pvalues: Sum up + proposal 
pvalues: Sum up + proposal 
Mar 11 2004, 02:28
Post
#1


Moderator Group: Members Posts: 1434 Joined: 26November 02 Member No.: 3890 
Hi.
I've been looking into statistics of ABX tests under different conditions. What we refer to as pvalue only gives correct results for the "probability to reach a certain score (or better) by random guessing" if the number of trials is fixed before the test starts. In this thread there's more information. Let's repeat some basics: This table shows the classical pvalues. Moving to the right means more total trials, moving down means more wrong trials. Picture (1) The pvalues are calculated using pascal's triangle. For every trial there are 2 possibilities  right + wrong (imagine throwing a coin). For 2 trials there are 4 possibilities (rr, rw, wr, ww), ..., for n trials there are 2^n possibilities, represented by the blue numbers in next picture. A correct trial ("r") is represented by the green arrow, a wrong one by the red arrow. These two arrows can be regarded as the only allowed directions of 'movement' through the triangle. The blue line is one possible way to reach a 4/6 score. The number 15 at the end of this line shows that there are 15 possible ways to reach 4/6  out of 64 total 'ways" for 6 'movements'. So the probability to reach 4/6 is 15/64. The pvalue for 4/6 score is calculated by adding this and the probabilities for all x/6 results with x>4, i.e. 5/6 and 6/6, so pvalue (4/6) = (15+6+1)/64. Picture (2) So far, so good. The explanation why this doesn't work as it should follows soon in a separate post.  Let's suppose that rain washes out a picnic. Who is feeling negative? The rain? Or YOU? What's causing the negative feeling? The rain or your reaction?  Anthony De Mello



