Stack Exchange
log in sign up chat discuss faq users badges

Area 51 » Science

definition commitment beta
218
followers

Statistical Analysis

Launched Q&A site for statistics, data analysis, data mining and data visualization

Announcements

4  
I'd like to propose a change to 'Proposed Q&A site for statistics, data analysis and data mining'. It sounds a bit trivial, but the name as it stand implies that only people who do only statistics for a living should use the site. There are people in many other professions who might have a lot to contribute to the site, but be put off if they feel like it is just for people where statistics is their profession rather than part of their profession. – Ian Turner May 27 '10 at 20:57
8  
Statistics is not a subset of mathematics. It uses some mathematics, but so does physics, engineering, etc. Try asking any of these questions on MO and they will (rightly) be closed as off topic. – Rob Hyndman May 27 '10 at 23:40
5  
I've modified the subheading to take account of the comments being made. Let me know if you think this is better (perhaps vote up this comment). I'm still not sure what to do with the major heading. I understand the objections, but haven't come up with anything better yet. Feel free to make some suggestions in the comments. – Rob Hyndman Jun 1 '10 at 3:55
show 14 more announcements
no discussions yet discuss this proposal

113 Example Questions (12 closed)

active newest votes
up vote 1 down vote
When computing the Mahalanobis distance is the covariance matrix expected to be close to singular?
added by WikiSpeedia hang-around May 27 '10 at 12:16
link
1  
(From en.wikipedia.org/wiki/Mahalanobis_distance: "Mahalanobis distance is widely used in cluster analysis and classification techniques. It is closely related to Hotelling's T-square distribution used for multivariate statistical testing and Fisher's Linear Discriminant Analysis that is used for supervised classification.") – WikiSpeedia hang-around May 27 '10 at 12:19
up vote 1 down vote
What is the best way of determining that the scatter of a data set changes as one variable changes?
added by Ian Turner May 27 '10 at 12:17
link
up vote 1 down vote
Using R, how do I generate a boxplot from my data?
added by Andrew Song May 27 '10 at 21:18
link
1  
The R tag on stackoverflow is already pretty active: is the goal to move that community over to this site instead? – Shane Jun 1 '10 at 15:50
It does not have to be one or the other. Overlap is going to happen with the plethora of sites that will spring from Area51. – Stu Thompson Jun 1 '10 at 16:34
3  
I agree with Stu that there will be some overlap. However, as a general rule I think programming and syntax questions should go to StackOverflow and statistical questions should go here. The boundary is obviously fuzzy. – Rob Hyndman Jun 1 '10 at 22:09
up vote 1 down vote
Is SAS Enterprise Guide useful as a statistical analysis tool?
added by Jay Stevens May 29 '10 at 12:24
link
up vote 1 down vote
My data set has a high Kurtosis. what does this mean?
added by chollida May 31 '10 at 17:25
link
en.wikipedia.org/wiki/Kurtosis ... so I'm inclined to say it's not a good example. – Matt Parker Jun 8 '10 at 17:04
@Matt Parker, all you did was post a link to a wikipedia article. It's entirely unclear what point you were trying to make with the link. Can you expand on your reasoning? – chollida Jun 9 '10 at 19:28
2  
My apologies. The point I so feebly tried to make is that, while on-topic, the question isn't one that will make make experts think, "Finally, this is a statistics site I can get something from." It's just too basic to serve as an outstanding example of what the site should be about. If the question were more like, "I'm fitting a linear regression to a dependent variable with high kurtosis. How will this affect the model?", I think it would suit the aims of the StackExchange sites better - i.e., to create knowledge-sharing communities of experts. – Matt Parker Jun 9 '10 at 23:06
@Matt Parker, great response Matt, I agree with you. – chollida Jun 10 '10 at 17:02
up vote 1 down vote
How should I adapt ANOVA for categorical dependent variables?
added by Anon Jun 2 '10 at 3:22
link
up vote 1 down vote
How do I perform PCA on an RGB image?
added by Foster Brereton Jun 2 '10 at 20:48
link
up vote 1 down vote
Which methods are used for testing random variate generation algorithms?
added by Mehper C. Palavuzlar Jun 3 '10 at 10:38
link
up vote 1 down vote
Can you give some examples of cohort-modelling outside from medical statistics and actuarial science?
added by Karsten W. Jun 12 '10 at 11:57
link
up vote 0 down vote
What's the record for home runs in a single season of baseball? [closed]
added by Rob Hyndman May 25 '10 at 2:18
link

closed as off topic by Ian Turner, Mike Mazur, Shane, François G. Dorais, Michel de Ruiter Jun 15 '10 at 20:00

This question does not relate to the topic of the proposal.
It was closed as part of an automated migration of off-topic to close votes on September 29, 2011.

