JVC RS40/50/60 OWNERS Lamp Poll - Page 4 - AVS Forum
View Poll Results: Have you had to replace your RS40/50/60 Lamp?
I own(ed) an RS40/50/60 and have had NO Lamp issues. 0 0%
I own(ed) an RS40/50/60 and have had 1 Lamp issues. 0 0%
I own(ed) an RS40/50/60 and have had 2 Lamp issues. 0 0%
I own(ed) an RS40/50/60 and have had 3 Lamp issues. 0 0%
Voters: 0. You may not vote on this poll

Forum Jump: 
Reply
 
Thread Tools
post #91 of 164 Old 11-03-2011, 09:40 PM
AVS Addicted Member
 
coderguy's Avatar
 
Join Date: Dec 2006
Posts: 10,074
Mentioned: 1 Post(s)
Tagged: 0 Thread(s)
Quoted: 60 Post(s)
Liked: 159
I already answered the question many times based on probabilities of a sample that has multiple recurrences of bulb failures. The multiple recurrences do not have to be used to track any specific failure rates based on a user sample from a simple equation, it can simply be a more targeted statistic for the entire sample set. However, there are multiple ways to examine this data. The reason it is more targeted is simply because the rarity of the event occurring in such a small sample. It's also easier to apply over-dispersion corrections once you have computed all the possible data from the sample that is relevant to the weighting and correction factors. So if you have one large sample where a pattern is already rare (like the industry standard data) vs. one small sample where the pattern is occurring too often (like the data we have for the JVC), that is why it is an important statistic. The sample does not care if the reason more users have multiple failures at a lower bulb life is related to a defect in the projector or not, it is simply answering the question of number of defects in this one situation regardless of the reason, you add the other data back into it later.


Quick and Easy Shelf Mount Method for both one projector or dual stacks

Web Calculator v023 & v025
- Quick Peak at the new upcoming calculator
**Current Projector Calculator** -- http://www.eliteprojectorcalculator.com

Coder's Top Projector Picks of 2012 --http://www.avsforum.com/avs-vb/showthread....

coderguy is online now  
Sponsored Links
Advertisement
 
post #92 of 164 Old 11-03-2011, 09:51 PM
Advanced Member
 
jim2100's Avatar
 
Join Date: Aug 2011
Posts: 762
Mentioned: 0 Post(s)
Tagged: 0 Thread(s)
Quoted: 0 Post(s)
Liked: 34
Quote:
Originally Posted by coderguy View Post

Now you are claiming I am breaking forum rules in responding to your attacks in a POLL thread, give me a break.

Feel free to ask a moderator if bets are allowed on AVS forums.
jim2100 is offline  
post #93 of 164 Old 11-03-2011, 10:36 PM
AVS Special Member
 
Clark Burk's Avatar
 
Join Date: Aug 1999
Location: Baltimore,MD.USA
Posts: 1,063
Mentioned: 0 Post(s)
Tagged: 0 Thread(s)
Quoted: 0 Post(s)
Liked: 12
I think the failure rate should really be figured using the total number of bulbs in the poll. If one owner has had three bulb failures this counts three times, and not as one vote. So by using the latest figures if there are 3 owners that have had three failures this counts as 9 bad bulbs. 6 owners have had 2 failures so that totals 12 bulbs, and 19 owners have had 1 failure for a total of 19. Adding up all the bad bulbs totals 40 versus the number of owners that have had no bad bulbs which is also 40. That breaks down to a one in two chance that the bulb you have will suffer an early demise.

Clark
Clark Burk is online now  
post #94 of 164 Old 11-04-2011, 12:01 AM
AVS Special Member
 
bosng's Avatar
 
Join Date: Oct 2001
Posts: 2,238
Mentioned: 0 Post(s)
Tagged: 0 Thread(s)
Quoted: 0 Post(s)
Liked: 15
still under 200 hrs. no issues. light 3d use. normal lamp
bosng is offline  
post #95 of 164 Old 11-04-2011, 06:29 AM - Thread Starter
AVS Special Member
 
Geof's Avatar
 
Join Date: Feb 1999
Location: Eden NY
Posts: 6,020
Mentioned: 0 Post(s)
Tagged: 0 Thread(s)
Quoted: 13 Post(s)
Liked: 34
Quote:
Originally Posted by Clark Burk View Post

I think the failure rate should really be figured using the total number of bulbs in the poll. If one owner has had three bulb failures this counts three times, and not as one vote. So by using the latest figures if there are 3 owners that have had three failures this counts as 9 bad bulbs. 6 owners have had 2 failures so that totals 12 bulbs, and 19 owners have had 1 failure for a total of 19. Adding up all the bad bulbs totals 40 versus the number of owners that have had no bad bulbs which is also 40. That breaks down to a one in two chance that the bulb you have will suffer an early demise.

