudges_talkRO, nsJudges_talkRW, nsTeam2RO, nsTeam2RW, nsTeam2_talkRO, nsTeam2_talkRW, oversight, Administrators
125,795
edits
Changes
Jump to navigation
Jump to search
mLine 109:
Line 109: − + Line 161:
Line 161: − − :::Aschlafly, are we not getting back to the distinction I made [http://www.conservapedia.com/index.php?title=Talk%3APNAS_Response_to_Letter&diff=520539&oldid=520525 here]? A suggestion that you [http://www.conservapedia.com/index.php?title=Talk%3APNAS_Response_to_Letter&diff=520611&oldid=520539 rejected]? − − :::If we are agreed on what constitutes the sample then it is clear that Lenski did combine the sample in a logical manner with proper weighting. He followed accepted practice and used established statistical techniques. Your letter did not dispute the soundness of accepted practice and established techniques, it alleged that Lenski had diverted from them. If the sample is agreed then this allegation is untrue. − − :::If, contrary to your earlier statement, there is a dispute about the sample then it is Lenski who is correct on the sample size. Lenski is testing a hypothesis about Cit+ replicates. If you were testing (to use Brossa’a example) “most murders are committed by 20 to 35 year olds” you would include murderers, you would not run statistics on the age of fraudsters. You may get your data from a source that includes fraudsters, say prison records that include details of all types of criminals. However you would exclude non-murderers, and correctly exclude non-murderers, when reviewing the age of murderers. − − :::That is the situation we have here. Lenski’s null hypothesis is that Cit+ replicates arose randomly. This says no more about Cit- replicates than it does about what Lenski had for lunch the day he wrote the paper. The presence of Cit- replicates is a result of the method of generating the sample, a side product. To give another example, if you were doing an experiment breeding chickens you would generate a lot of manure: you wouldn’t include it in the analysis! − − :::Finally the argument has no end product: if we erroneously consider the Cit- replicates as part of the sample the null hypothesis is still refuted. Your objections to Lenski’s wording do not establish deceit on his part, yet they would were they to be established themselves. Your objections to Lenski’s calculations, however, would not establish the falsity of his conclusions even if the objections were correct. The calculations of the three differing weightings above are not intended: − − ::::1. to show that Lenski was honest (he was, but that is established by other evidence) − ::::2. to show that Lenski correctly applied accepted statistical techniques (he did, but that is established by other evidence) or − ::::3. to show that only Cit+ replicates are part of “the sample” (they are, but that is established elsewhere) − − :::The calculations of the three differing weightings above show that your objections are moot. --[[User:Toffeeman|Toffeeman]] 07:37, 24 September 2008 (EDT) −
Talk:PNAS Response to Letter (view source)
Revision as of 21:56, September 24, 2008
, 21:56, September 24, 2008Reverted edits by Toffeeman (Talk); changed back to last version by Brossa
|}
|}
So weighting on the basis of the number of replicates considerably increases the P-value. It remains, however, well within the range of statistical significance (0<P<0.05). If we hold that Lenski should have weighted on the basis of replicates then he should have rejected the null hypothesis and reached exactly the same conclusions that he did. The entire paper would have been exactly the same except the sentence “the result is extremely significant (P<0.0001) whether or not….” Would read “the result is significant (P<0.04) whether or not”. Point 5 establishes one number and an “extremely”. Point 5, therefore, has no weight (excuse the pun).
So weighting on the basis of the number of replicates considerably increases the P-value. It remains, however, well within the range of statistical significance (0>P<0.05). If we hold that Lenski should have weighted on the basis of replicates then he should have rejected the null hypothesis and reached exactly the same conclusions that he did. The entire paper would have been exactly the same except the sentence “the result is extremely significant (P<0.0001) whether or not….” Would read “the result is significant (P<0.04) whether or not”. Point 5 establishes one number and an “extremely”. Point 5, therefore, has no weight (excuse the pun).
--[[User:Toffeeman|Toffeeman]] 15:18, 20 September 2008 (EDT)
--[[User:Toffeeman|Toffeeman]] 15:18, 20 September 2008 (EDT)
::So that's an "I don't know" then? Or did you mean something else?--[[User:Brossa|Brossa]] 07:34, 24 September 2008 (EDT)
::So that's an "I don't know" then? Or did you mean something else?--[[User:Brossa|Brossa]] 07:34, 24 September 2008 (EDT)
Maybe the Journal of Nature can be your next letter submission source. ''International Weekly Journal of Science'' -- [[Image:50 star flag.png|14px]] [[User:Jpatt|jp]] 21:17, 22 September 2008 (EDT)
Maybe the Journal of Nature can be your next letter submission source. ''International Weekly Journal of Science'' -- [[Image:50 star flag.png|14px]] [[User:Jpatt|jp]] 21:17, 22 September 2008 (EDT)