Mar 11 2004, 03:15
Post
#2


Moderator Group: Members Posts: 1434 Joined: 26November 02 Member No.: 3890 
These 3 pictures will help to explain the problem:
Picture (1) Picture (3) Picture (4) A typical example: A tester wants to get a pvalue < 0.05, but he doesn't decide to perform e.g. 8 trials before the test. Instead he would stop the test whenever a pvalue < 0.5 is reached (> yellow numbers in Picture (1)). These results (5/5), (7/8), ... are the "stop points" of the test. Problem: After each stop point the possibilities of 'movement' or 'ways' in the triangle are reduced. E.g. (5/6) can't be reached from (5/5) anymore because (5/5) will stop the test. This is why the numbers in pascal's triangle in picture (4) are changed compared to picture (3). The number of ways to reach the 2nd stop point (7/8) is reduced from 8 to 5. Now the total proability (corrected pvalue or 'cvalue') to finish this test 'successfully' (= max. number of trials: 8, test stops when pvalue < 0.05) is: cvalue (7/8) = 1/32 + 5/256 = 0.051 That doesn't seem very bad, but here are some cvalues for bigger number of trials (pvalue that stops the test 0.05): 15 trials > 0.079 30 trials > 0.129 50 trials > 0.158 100 trials > 0.202 Now the question is: Should we just modify ABX software to force people to specify a fixed number of trials before testing  showing pvalues or show cvalues if the number of trials hasn't been fixed before? With this approach there might another problem  I quote a PM Schnofler sent me recently about this: QUOTE If I understood it correctly the idea goes like this: The pvalue, that is "the probability to get c or more correct in n trials if you guess blindly", doesn't give an accurate measure of "probability that you were guessing" because it doesn't take into account that the listener might just stop as soon as he has the value he wants and continue otherwise. So what we do is, we calculate the "probability to reach your current or a better pvalue with up to n trials" and call this "corrected pvalue" or cvalue as you do in your source. Sounds nice, but why don't we go a step further and calculate the "probability to reach your current or a better cvalue with up to n trials", because after all the listener could just stop as soon as he has his desired cvalue or continue otherwise. That's why I called it a "hack", that is cvalues don't take a fundamentally different approach to calculate the measurement we'd like to have ("probability you were guessing"), but just try to "patch up" the approach we already have, and in the end leave you with the same problem you started out with. I'm not sure about this, but if the tester isn't forced to specify a pvalue that stops the test before the test starts  and the software stops or continues the test based on this automatically, Schnofler's thought is probably right. If a tester is allowed to watch cvalues and stop the test based on them, we would need 'corrected cvalues', 'corrected corrected cvalues' ... I think I have found a sollution for this problem  there might be better ones, but anyway  here it is: The goal is: no matter how long the test is going to take, the cvalue must not become higher than e.g. 0.05. Every stop point will 'consume' a part of this cvalue. It's necessary to make sure that adding the probabilities of each stop point, the sum can never be bigger than the cvalue we want to reach (here 0.05). A simple approach for something like this: 2^(1) + 2^(2) + 2^(3) + ... + 2^(n) < 1 , no matter how big n gets. We have to choose the stop points like this (easier for me to explain from an example): Picture (5) Desired cvalue: c = 0.05 or lower. 1/2*0.05 = 0.025, so the 1st stop point must have a probability p < 0.025. This is the case for 6/6 correct trials with p = 1/64 = 0.0156 So 1st stop point: 6/6 c > c  p = 0.05  0.0156 = 0.0344, the remaining "c" for the rest of the stop points. Condition for the next stop point: p < 0.5 * 0.0344 = 0.0172 From the table it's obvious that for the next stop point (n1)/n the p is 6/2^n For n=9: p = 6/512 = 0.0117 So 2nd stop point: 8/9 c > c  p = 0.0344  0.0117 = 0.0227 p < 0.5 * 0.0227 = 0.0114 p = 33/2^n for next stop point (n2)/n for n=12: p = 33/4096 = 0.0081 so 3rd stop point: 10/12 c > c  p = 0.0227  0.0081 = 0.0146 p < 0.5 * 0.0146 = 0.00730 p = 182/2^n for next stop point (n3)/n for n=16: p = 182/32768 = 0.0056 so 34d stop point: 12/15 c > c  p = 0.0146  0.0056 = 0.0090 ... This way, it would be possible that the tester specifies a "probability that you could get that score by guessing" = cvalue he wants to reach, and the ABX software tells where the stop points are  or just works as we're used to: It displays the current cvalue based on the stop points it calculated from the 'goal cvalue'. Puh... writing this was hard, reading too I guess. As reward here's a little toy: I created some small dosbox program that can calculate cvalues. It's attatched to this post. Enjoy Edited: "probability that you're guessing" replaced with "probability that you could get that score by guessing" This post has been edited by tigre: Mar 15 2004, 10:12
Attached File(s)
 Let's suppose that rain washes out a picnic. Who is feeling negative? The rain? Or YOU? What's causing the negative feeling? The rain or your reaction?  Anthony De Mello



Mar 11 2004, 03:53
Post
#3


ABC/HR developer, ff123.net admin Group: Developer (Donating) Posts: 1396 Joined: 24September 01 Member No.: 12 
One solution that several of us discussed in 2001 was to create ABX "profiles" designed to give a reasonable number of max trials (for example 28), and a reasonable number of places where the program automatically stops.
See my summary post from the massive thread here: http://www.hydrogenaudio.org/forums/index....indpost&p=32170 QUOTE 1. The test will automatically stop if the following points are reached: 6 of 6 10 of 11 10 of 12 14 of 17 14 of 18 17 of 22 17 of 23 20 of 27 20 of 28 2. The program will display overall alpha values after each of the above stop points has been achieved. Also, the overall alpha values will be displayed regardless of whether the test stops or not at the following (look) points: trials 6, 12, 18, 23, and 28. (The earlier the test is terminated when the listener passes, the lower the overall alpha is.) 3. The program will display the number correct after each trial is completed. 4. The test will automatically stop if 9 incorrect are achieved. ff123 


Mar 11 2004, 10:18
Post
#4


Group: Members Posts: 246 Joined: 10February 04 From: London Member No.: 11923 
QUOTE (tigre @ Mar 10 2004, 06:15 PM) The goal is: no matter how long the test is going to take, the cvalue must not become higher than e.g. 0.05. Every stop point will 'consume' a part of this cvalue. It's necessary to make sure that adding the probabilities of each stop point, the sum can never be bigger than the cvalue we want to reach (here 0.05). A simple approach for something like this: 2^(1) + 2^(2) + 2^(3) + ... + 2^(n) < 1 , no matter how big n gets. What will happen if the listener does, say 6 failed ABX trials, then (almost) all following trials are successful? Would it ever be possible to bring the cvalue down again? 


