Reputation
12,683
Top tag
Next privilege 15,000 Rep.
Protect questions
Badges
1 21 65
Impact
~556k people reached

Apr
25
awarded  Notable Question
Mar
31
comment For a continuous DV that ranges between 0 and 1, which of the gbm package's distributions would you recommend?
Another possibility is to transform your variable eg by taking its logit so it takes up the whole space of real numbers. Then least squares is likely to work quite well. But I'm not familiar enough with gbm to give you a definitive answer.
Feb
12
awarded  Nice Answer
Feb
5
awarded  Revival
Jan
19
comment What type of regression will improve the prediction for these data?
maybe... OP's call. If they want to use R, fitting a gam is very nearly as simple as fitting the original regression, and is just a one-liner. I would think that adding polynomials or trigonometric functions by hand (some of the other suggestions) would be in fact more complex.
Jan
19
reviewed Close What is the answer to this Chebyshev's rule questions in statistics?
Jan
19
answered What type of regression will improve the prediction for these data?
Dec
28
awarded  Custodian
Dec
28
reviewed No Action Needed improve precision in text classification
Dec
28
reviewed No Action Needed Python Text Classification Features Engineering
Dec
28
reviewed No Action Needed Classifier with adjustable precision vs recall
Dec
27
awarded  Electorate
Dec
13
awarded  Yearling
Sep
20
revised Proving similarities of two time series
added 412 characters in body
Sep
19
comment Proving similarities of two time series
Thanks @user333700, I'll have a think.
Sep
18
comment Proving similarities of two time series
Thanks, it might help, but even then you can have identical acfs and two very different processes eg see ellisp.github.io/blog/2015/09/19/timeseries-same-acf . I'm pretty sure the answer requires multiple runs of each data generating black box and create a similarity statistic of some sort.
Sep
13
comment Suppose every family makes babies until a boy is born: will this result in gender bias in the society?
I've done an answer but won't post it until we know if this is homework or not (in which case I'll turn it into hints).
Sep
13
revised Proving similarities of two time series
linked to IrishStat reference to F statistic test of common parameters
Sep
13
answered Proving similarities of two time series
Sep
13
comment Proving similarities of two time series
Judging from the ARIMA results, the simulation values are for a stationary time series that fluctuates in the interval [-10, 10] (approximately). This doesn't look like a number of infections; or even a number of new infections. Have you transformed it, or taken differences twice, or something, before fitting auto.arima?