| --- Log opened Sun Feb 20 00:00:06 2011 |
| 00:14 | | Derakon[DDR] is now known as Derakon |
| 00:20 | | celticminstrel [celticminst@Nightstar-f8b608eb.cable.rogers.com] has quit [[NS] Quit: And lo! The computer falls into a deep sleep, to awake again some other day!] |
| 00:56 | | You're now known as TheWatcher[T-2] |
| 00:59 | | You're now known as TheWatcher[zZzZ] |
| 01:07 | | Neophox [Tertius_Vul@Nightstar-bb8dd90c.abhsia.telus.net] has quit [[NS] Quit: ] |
| 01:12 | | Phox [Tertius_Vulpe@Nightstar-bb8dd90c.abhsia.telus.net] has joined #code |
| 02:51 | | Attilla [Some.Dude@Nightstar-92c9199f.cable.virginmedia.com] has quit [Ping timeout: 121 seconds] |
| 03:09 | | gnolam [lenin@Nightstar-38637aa0.priv.bahnhof.se] has quit [[NS] Quit: Z?] |
| 03:27 | | RichardBarrell_droid [yaaic@Nightstar-f68eb197.cable.virginmedia.com] has joined #code |
| 03:46 | < Reiv> | Is there a way to get Excel to count the number of unique values in a column? |
| 03:46 | < Reiv> | AKA 1, 1, 2, 4, 6, 4 would be counted as 4? |
| 03:47 | <@Derakon> | cat values | sort -u | awk '{s += $1} END {print s}' |
| 03:47 | <@Derakon> | (Sorry, don't know Excel) |
| 03:49 | < RichardBarrell_droid> | The best solution here might actually be to use Matlab. |
| 03:51 | < Reiv> | ;_; |
| 03:52 | < Reiv> | I know the best solution is not-excel, darnit~ |
| 03:53 | <@Derakon> | http://office.microsoft.com/en-us/excel-help/filter-for-unique-values-or-remove- duplicate-values-HP010073943.aspx |
| 03:55 | | RichardBarrell_droid [yaaic@Nightstar-f68eb197.cable.virginmedia.com] has quit [Ping timeout: 121 seconds] |
| 04:00 | < Reiv> | Crikey. Cheers! |
| 04:01 | <@Derakon> | Just googled for "excel unique values column". |
| 04:03 | < Reiv> | I had done very similar and not gotten that. |
| 04:03 | < Reiv> | I swear my google fu is in negatives or something of late ;_; |
| 04:03 | <@Derakon> | Heh. |
| 04:14 | | Kindamoody is now known as Kindamoody[zZz] |
| 06:14 | | AnnoDomini [annodomini@Nightstar-1114d35c.adsl.tpnet.pl] has joined #code |
| 06:14 | | mode/#code [+o AnnoDomini] by Reiver |
| 07:47 | | Derakon is now known as Derakon[AFK] |
| 09:38 | | kwsn [kwsn@31356A.5FD175.47BC3A.9DB834] has quit [[NS] Quit: ] |
| 10:02 | | Vornicus is now known as Vornicus-Latens |
| 10:06 | | Kindamoody[zZz] is now known as Kindamoody |
| 10:38 | | AnnoDomini [annodomini@Nightstar-1114d35c.adsl.tpnet.pl] has quit [Ping timeout: 121 seconds] |
| 10:40 | | AnnoDomini [annodomini@Nightstar-e967e606.adsl.tpnet.pl] has joined #code |
| 10:40 | | mode/#code [+o AnnoDomini] by Reiver |
| 10:58 | | Attilla [Some.Dude@Nightstar-92c9199f.cable.virginmedia.com] has joined #code |
| 10:58 | | mode/#code [+o Attilla] by Reiver |
| 11:00 | | You're now known as TheWatcher |
| 11:03 | | Reiv is now known as vicious_barnacles_of_inf |
| 11:04 | | vicious_barnacles_of_inf is now known as Reiv |
| 11:38 | | gnolam [lenin@Nightstar-38637aa0.priv.bahnhof.se] has joined #code |
| 14:25 | | Tarinaky [Tarinaky@Nightstar-f349ca6d.plus.com] has joined #code |
| 15:08 | | Kindamoody [Kindamoody@Nightstar-4764665d.tbcn.telia.com] has quit [Ping timeout: 121 seconds] |