Mar 11 2004, 14:26
Post
#5


Moderator Group: Members Posts: 1434 Joined: 26November 02 Member No.: 3890 
QUOTE (jido @ Mar 11 2004, 11:18 AM) QUOTE (tigre @ Mar 10 2004, 06:15 PM) The goal is: no matter how long the test is going to take, the cvalue must not become higher than e.g. 0.05. Every stop point will 'consume' a part of this cvalue. It's necessary to make sure that adding the probabilities of each stop point, the sum can never be bigger than the cvalue we want to reach (here 0.05). A simple approach for something like this: 2^(1) + 2^(2) + 2^(3) + ... + 2^(n) < 1 , no matter how big n gets. What will happen if the listener does, say 6 failed ABX trials, then (almost) all following trials are successful? Would it ever be possible to bring the cvalue down again? Sure. How low the cvalue can become after a large number of trials depends on the 'stop points' only. E.g. if you want to reach a cvalue < 0.01 and start with 6 wrong trials, it could look like this (this example is not calculated with 2^(1) + ... method but the result is similar): Maximum number of trials: 40 Stop points with pvalue < 0.003: 9/9 12/13 14/16 16/19 18/22 20/25 21/27 23/30 25/33 26/35 28/38 In your case, if you reach 26/35 = 6/6 + 20/29 or 28/38 = 6/6 + 22/32 your final cvalue is still < 0.01 With the "2^(1) + ..." method, you can reach the cvalue you want but the number of trials is not limited. For a final cvalue < 0.01 the stop points would be: 8/8 11/12 13/15 ... (I have to calculate these values manually because I haven't had time yet to add this to my little program.)  Let's suppose that rain washes out a picnic. Who is feeling negative? The rain? Or YOU? What's causing the negative feeling? The rain or your reaction?  Anthony De Mello



Mar 13 2004, 00:59
Post
#6


Group: Members (Donating) Posts: 707 Joined: 20July 03 From: Canada Member No.: 7895 
QUOTE (tigre @ Mar 10 2004, 06:15 PM) Schnofler's thought is probably right. If a tester is allowed to watch cvalues and stop the test based on them, we would need 'corrected cvalues', 'corrected corrected cvalues' ... Would the corrected, corrected, corrected × 10 value approach a particular value? Could this not be a asymptote? Couldn't we use calculus to find this out instead of using simplistic hacks? Lazy?  gentoo ~amd64 + layman  ncmpcpp/mpd  wavpack + vorbis + lame



Mar 13 2004, 02:05
Post
#7


ABC/HR developer, ff123.net admin Group: Developer (Donating) Posts: 1396 Joined: 24September 01 Member No.: 12 
QUOTE (music_man_mpc @ Mar 12 2004, 03:59 PM) QUOTE (tigre @ Mar 10 2004, 06:15 PM) Schnofler's thought is probably right. If a tester is allowed to watch cvalues and stop the test based on them, we would need 'corrected cvalues', 'corrected corrected cvalues' ... Would the corrected, corrected, corrected × 10 value approach a particular value? Could this not be a asymptote? Couldn't we use calculus to find this out instead of using simplistic hacks? Lazy? The ABX "profile" sidesteps this issue by specifying maximum trials allowable. If the ABX does not pass after this max, then it is automatically failed. 28 trials max was one profile design, chosen to allow a reasonable number of trials, but other profiles can be designed with higher max trials if desired. Keep in mind that the higher the max trials in the profile, the more difficult that profile will be to pass. ff123 


