> On Jan 23, 2016, at 3:03 PM, Jim Lemon wrote:
>
> Hi,
> Seeing that the "rstanarm" package was available on CRAN in an answer to:
>
> Constrained Poisson model / Bayesian Poisson model
>
> I tried to install it. Took quite a while, but compilation failed at:
>
> ^
> {standard input}: Asse
Hi,
Seeing that the "rstanarm" package was available on CRAN in an answer to:
Constrained Poisson model / Bayesian Poisson model
I tried to install it. Took quite a while, but compilation failed at:
^
{standard input}: Assembler messages:
{standard input}:3144199: Warning: end of file in stri
Assuming that's qplot from ggplot2, it's trying to pass span to the
Point Geom which doesn't recognize it. I highly suggest moving away
from using qplot and working with the stat_s and geom_s directly with
ggplot().
On Sat, Jan 23, 2016 at 8:46 AM, Jeff Reichman wrote:
> R-Users
>
>
>
> Anyone se
with glm(), you might try the quasi binomial family
On Saturday, January 23, 2016, pari hesabi wrote:
> Hello everybody,
>
> I am trying to fit a logistic regression model by using glm() function in
> R. My response variable is a sample proportion NOT binary numbers(0,1).
>
> Regarding glm() fun
R-Users
Anyone see what maybe wrong with the following command, other than R doesn't
seem to recognize the "span" parameter - it should must be my syntax.
> qplot(seq, count,geom=c("point","smooth"), span=0.8)
Error: Unknown parameters: span
Jeff
[[alternative HTML version de
Hi David,
I'm sorry. I'm not familiar with posting problems on helppages.
As the data I deal with is confidential I can't provide all details,
but I will try to be as precise as possible about my problem:
As I said I'm working on a Poisson regression model with a linear
predictor and the identit
You can keep it a dataframe as follows:
> set.seed(123)
> x <- data.frame(a = 1:10, b = 2:11, c = 3:12, other = rnorm(10))
> x
a b c other
1 1 2 3 -0.56047565
2 2 3 4 -0.23017749
3 3 4 5 1.55870831
4 4 5 6 0.07050839
5 5 6 7 0.12928774
6 6 7 8 1.71506499
7
Alternatively you might use log(p/1-p) as your dependent variable and use
OLS with robust standard errors. Much of your inference would be analogous
to a logistic regression
John C Frain
3 Aranleigh Park
Rathfarnham
Dublin 14
Ireland
www.tcd.ie/Economics/staff/frainj/home.html
mailto:fra...@tcd.ie
> On Jan 23, 2016, at 12:41 PM, pari hesabi wrote:
>
> Hello everybody,
>
> I am trying to fit a logistic regression model by using glm() function in R.
> My response variable is a sample proportion NOT binary numbers(0,1).
So multiply the sample proportions (and 1-proportions) by the number
> On Jan 23, 2016, at 9:40 AM, David Winsemius wrote:
>
>
>> On Jan 23, 2016, at 5:24 AM, mara.pfleide...@uni-ulm.de wrote:
>>
>> Hi David,
>>
>> I'm sorry. I'm not familiar with posting problems on helppages.
>> As the data I deal with is confidential I can't provide all details,
>> but I wi
> On Jan 23, 2016, at 5:24 AM, mara.pfleide...@uni-ulm.de wrote:
>
> Hi David,
>
> I'm sorry. I'm not familiar with posting problems on helppages.
> As the data I deal with is confidential I can't provide all details,
> but I will try to be as precise as possible about my problem:
>
> As I said
One additional point:
On 23/01/2016 8:33 AM, Duncan Murdoch wrote:
distinction between answers and comments, it's gamification (badges,
One advantage of Stackoverflow is that you can go back and correct silly
errors (like misspelling "its").
Duncan Murdoch
On Sat, 23 Jan 2016, Duncan Murdoch wrote:
I don't see duplication as counterproductive -- some people like one style,
some like the other, both will find answers.
Duncan,
There's another factor to add to your list. Mail lists, such as r-help and
the various SIGs _push_ messages to subscrib
On 23/01/2016 7:28 AM, Jean-Luc Dupouey wrote:
Dear members,
Not a technical question:
The number of threads in this mailing list, following a long period of
increase, has been regularly and strongly decreasing since 2010, passing
from more than 40K threads to less than 11K threads last year. T
Hi,
from my perspective as R user and package maintainer I would consider
the normalization of the r-help mailing list a good sign. r-help is
still a good place for general questions, while more specific
discussions moved to the r-sig-... mailing lists.
Maybe a slight reduction can also be a
Dear members,
Not a technical question:
The number of threads in this mailing list, following a long period of
increase, has been regularly and strongly decreasing since 2010, passing
from more than 40K threads to less than 11K threads last year. The trend
is similar for most of the "ancient"
16 matches
Mail list logo