OT What is your subjective estimate of the percentage of original posts that need list members to ask follow up questions.

[Art Kendall]

In consulting it is frequently important to move from the "presenting
question" to the underlying question.

I was wondering what swag list members would give for "the percentage of
original posts that need list members to ask follow up questions, before
being confident of giving a helpful reply"?

--
Art Kendall
Social Research Consultants

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD

[Ryan]

I can only speak to stats posts that interest me and therefore pay attention to. That said, 50%, maybe a little lower? Hard to estimate off-hand. I generally try to work with what I'm given and state assumptions I have to make in order to provide an answer.

Ryan

On Oct 24, 2012, at 11:05 AM, Art Kendall <[hidden email]> wrote:

> In consulting it is frequently important to move from the "presenting
> question" to the underlying question.
>
> I was wondering what swag list members would give for "the percentage of
> original posts that need list members to ask follow up questions, before
> being confident of giving a helpful reply"?
>
> --
> Art Kendall
> Social Research Consultants
>
> =====================
> To manage your subscription to SPSSX-L, send a message to
> [hidden email] (not to SPSSX-L), with no body text except the
> command. To leave the list, send the command
> SIGNOFF SPSSX-L
> For a list of commands to manage subscriptions, send the command
> INFO REFCARD

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD

[Rich Ulrich]

I ask fewer follow-up questions that most people who answer
a lot of question.  Now and then, I read slowly and carefully,
taking on the challenge of puzzling it out.

Sometimes, it is because I am willing to *guess at* what
the question might be.  I exercise what David M. calls
"internet telepathy."   I don't really want to post something
that might be egregiously inapt, but I do feel good if I get
it right.  If there is a lesson for other readers, I am more
willing to take the chance.  I try to make it clear when I am
guessing, so my answer is also a question.
- It is easier when I have made (or seen) the error before.  
- Sometimes I wait to see if someone else will grasp what
the question is about.  Or they show that I am not alone in
failing to understand, by asking.

It might be half. 

--
Rich Ulrich

> Date: Wed, 24 Oct 2012 21:41:32 -0400

> From: [hidden email]
> Subject: Re: OT What is your subjective estimate of the percentage of original posts that need list members to ask follow up questions.
> To: [hidden email]
>
> I can only speak to stats posts that interest me and therefore pay attention to. That said, 50%, maybe a little lower? Hard to estimate off-hand. I generally try to work with what I'm given and state assumptions I have to make in order to provide an answer.
>
> Ryan
>
> On Oct 24, 2012, at 11:05 AM, Art Kendall <[hidden email]> wrote:
>
> > In consulting it is frequently important to move from the "presenting
> > question" to the underlying question.
> >
> > I was wondering what swag list members would give for "the percentage of
> > original posts that need list members to ask follow up questions, before
> > being confident of giving a helpful reply"?
> >
> ...

[Kornbrot, Diana]

My estimate also ~50%
Advice to advice seekers

1. FIRST explain problem in words not statistical techniques. E.g. Would like to know if socioeconomic status aand employment status have an effect on happiness
2. Describe ALL variables, and their role in proposed model or problem
3. Then, ask how to implement or interpret an SPSS analysis, or a restructuring of the data, or computation of a new variable
   

1&2 give the context of the problem which is essential to getting good advice. CONTEXT is useful even when problem is ab out data manipulation prior to analysis. My estimate is that aobut 40% of problems fall into this category
Maybe SPSS discussion can give this kind of generic advice to advice seekers
Best

Diana


On 25/10/2012 02:41, "Ryan Black" <ryan.andrew.black@...> wrote:

I can only speak to stats posts that interest me and therefore pay attention to. That said, 50%, maybe a little lower? Hard to estimate off-hand. I generally try to work with what I'm given and state assumptions I have to make in order to provide an answer.

Ryan

On Oct 24, 2012, at 11:05 AM, Art Kendall <Art@...> wrote:

> In consulting it is frequently important to move from the "presenting
> question" to the underlying question.
>
> I was wondering what swag list members would give for "the percentage of
> original posts that need list members to ask follow up questions, before
> being confident of giving a helpful reply"?
>
> --
> Art Kendall
> Social Research Consultants
>
> =====================
> To manage your subscription to SPSSX-L, send a message to
> LISTSERV@... (not to SPSSX-L), with no body text except the
> command. To leave the list, send the command
> SIGNOFF SPSSX-L
> For a list of commands to manage subscriptions, send the command
> INFO REFCARD

=====================
To manage your subscription to SPSSX-L, send a message to
LISTSERV@... (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD

---

Emeritus Professor Diana Kornbrot
email:  d.e.kornbrot@...    
web:    http://dianakornbrot.wordpress.com/
Work
Department of Psychology
School of Life and Medical Sciences
 University of Hertfordshire
 College Lane, Hatfield, Hertfordshire AL10 9AB, UK
   voice:   [phone]
   fax:     [phone]
Home
 19 Elmhurst Avenue
 London N2 0LT, UK
    voice:   [phone]
    mobile: [phone]
    fax:      [phone]

---

[Andy W]

Since you are a statistical consultant, why don't you say, take a random sample of a few days, and look up the posts on those days and make your own determination if further clarification was needed before giving a helpful reply (of course you could even expand upon this by having multiple raters as well).

Of course this is partly in jest, as "helpful reply" is IMO to vacuous a definition to have any clear meaning (I don't intend to write anything that is not helpful). One of the nice things about the stackoverflow type sites (see the one for statistics) is that they have the ability to make comments on posts, as opposed to actual answers, to basically ask for such clarifications.

You could look it up in their data to see how many questions have comments and subsequent edits for some comparable (already compiled) stats on a neighboring forum. Or of course you could conduct a convenience sample of whomever replies to this thread about their subjective guess of the percent of questions that need further clarification, your call!

[Marhefka, Stephanie]

Hello. I will be out of the office  until Thursday, November 1, 2012. I will do my best to respond to you upon my return. If you have not heard back by Monday, November 5, please feel free to re-send your email or call to follow up.

 

Thank you,

Stephanie L. Marhefka, Ph.D.