meta user
network profile
| bio | website | naught101.org |
|---|---|---|
| location | Australia | |
| age | ||
| visits | member for | 1 year, 3 months |
| seen | May 21 at 10:44 | |
| stats | profile views | 189 |
Contact:
Skype: naught101
XMPP/Googletalk: naught101@jabber.org
|
May 18 |
comment |
How to compare three different replacements for eggs in baking? @Wendy, you probably should add that information to the question, and kyle should add his responses to his amswer |
|
May 17 |
comment |
when to aggregate when time series forecasting You can never absolutely trust a prediction - you need confidence intervals. Have you tried plotting a projection with confidence intervals? Your second prediction algorithm doesn't make much sense to me. Isn't a given product always going to be in the same subcategory, category, and department? If so, isn't the forcast for the product already going to include all the information that the categories could add anyway? What would you be regressing against? |
|
May 17 |
comment |
How should I color scheme a heat map based off data below? @EngrStudent: I think you should post that as an answer. |
|
May 17 |
answered | How to standardise cases within groups to perform ranking across groups and over time? |
|
May 17 |
comment |
How to interpret the output of the summary method for an lm object in R? @godzilla: Perhaps try some of the answers at stats.stackexchange.com/questions/31/… |
|
May 17 |
comment |
How to interpret the output of the summary method for an lm object in R? @godzilla: I think you really need to read an introductory stats text, and/or the wikipedia pages I linked to. I answered those exact questions in my answer. If you want detail, then ask for specifics. |
|
May 17 |
comment |
How to interpret the output of the summary method for an lm object in R? @godzilla: um... not unless you specify what it is that you want to know. |
|
May 17 |
comment |
How to interpret the output of the summary method for an lm object in R? @godzilla: if the std.err goes up, then the distribution of likely values is widening, which means that your effect size will become swamped, so making predictions will be harder. |
|
May 17 |
revised |
How to interpret the output of the summary method for an lm object in R? added 32 characters in body |
|
May 17 |
answered | How to interpret the output of the summary method for an lm object in R? |
|
May 16 |
comment |
What PDF should be fit to a rank histogram? @Glen_b: I'm looking for the argument, not the description. |
|
May 16 |
comment |
What PDF should be fit to a rank histogram? @Glen_b: Basically I thought that because it's discrete data over a finite interval, and the graphs look similar. I don't have any better rationale, but that's kind of what I was trying to get at with the question I guess: is there a reason to assume that this data is NOT from a close-to-beta-binomial distribution? |
|
May 16 |
comment |
Are non-square latin hypercubes viable? See stats.stackexchange.com/questions/58201/… for a potential solution to this |
|
May 16 |
comment |
How to determine the sample size of a Latin Hypercube sampling? See also stats.stackexchange.com/questions/24604/… |
|
May 16 |
revised |
What PDF should be fit to a rank histogram? Add example image |
|
May 16 |
revised |
How to statistically compare two fibonacci algorithms? add images |
|
May 16 |
reviewed | Reviewed How to statistically compare two fibonacci algorithms? |
|
May 16 |
suggested | suggested edit on How to statistically compare two fibonacci algorithms? |
|
May 16 |
comment |
How to statistically compare two fibonacci algorithms? Do you really need statistics to tell you that the second sequence is hundreds or thousands of times faster for long sequences? What are you trying to prove that a single glance at the data doesn't already improve? |
|
May 15 |
comment |
Why are drug trials designed with discrete treatment values? Couldn't you discretise the data afterwards, and then run any tests that would be available for discrete data? |