Unless, of course, there is something wrong with those particular projectors which is causing early lamp failures. There are just not enough facts in evidence to make any solid conclusions.......

Geof
Geof is offline  
post #96 of 164 Old 11-04-2011, 06:44 AM
AVS Addicted Member
 
coderguy's Avatar
 
Join Date: Dec 2006
Posts: 10,074
Mentioned: 1 Post(s)
Tagged: 0 Thread(s)
Quoted: 60 Post(s)
Liked: 159
It doesn't actually affect the numbers if something is wrong with a projector that is causing the failures, because the same number of people in the sample would not know if their projector was one with the defect or not, so the number still applies overall to the sample number. So everyone in the sample has the exact same odds of having a defective bulb due to any reason as the next guy does. Hence, the end outcome of what is trying to be determined here is still the same.

A lot of these factors people consider to invalidate results are not the reason the results are invalid, in statistics a single bad variable does not invalidate the entire set by any stretch unless it is a non-resolvable error on the original basis.

This is just being too oversimplified, statistics is so complicated and I'm certainly not the all-end expert either, but have had to program some peoples formulas in and picked up things here and there. I agree the simpler the better, but in cases where the data is inaccurate, you have a much more complex model to create. BTW, there are actually polling bias studies you can get to add in to adjust your error factors that have been used with online polling and even forums to factor into such polls in a generic fashion.


Quick and Easy Shelf Mount Method for both one projector or dual stacks

Web Calculator v023 & v025
- Quick Peak at the new upcoming calculator
**Current Projector Calculator** -- http://www.eliteprojectorcalculator.com

Coder's Top Projector Picks of 2012 --http://www.avsforum.com/avs-vb/showthread....

coderguy is online now  
post #97 of 164 Old 11-04-2011, 07:14 AM - Thread Starter
AVS Special Member
 
Geof's Avatar
 
Join Date: Feb 1999
Location: Eden NY
Posts: 6,020
Mentioned: 0 Post(s)
Tagged: 0 Thread(s)
Quoted: 13 Post(s)
Liked: 34
Quote:
Originally Posted by coderguy View Post

It doesn't actually affect the numbers if something is wrong with a projector that is causing the failures, because the same number of people in the sample would not know if their projector was one with the defect or not, so the number still applies overall to the sample number. So everyone in the sample has the exact same odds of having a defective bulb due to any reason as the next guy does. Hence, the end outcome of what is trying to be determined here is still the same.

I disagree. What we are attempting to discover is the percentage of bad lamps. If the numbers are skewed because some hardware defect is creating bad lamps then that's another issue.

There are 9 instances with 2 or more lamp failures. IF the lamps were all bad, and there is no hardware issue with these failures, then that adds up to 21 bad lamps. OTOH, what if all of them were due to a projector hardware problem that (for example) overdrives the lamps and burns them out before they die of old age. Then we have 0 bad lamps. These are the two extremes but reality may lie somewhere in between. More data is required to draw solid conclusions.

Geof
Geof is offline  
post #98 of 164 Old 11-04-2011, 07:20 AM
AVS Addicted Member
 
coderguy's Avatar
 
Join Date: Dec 2006
Posts: 10,074
Mentioned: 1 Post(s)
Tagged: 0 Thread(s)
Quoted: 60 Post(s)
Liked: 159
Yes, if you are trying to separate the reasons for failure, but what is the purpose in doing so, it has no relevance in how it affects the general population. The general population still has the same chance of having a defective projector as the next guy, so overall the chances of having a defective bulb doesn't change enough to matter. Even if you are referring to how it applies to the multiple failure statistic that could cause the multiple failures from one person to cause a distribution error back into the overall sample on the basis that only a small segment of the population would have a defective projector, well the problem with focusing on this is that the distribution error isn't significant enough (at least in this poll) to cause any significant error margin to the overall number.

In my earlier example, I am only using the multiple failure number as a weighting factor before it is adjusted back based on the overall larger sample (when re-including single failures), so it was never an overall determining basis. We have to think in terms of multiple variables and corrective methods because the data is too error prone and is such a small sample.

You did however outline another reason why it is better to keep multiple lamp failures from the same individual under a separate answer as opposed to single failures from another (hence the reason to keep these separate, but they are already separated in this poll).