NOT BASEBALL STATS! I GET IT! haha – Joel Spolsky♦ May 25 '10 at 3:16
up vote 0 down vote
How should I present a bar chart with two classification variables?
added by Rob Hyndman May 25 '10 at 2:21
link
Should I use a three-dimensional bar chart, stacked bar chart, side-by-side barchart, or something else? – Rob Hyndman May 25 '10 at 2:21
I voted yes, because I believe that data visualization is just as important as the actual data analysis. But, I am assuming that you will be presenting some information in the question about what the data looks like and what you are trying to analyze. – Waleed Al-Balooshi May 27 '10 at 12:27
Data visualization is part of data analysis. In general, I am assuming that there will usually be more information than what is given in these short questions. – Rob Hyndman May 27 '10 at 12:32
up vote 0 down vote
Can I include covariates when forecasting using exponential smoothing?
added by Rob Hyndman May 25 '10 at 5:46
link
up vote 0 down vote
After using Grubbs' test to identify and remove an outlier, is it Kosher to run it again on the remaining values?
added by Harvey Motulsky May 25 '10 at 11:35
link
up vote 0 down vote
What is the best free software application for basic statistical analysis?
added by Ciaran De Buitlear1 May 25 '10 at 15:19
link
8  
Best of lists should not be encouraged, but this is likely to be something A LOT of visitors might be interested in. – Ivo Flipse May 25 '10 at 20:59
3  
It's on topic, but is subjective and argumentative. The body of the question might remedy this by explaining what problem the asker is trying to solve (i.e. best for what?). – Anton Geraschenko May 27 '10 at 6:48
1  
This seems more suited for a community wiki type of questions. I think it needs to be rephrased. Maybe "What tool is most used in Econometric Analysis and Why?" – Waleed Al-Balooshi May 27 '10 at 12:21
voted up, but subjective no? – George May 28 '10 at 4:48
Subjective, unless Community Wiki. Compare stackoverflow.com/questions/1711/… – György Andrasek Jun 3 '10 at 2:49
up vote 0 down vote
How can I graph a frequency plot of data in Excel?
added by Rog May 27 '10 at 4:57
link
Such a common problem that people don't understand. Really improtant to have a good resource for this sort of thing. – Ian Turner May 27 '10 at 13:35
I agree that it's important to have a good resource for it, but I just don't want to see a thousand "How do I graph Plot X in Software Y?" questions. They are essentially limitless and are probably better answered in the program's help files. – Matt Parker Jun 2 '10 at 23:55
You will get an answer on SO for that – Karsten W. Jun 6 '10 at 15:17
up vote 0 down vote
Which tools should I use to scrape data from a webpage? [closed]
added by Juan A. Navarro, edited by Rob Hyndman Jun 2 '10 at 4:18
link

closed as off topic by Yacoby, Karsten W., therefromhere, Joe Mako, Charles Stewart Jun 7 '10 at 12:35

This question does not relate to the topic of the proposal.
It was closed as part of an automated migration of off-topic to close votes on September 29, 2011.

1  
Appropriate for SO but not for this site I think. – Anon Jun 2 '10 at 3:02
*scrape data...? – d03boy Jun 2 '10 at 4:06
d03boy - let's say there's a government website with hundreds and hundreds of tables of data that I want. If the tables and pages have a pretty regular structure, you can write a program to cycle through all of the pages, collect the data, and create a database on your local file. – Matt Parker Jun 16 '10 at 23:42
up vote 0 down vote
How can I graph two 3D data sets into a planar graph with MS Excel 2008 for Mac? [closed]
added by Stu Thompson May 27 '10 at 6:30
link

closed as off topic by Ian Turner, Yacoby, walkytalky, Harlan, Sinan Ünür Jun 16 '10 at 22:13

This question does not relate to the topic of the proposal.
It was closed as part of an automated migration of off-topic to close votes on September 29, 2011.

