Reputation
13,606
Top tag
Next privilege 15,000 Rep.
Protect questions
Badges
2 37 70
Newest
 Enlightened
Impact
~712k people reached

9h
comment Determining if data is normally distributed
I would say you have a single sample from the population of all phone calls. You looked at 3 different hours, so you might want to control for different mean call rates in the three hours, but this is still a sample from the population. You could work on a single hour as the sample but then you'd have no means of testing whether different hours had different call rates.
19h
comment Determining if data is normally distributed
You might be able to approximate the data with a normal distribution (plot them and see), but you must realise that the data are discrete, can't be less than zero, and likely have larger variance as counts get larger.
1d
comment How to include an interaction term in GAM?
I should update this answer a little given some new functionality in the mgcv package in terms of splines for marginal bases. That said, I don't agree that you need to fix the degrees of freedom for the spline. The key is to ensure that the bases for the models are appropriately nested. Then differences between models are possible by setting some of the coefficients for the basis functions to zero, just as would happen in a linear model with non-spline terms.
2d
revised Data sets for which PCA can classify better than LDA (using a very small training set)
typo
Jul
23
comment What is the origin of squaring centred data as way to model variances instead of means?
We're getting a little away from the specifics of the original question but this discussion is very useful, so thanks. Can I do inference on the robust standard errors? In the R implementation in sandwich I can get & use the covariance matrix but then what? In the specific context I want to ask whether the variance changes with time & where it changes in time, the latter of which would be given by the GAM $y_i^{\prime} \sim \beta_0 + f(\mathrm{time}_i)$.
Jul
23
comment What is the origin of squaring centred data as way to model variances instead of means?
@AdmaO OK, I see what you mean now, esp re variograms. In the case of the variogram, as I understand it, that is a global assessment of variance; over all pairs of data separation. It's not a model for the variance conditional on $x$ but on separation in space/time, right? I'm interested in a model that allows the variance to change with time, just as a linear regression would allow the mean to change with time, with time being the $x$ data. Hence I'm looking for a canonical reference for this sort of model. Perhaps there isn't one and the justification derives simply from the math?
Jul
23
revised What is the origin of squaring centred data as way to model variances instead of means?
typo
Jul
23
comment What is the origin of squaring centred data as way to model variances instead of means?
I wasn't meaning that I wanted to look at the residuals of a model and compute their variance, which is what your answer seems to be getting at. I and the linked question envisaged fitting a model to the transformed values $y_i^{\prime}$ directly, so that rather than the regression model estimating the conditional mean of $y_i$ it was estimating the conditional variance of $y_i$. Levene's test is essentially ANOVA on the transformed $y_i$ (but variations do different transformations). As for motivation; time series models of variance in continuous time seem hard & not widely implemented :-)
Jul
23
answered Penalized regression with zero-inflated models
Jul
23
asked What is the origin of squaring centred data as way to model variances instead of means?
Jul
17
awarded  Enlightened
Jul
17
awarded  Nice Answer
Jul
13
revised Backtransform coefficients of a Gamma-log GLMM
added 1174 characters in body
Jul
13
answered Backtransform coefficients of a Gamma-log GLMM
Jul
7
revised How to handle gaps in a time series when doing GAMM?
typo
Jun
30
revised gam models with random effect R
added 76 characters in body
Jun
30
comment gam models with random effect R
I should add that, unless there is wording to the contrary somewhere, gamm4 returns the full lmer fit and according to the documentation for the lme4 package, predictions can be at the population level only if requested. predict on the $mer component of the returned object should return predictions conditional upon the random effects (i.e. including them).
Jun
30
revised gam models with random effect R
added 636 characters in body
Jun
30
answered gam models with random effect R
Jun
30
comment Get survival rates from a cox regression in R
The variable type and delta are not in the kidney data set I get from survival