| 15:10 | | Kindamoody [Kindamoody@Nightstar-4764665d.tbcn.telia.com] has joined #code |
| 15:27 | | celticminstrel [celticminstre@Nightstar-f8b608eb.cable.rogers.com] has joined #code |
| 16:31 | | Kindamoody is now known as Kindamoody|out |
| 16:35 | | RichardBarrell_droid [yaaic@Nightstar-f68eb197.cable.virginmedia.com] has joined #code |
| 16:55 | | RichardBarrell_droid [yaaic@Nightstar-f68eb197.cable.virginmedia.com] has quit [Client closed the connection] |
| 17:53 | | Kindamoody|out is now known as Kindamoody |
| 18:29 | | AnnoDomini is now known as Birds |
| 18:56 | | RichardBarrell_droid [yaaic@Nightstar-f68eb197.cable.virginmedia.com] has joined #code |
| 20:34 | | Kindamoody is now known as Kindamoody|out |
| 20:39 | | Vornicus-Latens is now known as Vornicus |
| 20:42 | | Derakon[AFK] is now known as Derakon |
| 20:44 | <@Vornicus> | *vroom* |
| 20:44 | <@Vornicus> | I have a worksheet for 2-dimensional chi-squared around here somewhere. |
| 20:45 | < Reiv> | Shiiny. |
| 20:45 | < Reiv> | OK, so, the question, before legalspeak: |
| 20:47 | < Reiv> | Group 1: 3 out of 271. |
| 20:48 | < Reiv> | Baseline: 118 out of 10,000. |
| 20:48 | < Reiv> | Is Group 1 statistically significant? |
| 20:49 | < Reiv> | (I doubt it. But I need to prove that I doubt it.) |
| 20:50 | <@Vornicus> | If there's only one thing we should actually be using binomial distribution. |
| 20:52 | < Reiv> | Really? |
| 20:52 | < Reiv> | Oh. Jolly good. |
| 20:52 | < Reiv> | I bow to your knowledge, sir, so long as we get a convinient value out the other end. |
| 20:53 | <@Vornicus> | gnerk, but you can't use the normal approximation to get a good answer, so this might be fun. |
| 20:55 | < Reiv> | Why so? |
| 20:56 | <@Vornicus> | Because in order to get a "statistically significant" setup you need to pull off the top and bottom 2.5%. |
| 20:57 | <@Vornicus> | ...Which in this case is about half of the "0" result (and down) and about half of the "7" result and up. |
| 20:58 | <@Vornicus> | Which is to say, then, that the only actually statistically significant portion of the possible answers is "more than 7" |
| 20:59 | <@Vornicus> | While w'ere in the neighborhood, the actual mean of the possible results, coming off of baseline, is 3.19, so you're right there. |
| 21:02 | < Reiv> | Haha. Yeah. |
| 21:03 | < Reiv> | This is why I went hunting to see if I could find a Vorny >_> |
| 21:03 | <@Vornicus> | (we pull off the top and bottom 2.5% for a significance level of 5%, and we must do this (for non-approximated versions) by adding up result values until we hit that. |
| 21:03 | <@Vornicus> | Which happens about halfway through 0, and halfway through 7. |
| 21:04 | < Reiv> | Man, it's been way too long since my stats classes. |
| 21:04 | < Reiv> | !10000/271 |
| 21:04 | < DiceBot> | [Reiv] 10000/271 = 36.900369. |
| 21:05 | < Reiv> | !36.9*3 |
| 21:05 | < DiceBot> | [Reiv] 36.9*3 = 110.7. |
| 21:05 | < Reiv> | 110 vs 118. Yeah, something tells me this is going to be a 'no'. :p |
| 21:05 | <@Vornicus> | !118*271/10000 |
| 21:05 | < DiceBot> | [Vornicus] 118*271/10000 = 3.1978. |
| 21:06 | <@Vornicus> | (3 is also the mode, and the median.) |
| 21:08 | < Reiv> | (3 is in fact the only number we have~ |