Do you mean Excel 2007 or 2010? – Waleed Al-Balooshi May 27 '10 at 12:35
2  
2008 is the Mac version and it is actually different enough to the Windows version to cause this sort of problem. I would argue this question should be better sited on a Microsoft Excel Stack Exchange. – Ian Turner May 27 '10 at 13:36
Yup, I meant Mac. Clarified. – Stu Thompson May 27 '10 at 15:33
I agree with Splash. I really don't want this to be a MS Excel plots help site. There are plenty of resources on the web to help people with Office products, but precious few that are much use for statistics. – Matt Parker Jun 2 '10 at 23:59
up vote 0 down vote
What type of statistical analysis should I use when I have data which is both MCAR and MNAR?
added by Menno May 27 '10 at 8:37
link
up vote 0 down vote
What is k-means clustering?
added by Ian Turner May 27 '10 at 15:00
link
To basic question imo – Peter Smit Jun 16 '10 at 17:29
up vote 0 down vote
What is the easiest way to generate a Poisson distribution programmatically.
added by Ian Turner May 27 '10 at 21:06
link
1  
I'd thin this question is too broad. Which language? What output format? What inputs? – chollida Jun 1 '10 at 18:39
up vote 0 down vote
How do I extract trial data from a database?
added by Jon Seigel May 28 '10 at 0:30
link
up vote 0 down vote
What is the best application to use to store trial data?
added by Jon Seigel May 28 '10 at 0:31
link
up vote 0 down vote
What is the best way to compute how homologous two genes are?
added by Harvey Motulsky May 28 '10 at 3:04
link
I posted this to start a discussion about analyzing molecular biology data. I think analysis of sequences, homology, genetic linkage, etc. are in another world and belongs on another site. – Harvey Motulsky May 28 '10 at 3:05
1  
... like biostar.stackexchange.com. – Matt Parker May 28 '10 at 6:19
up vote 0 down vote
How do I calculate the KS for a set of data using SAS?
added by Jay Stevens May 29 '10 at 12:24
link
up vote 0 down vote
Can someone point me to an algorithm that I can use to generate truncated (from both sides) multivariate normal random variables?
added by Anon Jun 2 '10 at 3:26
link
up vote 0 down vote
How can I speed up my matlab routine which uses MCMC methods for estimation? [closed]
added by Anon Jun 2 '10 at 3:53
link

closed as off topic by Matt Parker, chollida, Rob Hyndman, Peter K., Mike Mazur Jun 5 '10 at 10:33

This question does not relate to the topic of the proposal.
It was closed as part of an automated migration of off-topic to close votes on September 29, 2011.

Pretty clearly a question for StackOverflow. When I'm optimizing code, I want computer geniuses picking it over. – Matt Parker Jun 3 '10 at 0:01
That was the intent! I wanted it be declared as off-topic as I agree with your assessment.To my surprise most of us saw it as on topic. :-) – Anon Jun 3 '10 at 0:21
up vote 0 down vote
What is the best method for finding a good covariate?
added by Menno Jun 2 '10 at 9:10
link
Probably too general a question. – Pedro J. Aphalo Jun 8 '10 at 13:28
up vote 0 down vote
I have a huge (100 Go) dataset of commercial data. How should I store them to be able to use a free statistical software ?
added by robin girard, edited by WikiSpeedia hang-around Jun 3 '10 at 21:58
link
up vote 0 down vote
How can I find the pdf (probability density function) given the cdf (cumulative distribution function)?
added by Mehper C. Palavuzlar Jun 3 '10 at 10:59
link
up vote 0 down vote
How much should I expect to pay for a SAS licence? [closed]
added by Simon Nickerson Jun 3 '10 at 19:04
link

closed as off topic by delete, Shane, Pedro J. Aphalo, Peter Smit, Harvey Motulsky Jun 8 '10 at 16:26

This question does not relate to the topic of the proposal.
It was closed as part of an automated migration of off-topic to close votes on September 29, 2011.

Too variable. it depends on the country, how many licenses you buy and the price at the time you ask. – chollida Jun 3 '10 at 22:55
up vote 0 down vote
What options do I have for randomizing binary data while preserving some clusters
added by Peter Smit Jun 8 '10 at 10:30
link
Maybe one sentence doesn't catch this question completely. Here randomization is meant in the context of statistical significance testing. – Peter Smit Jun 16 '10 at 17:26
up vote -1 down vote
What is the unemployment rate in Taiwan? [closed]
added by Rob Hyndman May 25 '10 at 2:17
link

closed as off topic by Noah Snyder, Joe Mako, Shane, François G. Dorais, Maxim Zaslavsky Jun 8 '10 at 19:31

This question does not relate to the topic of the proposal.
It was closed as part of an automated migration of off-topic to close votes on September 29, 2011.