Mar 13 2004, 15:19
Post
#8


Java ABC/HR developer Group: Developer Posts: 175 Joined: 17September 03 Member No.: 8879 
Ok, I guess I should say something on this subject, too. The problem is, the really clean solutions always make the whole testing procedure less comfortable or more complicated.
Not showing the listener his results until some point he specified in advance would make it extremely easy to calculate a precise "probability that you were guessing" (just the pvalue we use now), but it would also be a major pain in the ass for the listener. ff123s ABX "profiles" are a much better solution, but they would still make testing more complicated than it is now. Especially in ABC/HR tests I like the possibility to just start an ABX, try a few times, give up or try some more, stop whenever I want to, etc. First choosing a profile, not knowing your score until you reach the next stop point, having to stop if max trials is reached, all this would make the test a lot less comfortable for the listener. tigre, I haven't really made up my mind about the approach you describe in the second half of your second post. I understand how you do what you want to do, but I didn't understand how this solves the problem. Could you try to clarify? So, since my contribution to this discussion so far mainly consists of undecisiveness, I decided to make something "useful", a program that can calculate the correctedcorrectedcorrectedetc.cvalue. You specify the number of total and correct trials and a "depth", that is the number of "corrections" (where a depth of 1 is the normal pvalue). To answer music_man_mpc's question: Yes, of course the values approach a certain limit (they have to, the sequence is monotonic increasing and has 1 as an upper bound). It would be nice to have a closed form of the limit function, but I guess that won't be easy (in the current form the definition of the sequence is terribly recursive). However, empirically, it seems like after a certain number of correctioniterations the value actually remains constant, so it's possible to calculate the limit even if we don't have a nice function for it. The limit function p(n,c) is characterized by the following property: p(n,c) is exactly the probability of reaching a point (n',c') with n'<=n and p(n',c')<=p(n,c). That's why the argument "but the listener could have stopped as soon as he got a value <=p and continued otherwise" doesn't hold here. Sure, he could have stopped, but the chances of reaching such a point with the same or a better cvalue (meaning corrected, corrected, etc. pvalue) than he has now, are exactly the same as the cvalue that is shown at the moment. That would kind of solve the problem, since we could freely show the listener his cvalue all the time, and ABXing would be the same as before, only the pvalues would be a bit higher than usual. The obvious problem is, what the heck *are* these values? I don't have a clue. They are the result of some mysterious calculations, but do they have anything to do with the "probability that you were guessing"? Well, I don't know, maybe someone more knowledgeable can shine some light on this.
Attached File(s)



Mar 14 2004, 12:47
Post
#9


Moderator Group: Members Posts: 1434 Joined: 26November 02 Member No.: 3890 
Thanks for feedback so far.
To clarify/mention an aspect that hasn't been made totally clear so far: The cvalues / corrected cvalues /... are all caculated the same way: They use the stop points (i.e. the ABX scores where the test would have stopped) and the actual score that is reached. What differs, depending on different approaches (cvalue, corrected^n cvalue, "asymptote approach", ...) are the stop points. The problem is, that without any information before the test starts, the ABX software has to make assumptions about the stop points. Example: Let's say a score of 11/14 is reached in a ABX test. The tester can see the scores + pvalues he has reached and decides based on them when to stop the test (basic cvalues approach). 1st case: His stop condition is a pvalue of <= 0.031. The stop points are: 6/6, 8/9, 10/12, 11/14, the cvalue is 0.047 2nd case: stop condition = pvalue <= 0.032. Stop points: 5/5, 8/9, 10/12, 11/14, the cvalue is 0.059 If the listener doesn't specify a pvalue that will stop the test, the results will vary depending on the software's assumptions about at what score the tester would have stopped. Because of this, IMO ABX software *must* ask for some information before the test starts to produce reliable p/cvalues. My "asymptote approach" (2^1 + 2^2 + ...) is one way to get correct cvalues with an unlimited number of trials (and an unlimited number of wrong trials ). The tester must specify what cvalue he wants to reach at the beginning. Maybe there is a way to calculate corrected values without the tester giving information before the test starts, but I doubt this, since the software always has to make assumptions that might be wrong. Immagine a listener wants to reach a cvalue of < 0.01, but after 15 trials with some mistakes he decides that 0.05 is enough this time. This would change the stop points, no matter what method is used to calculate them, and therefore the cvalues. Without the user giving some information about this to the software, there's no way to get correct results here.  Let's suppose that rain washes out a picnic. Who is feeling negative? The rain? Or YOU? What's causing the negative feeling? The rain or your reaction?  Anthony De Mello



