|
|
15-11-2015, 01:37 AM
|
|
Quote:
Originally Posted by Unregistered
Knowing how to click on statistical software is different from knowing how to use regression analysis.
Did u do any diagnostic tests to check for normality, multicollinearity, and homoscedasticity?
if the model failed any of the test, how do u proceed?
How do u choose the the independent variables? by experience? based on empirical result? stepwise or some other forms of selection process? Is the model variation in discrete selection process a concern? If so, should I use penalty regression instead?
And that is just the model building stage. There are many more other issues to take note of at the inference stage.
|
Yea we do have some data QC procedures that we need to check for before processing. Normality yes, the other 2 I don't know.
I'm not trying to offend anybody who truly likes data crunching or doing academic stuff, but I highly doubt most normal jobs out there in the consultancy world really require the sort of knowledge you are saying. These sound more like university research than real world consultancy.
I look around my office of 70+ people and maybe 2-3 principals who are actuaries will be involve in this sort of stuff, but then they are very experienced subject matter experts and are probably paid like >20k. The rest of us are really just doing simple analytic. I am sure Neilsen isn't hiring him at 4k to do any of the things you are suggesting.
|
15-11-2015, 01:53 AM
|
Verified Member
|
|
Join Date: Sep 2015
Posts: 22
|
|
yeah, we had discussed all this stuff during interview. So, its not just a simple run a regression using data points you extract from the internet. There's so much more thought that goes into it. That's why I assumed it was a fairly intellectual stimulating role & was surprised at the remuneration offered.
More importantly, the modeling team I interviewed with all had Phd or Masters in statistics, economics etc.. So, its surprising that even a junior position would pay fairly below average for a quantitative analyst type of position
|
15-11-2015, 01:55 AM
|
Verified Member
|
|
Join Date: Sep 2015
Posts: 22
|
|
"I am sure Neilsen isn't hiring him at 4k to do any of the things you are suggesting."
In what i gathered from the interview, they are.
|
15-11-2015, 01:56 AM
|
|
Quote:
Originally Posted by Unregistered
Yea we do have some data QC procedures that we need to check for before processing. Normality yes, the other 2 I don't know.
I'm not trying to offend anybody who truly likes data crunching or doing academic stuff, but I highly doubt most normal jobs out there in the consultancy world really require the sort of knowledge you are saying. These sound more like university research than real world consultancy.
I look around my office of 70+ people and maybe 2-3 principals who are actuaries will be involve in this sort of stuff, but then they are very experienced subject matter experts and are probably paid like >20k. The rest of us are really just doing simple analytic. I am sure Neilsen isn't hiring him at 4k to do any of the things you are suggesting.
|
They are not academic stuff tbh. All those are taught in statistics 102 or 103, and any statistics grad (and some economics grad) can do the above.
I know normal jobs probably does not require any of these stuff cos there's simply no incentives for consultant firms to do the analysis properly for their clients. Afterall, it takes up alot of time and clients probably wont know enough to criticize ur methodology anyway. If im running a consultancy dept, that's probably what I would do too. but it jus kind of annoyed me that many ppl (esp those that are getting paid to give advice) take statistics for granted and think that it is a foolproof solution that can be applied broadly.
|
15-11-2015, 01:59 AM
|
|
i dun think a typical fmcg or auto firm is interested in this sort of thing....they just want simple reports that help them make sales & marketing decision. their main aim is to make money, not do modelling for modelling sake.
Quote:
Originally Posted by Unregistered
Knowing how to click on statistical software is different from knowing how to use regression analysis.
Did u do any diagnostic tests to check for normality, multicollinearity, and homoscedasticity?
if the model failed any of the test, how do u proceed?
How do u choose the the independent variables? by experience? based on empirical result? stepwise or some other forms of selection process? Is the model variation in discrete selection process a concern? If so, should I use penalty regression instead?
And that is just the model building stage. There are many more other issues to take note of at the inference stage.
|
|
15-11-2015, 02:06 AM
|
|
i think ur letting ur personal emotion get in the way of advising the ts properly. i can understand ur personal frustration, but what ur saying really isnt relevant to ts situation. he has a real job from neilsen in the real world and he wants to understand how it works career wise for him, not some hypo situation on what you will like to do in the ideal world.
we can all sit ard to complain abt what is wrong with this world, everyone has a fav pet topic. but this topic more for kopi/beer session...
Quote:
Originally Posted by Unregistered
They are not academic stuff tbh. All those are taught in statistics 102 or 103, and any statistics grad (and some economics grad) can do the above.
I know normal jobs probably does not require any of these stuff cos there's simply no incentives for consultant firms to do the analysis properly for their clients. Afterall, it takes up alot of time and clients probably wont know enough to criticize ur methodology anyway. If im running a consultancy dept, that's probably what I would do too. but it jus kind of annoyed me that many ppl (esp those that are getting paid to give advice) take statistics for granted and think that it is a foolproof solution that can be applied broadly.
|
|
15-11-2015, 01:40 PM
|
|
Quote:
Originally Posted by Unregistered
i think ur letting ur personal emotion get in the way of advising the ts properly. i can understand ur personal frustration, but what ur saying really isnt relevant to ts situation. he has a real job from neilsen in the real world and he wants to understand how it works career wise for him, not some hypo situation on what you will like to do in the ideal world.
we can all sit ard to complain abt what is wrong with this world, everyone has a fav pet topic. but this topic more for kopi/beer session...
|
u r right.. but my posts does shed some light to his query about the pay offered by nielson... if the job can be done by majority of the fresh grad from statistics, there's no reason for nielson to offer TS a much higher pay.
since ts described himself as no relevant experience in the field, the only advantage ts has is his corporate experience.
|
15-11-2015, 04:14 PM
|
|
Quote:
Originally Posted by Unregistered
u r right.. but my posts does shed some light to his query about the pay offered by nielson... if the job can be done by majority of the fresh grad from statistics, there's no reason for nielson to offer TS a much higher pay.
since ts described himself as no relevant experience in the field, the only advantage ts has is his corporate experience.
|
Yea I would be really surprised if Neilsen expects him to do the real PHD research and modelling stuff. 4k+ is really a normal office job pay for anyone with a deg & a few years of corporate exp. If they undercut him until like that, my advice is to just join the civil service or stat board. At least the job security and min bonus is there every year.
|
|
|
Posting Rules
|
You may not post new threads
You may post replies
You may not post attachments
You may not edit your posts
HTML code is Off
|
|
|
|
» 30 Recent Threads |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|