3  
A better question might be "What factors determine the unemployment rate? – Troggy May 27 '10 at 4:20
This question sits on the thin line between on- and off-topic. As an econometrician, I would be interested in where I can find unemployment rates for certain countries. So, this could be an on topic question if you replace the "what is" by "where can I find". – Waleed Al-Balooshi May 27 '10 at 12:11
1  
For me it is totally off topic. The site should be about data analysis etc. rather than how to gether the data. Getting general data covers just too many fields that are probably better suited to their own Stack Exchanges. – Ian Turner May 27 '10 at 12:40
2  
I agree with Splash. Questions like "How can I identify factors associated with the unemployment rate?" seem on-topic to me, and maybe "How are unemployment rates calculated?", but this is a reference question. Just because a question refers to a statistic doesn't mean it's a question about statistical analysis. – Matt Parker May 27 '10 at 18:22
This is exactly what Wolfram Alpha is for. Incidentally it's 4.1% (world rank 157th) (2008 estimate) – blissapp Jun 2 '10 at 23:12
up vote -1 down vote
GraphPad Prism creates a graph with mean and error bars directly from my raw data. How can I get it to show me the SD and SEM?
added by Harvey Motulsky May 25 '10 at 14:14
link
No tech support here. This site should be for statistical principles, not details of one particular program. – Harvey Motulsky May 25 '10 at 14:15
up vote -1 down vote
What are the pros and cons of fitting curves with nonlinear regression using GraphPad Prism vs. SigmaPlot?
added by Harvey Motulsky May 25 '10 at 14:16
link
This is trickier, but I think this is a slippery slope to a boring site. I'd keep it focussed on questions about analyses, not tools. – Harvey Motulsky May 25 '10 at 14:17
Like you say, if you start forbidden EVERYTHING that's not 'theoretical' you might end up with a very boring site. I would leave it be – Ivo Flipse May 26 '10 at 21:32
I think general tool questions are ok. I wouldn't want to see tech support questions for a specific tool, but I think it is useful to allow questions on what tool to use for a specific type of analysis. – Rob Hyndman May 27 '10 at 6:29
up vote -1 down vote
What models could I use to forecast the likelihood of a state or event based on historical data?
added by Mike Mazur May 27 '10 at 2:54
link
For example: how likely is it that Steve will be in his office at 10:00am based on his presence history on IRC? – Mike Mazur May 27 '10 at 2:56
I voted no. The idea of this site is to ask questions that have answers, not questions that require a text book to answer. Not to discuss perspectives. This one seems way too vague. If someone asked it, others might be able to point him towards the right text book. But there is no way to answer a question like that, so it doesn't really fit. One instance of that question like that is: What is the chance that the global mean temperature will be more than 4 degrees C warmer than now in 50 years? Many books have been written on that. – Harvey Motulsky May 27 '10 at 3:04
I'm not a statistician, so please take this with a grain of salt. I think this question has merits. One potential answer could be: Try a markov model. Here's a link. Or, use Bayseian statistics, etc. It could end up being a very useful resource on the web. – Scott Wisniewski May 27 '10 at 3:39
Voting no because it is too vague. A more specific question with context might be ok. – Rob Hyndman May 27 '10 at 3:44
I agree Scott, it just needs to be more specific. I'll add a similar question that I think would be more appropriate. – Rob Hyndman May 27 '10 at 4:32
up vote -1 down vote
What software can I use to automatically layout network graphs?
added by Juan A. Navarro May 27 '10 at 5:30
link
up vote -1 down vote
I have two children. One is a boy born on a Tuesday. What is the probability I have two boys? [closed]
added by Ian Turner May 27 '10 at 11:52
link

closed as off topic by ilhan, Peter K., Rob Hyndman, Jeromy Anglim, Anon Jun 5 '10 at 12:45

This question does not relate to the topic of the proposal.
It was closed as part of an automated migration of off-topic to close votes on September 29, 2011.

Sounds like homework – Rob Hyndman May 27 '10 at 11:57
I actually took this question from here: newscientist.com/article/…. It is actually more involved than you think, but really is a statisitics 'game'. I asked the question to see if users want this sort of game on the Stack Exchange. – Ian Turner May 27 '10 at 12:04
2  
This site is about data analysis, not probability. But a few brain teasers will make it more fun. More fun = more visitor = more chance of critical mass. So I vote yes. – Harvey Motulsky May 27 '10 at 13:32
Wait, isn't this one of those problems where people just can't seem to agree on the outcome? (Like the Monty Hall Problem) – Menno May 27 '10 at 18:01
Probability goes hand-in-hand with statistics, so I don't see why that subject would be off-topic. That said, this is a bad question. – Shane Jun 7 '10 at 13:42
up vote -1 down vote
How do I determine if two samples are related if I don't have enough data points to satisfy the Central Limit Theorem?
added by cletus May 27 '10 at 23:29
link
up vote -1 down vote
How do I generate data for missing values using SAS in preparation for fitting a logistic regression?
added by Jay Stevens May 29 '10 at 12:26
link
up vote -1 down vote
How can I tweak (hack/modify) STATA so that it uses more CPU cores?
added by Stu Thompson May 30 '10 at 9:08
link
(Or 'how can i do something dodgy in the world of statistics analysis') – Stu Thompson May 30 '10 at 9:09
Do you mean STATA? – Rob Hyndman Jun 2 '10 at 2:01
More approroate for STATA tech support or SO perhaps? – Anon Jun 2 '10 at 3:07
STATA, yes. (Been working with physical SATA hard drives lately :P) The edit feature is broken for me again...will write Area51 kids. – Stu Thompson Jun 2 '10 at 5:17
@Anon: Write STATA about how to hack their own software? Did you read the questions? – Stu Thompson Jun 2 '10 at 5:17
show 3 more improvement suggestions
prev 1 2 3 next