Mar 14 2004, 15:24
Post
#10


Moderator Group: Super Moderator Posts: 3936 Joined: 29September 01 Member No.: 73 
I wonder if the limit of the probability to have guessed, in a sequencial test, is 1. Maybe one day I'll try to calculate it.



Mar 14 2004, 22:55
Post
#11


Moderator Group: Members Posts: 1434 Joined: 26November 02 Member No.: 3890 
I've created a dosbox program (attatched to this post), that simulates "2^(1) + 2^(2) + 2^(3) + ..." method. I've extended it a bit, now it works like this:
A aimed cvalue is entered. The stop points are chosen by the program to make the cvalue when reaching one of them stay lower than the aimed cvalue, no matter how many trials are performed. The numer of total trials can be limited by the user to make the program stop after a reasonable number of trials. Every stop point is allowed to 'consume' a certain percentage (or less) of the remaining "aimed cvalue reservoir". This percentage can be chosen by the user as 3rd input (0.01  0.99). Example: The aimed cvalue is 0.05. The percentage is 0.4. The cvalue for the 1st stop point must be smaller than 0.05*0.4 = 0.02, this is the case for 6/6, cvalue = 0.0156. The "reservoir" is now 0.050.0156 = 0.0344. What's added by the next stop point to the cvalue must be smaller than 0.0344*0.4 = 0.0138. This is the case for 8/9, cvalue = 0.0273. "reservoir": 0.0227. Next stop point must add 0.0091 or less: 10/12., cvalue = 0.0354 ... Here's an example showing how the percentage value affects the stop points: For comparison the number of trials is limited to 50, but there's no limit in practice (besides limits caused by overflow in software etc.): Aimed cvalue = 0.01. 1. Percentage = 0.1: CODE 1. Stop point: (10/10) CValue: 0.000976563 2. Stop point: (13/14) CValue: 0.00158691 3. Stop point: (15/17) CValue: 0.00223541 4. Stop point: (17/20) CValue: 0.00282192 5. Stop point: (19/23) CValue: 0.00332022 6. Stop point: (21/26) CValue: 0.00373085 7. Stop point: (23/29) CValue: 0.0040638 8. Stop point: (24/31) CValue: 0.00459897 9. Stop point: (26/34) CValue: 0.00496011 10. Stop point: (28/37) CValue: 0.00523142 11. Stop point: (29/39) CValue: 0.00564917 12. Stop point: (31/42) CValue: 0.00592204 13. Stop point: (32/44) CValue: 0.00632385 14. Stop point: (34/47) CValue: 0.00657883 15. Stop point: (36/50) CValue: 0.00676343 2. Percentage = 0.3 CODE 1. Stop point: (9/9) CValue: 0.00195313 2. Stop point: (11/12) CValue: 0.00415039 3. Stop point: (14/16) CValue: 0.00511169 4. Stop point: (16/19) CValue: 0.00601006 5. Stop point: (18/22) CValue: 0.00676394 6. Stop point: (20/25) CValue: 0.00737441 7. Stop point: (22/28) CValue: 0.00786117 8. Stop point: (24/31) CValue: 0.00824657 9. Stop point: (26/34) CValue: 0.00855083 10. Stop point: (28/37) CValue: 0.00879084 11. Stop point: (30/40) CValue: 0.00898025 12. Stop point: (31/42) CValue: 0.00927956 13. Stop point: (33/45) CValue: 0.00947899 14. Stop point: (35/48) CValue: 0.00962775 3. Percentage = 0.5 CODE 1. Stop point: (8/8) CValue: 0.00390625 2. Stop point: (11/12) CValue: 0.00585938 3. Stop point: (13/15) CValue: 0.00769043 4. Stop point: (16/19) CValue: 0.00844574 5. Stop point: (18/22) CValue: 0.00913858 6. Stop point: (21/26) CValue: 0.00942713 7. Stop point: (23/29) CValue: 0.00969638 8. Stop point: (26/33) CValue: 0.00981075 9. Stop point: (29/37) CValue: 0.00986504 10. Stop point: (31/40) CValue: 0.00991874 11. Stop point: (34/44) CValue: 0.0099426 12. Stop point: (36/47) CValue: 0.00996601 4. Percentage = 0.8 CODE 1. Stop point: (7/7) CValue: 0.0078125 2. Stop point: (11/12) CValue: 0.00952148 3. Stop point: (16/18) CValue: 0.00973511 4. Stop point: (19/22) CValue: 0.00986528 5. Stop point: (22/26) CValue: 0.00993642 6. Stop point: (25/30) CValue: 0.00997436 7. Stop point: (28/34) CValue: 0.00999449 8. Stop point: (33/40) CValue: 0.00999717 9. Stop point: (36/44) CValue: 0.00999893 10. Stop point: (40/49) CValue: 0.00999945 5. Percentage = 0.9 CODE 1. Stop point: (7/7) CValue: 0.0078125
2. Stop point: (11/12) CValue: 0.00952148 3. Stop point: (15/17) CValue: 0.00994873 4. Stop point: (21/24) CValue: 0.00997794 5. Stop point: (25/29) CValue: 0.00998824 6. Stop point: (28/33) CValue: 0.00999505 7. Stop point: (31/37) CValue: 0.00999912 8. Stop point: (36/43) CValue: 0.0099997 9. Stop point: (40/48) CValue: 0.0099999
Attached File(s)
 Let's suppose that rain washes out a picnic. Who is feeling negative? The rain? Or YOU? What's causing the negative feeling? The rain or your reaction?  Anthony De Mello