This site has

Launched!

This Stack Exchange site's beta was successful, so it launched 10 years ago.

proposed by

Rob Hyndman
86.5k●36●223●367

10 years ago

edited by

Jaydles ♦ 1
108k●90●418●764

10 years ago

viewed

26,792 times

latest activity

10 years ago

followers

users also following

21.6% Mathematics
12.8% Quantitative Finance
12.4% Web Applications
12.4% TeX, LaTeX and fr...
23.9% only this proposal

followers active in

69.3% Stack Overflow
57.8% Cross Validated
49.5% Super User
45.0% Meta Stack Overflow
41.3% Server Fault
36.2% Web Applications

recent followers

added Aug 5 '10 at 17:44
las3rjock
12k●1●61●65
added Jul 18 '10 at 21:28
kitukwfyer
9,602●1●43●87
added Jul 18 '10 at 13:28
ArnaudB
51●1
added Jul 17 '10 at 17:42
ryfm
150●10
added Jul 16 '10 at 21:06
James Roth
13.5k●4●48●55
added Jul 16 '10 at 19:31
Abner Huang
52●1
added Jul 16 '10 at 16:34
bugsyrocker
51●2
added Jul 16 '10 at 14:23
koolkao
51●1
added Jul 16 '10 at 8:19
Egon Willighagen
4,120●8●34●88
added Jul 15 '10 at 14:57
NickAldwin
14.2k●21●78●135
added Jul 14 '10 at 17:02
James
67.3k●14●186●279
added Jul 14 '10 at 2:15
warren
98.2k●90●476●1093
added Jul 13 '10 at 20:44
Conci
52●1
added Jul 13 '10 at 14:38
txwikinger
50.7k●28●263●432
added Jul 13 '10 at 13:49
Tim
51●1
added Jul 13 '10 at 11:54
Baltimark
11.1k●16●58●65
added Jul 12 '10 at 5:29
Davis McC
64●6
added Jul 12 '10 at 1:29
user9536
51●1
added Jul 11 '10 at 11:08
Wojciech Sobala
7,373●2●21●30
added Jul 11 '10 at 6:03
terrace
3,507●4●33●74
added Jul 9 '10 at 17:21
xkcd150
9,710●4●30●39
added Jul 9 '10 at 2:37
Michael Ekstrand
35.2k●15●122●243
added Jul 8 '10 at 17:16
dassouki
23.9k●35●205●356
added Jul 8 '10 at 0:13
pds
51●1
added Jul 7 '10 at 23:13
Evion
78●2
added Jul 7 '10 at 17:14
user8586
51●1
added Jul 7 '10 at 14:34
Łukasz Lew
58.3k●50●200●337
added Jul 7 '10 at 11:47
oliverzip
71●2
added Jul 7 '10 at 11:03
William
4,445●12●43
added Jul 7 '10 at 3:46
repka
51●1
added Jul 6 '10 at 4:47
Thomas Bishop
51●1
added Jul 5 '10 at 21:39
user8288
10.4k●24●77●109
added Jul 5 '10 at 20:05
jbr
109●4
added Jul 5 '10 at 14:45
Dr G
7,955●48●62
added Jul 4 '10 at 21:24
Coronier
51●1
added Jul 4 '10 at 17:23
vrish88
17.9k●9●45●67
added Jul 3 '10 at 4:09
adi92
8,783●5●38●48
added Jul 2 '10 at 23:03
apeescape
1,528●8●15
added Jul 2 '10 at 8:56
Marcos
51●1
added Jul 2 '10 at 7:21
Wheelie
4,626●2●34●58
feed icon proposal feed
faq | blog | legal | privacy policy | contact us | feedback always welcome
site design / logo © 2021 Stack Exchange Inc; user contributions licensed under cc by-sa; see the licensing help page for more information.
rev 2021.2.22.577