Mar 14 2004, 23:13
Post
#12


Java ABC/HR developer Group: Developer Posts: 175 Joined: 17September 03 Member No.: 8879 
tigre: Just to clarify, with your method, the cvalue that is shown to the user will be the probability to reach one of the stop points (calculated as you described above) or his current score, right?



Mar 15 2004, 00:36
Post
#13


Moderator Group: Members Posts: 1434 Joined: 26November 02 Member No.: 3890 
QUOTE (schnofler @ Mar 15 2004, 12:13 AM) tigre: Just to clarify, with your method, the cvalue that is shown to the user will be the probability to reach one of the stop points (calculated as you described above) or his current score, right? 1. User tells software what cvalue he wants to reach "true probability that you could get a score by guessing", e.g. 0.01. 2. Software calculates stop points (can be made configurable > "probability" value). 3. There are several possibilities what can be shown to the user, e.g.: a) the cvalue based on the stop points and the actual score b) simply either "not yet passed, if you stop now you've failed" or "passed, stop now" c) the actual score and the next few reachable stop points d) the stop points that have been missed already My favourite would be a combination of a) and c), e.g. like this: QUOTE The "probability that you could get a score by guessing."" (cvalue) you want to reach is 0.01. Your current score is 7 correct trials out of 8. Actual cvalue: 0.0195 The next stop points you can reach are: 11/12; 4/4 correct trials needed 14/16; 5/6 correct trials needed 16/19; 9/11 correct trials needed You've missed these stop points: 8/8 Calculating and showing the probability to reach one of the stop points wouldn't make much sense IMO. Edit: "probability you're guessing" replaced with "probability that you could get a score by guessing." This post has been edited by tigre: Mar 15 2004, 10:17  Let's suppose that rain washes out a picnic. Who is feeling negative? The rain? Or YOU? What's causing the negative feeling? The rain or your reaction?  Anthony De Mello



Mar 15 2004, 01:10
Post
#14


Java ABC/HR developer Group: Developer Posts: 175 Joined: 17September 03 Member No.: 8879 
QUOTE (tigre) a) the cvalue based on the stop points and the actual score Yes, that's what I meant in my previous post, sorry if I didn't make it clear enough (the cvalue is, after all, calculated as the probability to reach one of the earlier stop points or your current score). The problem with your approach, as I see it, is still the following: you're using two different kinds of "cvalues" in your method. First you use the "traditional cvalue" calculation to find the stop points, but then you use a different way of calculating the value that is actually shown to the user, because here you use your new "custom" stop points. This results in the same problem as the transition from pvalues to cvalues: what you show to the user is something different than you used for your assumptions about user behaviour. The problem with the original cvalue approach was this: you assume that the user will stop at a certain pvalue, but then you don't even show him the pvalue but rather a different value, the cvalue, so the assumptions don't make sense. In your new approach the problem is similar. First you use "normal" cvalues to find out what the stop points are. But then you don't show these "normal" cvalues to the user, but you show him a different kind of cvalue, namely the ones based on your new stop points. Or maybe I got it all wrong? 


Mar 15 2004, 01:33
Post
#15


Moderator Group: Members Posts: 1434 Joined: 26November 02 Member No.: 3890 
QUOTE (schnofler @ Mar 15 2004, 02:10 AM) Or maybe I got it all wrong? Somewhat, I'd say. Based on the user input before the test starts, all stop points are fixed. The results can be shown, but that's not necessary. The software must have control over the stop points, i.e. when one of them is reached, the software stops the test. Therefore, no assumptions about user behaviour have to be made, because this 'behaviour' is replaced by the stop points calculated by the software. The cvalues that are calculated now using these stop points are correct, no matter what the user can see during testing. You can show him even the 'ordinary' pvalues as additional information. Since the user can't decide to change stop conditions after the test has started, cvalue calculation can't be messed up. There's only one way to calculate cvalues. The only thing that can change and therefore influence the results are the stop points. This is no problem if the stop points are fixed before the test starts. You could even give the user the possibility to set every stop point manually before testing starts. The resulting cvalues would be different from cvalues based on "equal pvalue stop points" of course, but still valid since the stop points are known without any doubt and not calculated based on assumptions about user behaviour.  Let's suppose that rain washes out a picnic. Who is feeling negative? The rain? Or YOU? What's causing the negative feeling? The rain or your reaction?  Anthony De Mello



Mar 15 2004, 02:35
Post
#16


ABC/HR developer, ff123.net admin Group: Developer (Donating) Posts: 1396 Joined: 24September 01 Member No.: 12 
QUOTE (tigre @ Mar 14 2004, 03:36 PM) QUOTE The "probability you're gessing" (cvalue) you want to reach is 0.01. Just a small wording thing that Continuum pointed out in the big thread: It isn't really the "probability you're guessing" that's being calculated, but the "probability that you could get that score by guessing." I like the idea of asking the listener what he wants to try for before he starts. ff123 


Mar 15 2004, 10:22
Post
#17


Moderator Group: Members Posts: 1434 Joined: 26November 02 Member No.: 3890 
QUOTE (ff123 @ Mar 15 2004, 03:35 AM) QUOTE (tigre @ Mar 14 2004, 03:36 PM) QUOTE The "probability you're gessing" (cvalue) you want to reach is 0.01. Just a small wording thing that Continuum pointed out in the big thread: It isn't really the "probability you're guessing" that's being calculated, but the "probability that you could get that score by guessing." You're right, thanks (edited now in my posts). In my 1st post I called it "probability to reach a certain score (or better) by random guessing", but when writing the other posts I must have become less aware of it QUOTE I like the idea of asking the listener what he wants to try for before he starts. I do as well. This way there could be even an option to keep the 'old' pvalues. (The tester would have to choose a fixed number of trials  and the test stops then, no matter what.)  Let's suppose that rain washes out a picnic. Who is feeling negative? The rain? Or YOU? What's causing the negative feeling? The rain or your reaction?  Anthony De Mello



LoFi Version  Time is now: 22nd November 2014  01:26 