Quick and Easy Shelf Mount Method for both one projector or dual stacks

Web Calculator v023 & v025
- Quick Peak at the new upcoming calculator
**Current Projector Calculator** -- http://www.eliteprojectorcalculator.com

Coder's Top Projector Picks of 2012 --http://www.avsforum.com/avs-vb/showthread....

coderguy is online now  
post #99 of 164 Old 11-04-2011, 07:30 AM - Thread Starter
AVS Special Member
 
Geof's Avatar
 
Join Date: Feb 1999
Location: Eden NY
Posts: 6,020
Mentioned: 0 Post(s)
Tagged: 0 Thread(s)
Quoted: 13 Post(s)
Liked: 34
Quote:
Originally Posted by coderguy View Post

Yes, if you are trying to separate the reasons for failure, but what is the purpose in doing so, it has no relevance in how it affects the general population. The general population still has the same chance of having a defective projector as the next guy, so overall the chances of having a defective bulb doesn't change enough to matter.

But I don't care about the general population...(sorry guys ). The answer I seek is what percentage of lamps are bad....ie, what chance do I have in getting a bad lamp. IOW, what is the LAMP failure rate. You cannot count lamps blown out by defective hardware as a bad lamp.

Geof
Geof is offline  
post #100 of 164 Old 11-04-2011, 07:34 AM
AVS Addicted Member
 
coderguy's Avatar
 
Join Date: Dec 2006
Posts: 10,074
Mentioned: 1 Post(s)
Tagged: 0 Thread(s)
Quoted: 60 Post(s)
Liked: 159
I see your point sort of, except for one thing...

What's to say your projector isn't defective (sorry don't mean to go there), but just saying. You are the general population statistically, we all are. None of us know which projectors could have a defect or develop a defect in the future, so anyone could own one.

The only thing this really changes is the original distribution sample for people that had multiple lamp failures in a row that were all caused by a defective projector, but it's a real slight change since not that many have reported the multiple failures yet in this poll based on the total number, so the changes at least in this poll are too minor to worry about it.

So from my viewpoint, you have to count lamps blown out by hardware as a defective lamp because there is no other determining factor, since people have no way of knowing if their projector is defective or not. There is no rule that says you cannot include all blown lamps regardless of the reason, pretty much you have to include them all at this point because there is no other data to add an exclusion filter.


Quick and Easy Shelf Mount Method for both one projector or dual stacks

Web Calculator v023 & v025
- Quick Peak at the new upcoming calculator
**Current Projector Calculator** -- http://www.eliteprojectorcalculator.com

Coder's Top Projector Picks of 2012 --http://www.avsforum.com/avs-vb/showthread....

coderguy is online now  
post #101 of 164 Old 11-04-2011, 07:41 AM - Thread Starter
AVS Special Member
 
Geof's Avatar
 
Join Date: Feb 1999
Location: Eden NY
Posts: 6,020
Mentioned: 0 Post(s)
Tagged: 0 Thread(s)
Quoted: 13 Post(s)
Liked: 34
You're right...the data is not obtainable and that includes the true lamp failure rate. Now we can presume all lamps in the 2 or more failure category are bad but it's just that...a presumption. We could also presume they count just once. So, depending on how you want to spin it you can come up with several answers. In reality there is only 1 truth but there is not enough data to conclude what that is.

Geof
Geof is offline  
post #102 of 164 Old 11-04-2011, 07:47 AM
AVS Addicted Member
 
coderguy's Avatar
 
Join Date: Dec 2006
Posts: 10,074
Mentioned: 1 Post(s)
Tagged: 0 Thread(s)
Quoted: 60 Post(s)
Liked: 159
There are ways to handle some of these things in statistics if the polling data is more complete (not blaming you at all). However, even if the polling data were complete and more questions asked, then all you could really get were a more precise distribution calculation or probability of deviation from some assumed industry standard or other projector, but it wouldn't answer some of the more fundamental questions.

One thing though, in statistics you don't always have to be right, you can also just be almost right. Sometimes people are just completely wrong in statistics, so that is always an option as well.

Depending on the error margins someone is willing to live with, there are a few things you could derive based on some assumptions as well. That's why you have error margins, corrective weighting, sub-sampling, and all kinds of derived methods you can apply, but yah it's a real pain in the rear anyways. OK, well I think I'm about done with statistics for now, I think this thread about wore me out.


Quick and Easy Shelf Mount Method for both one projector or dual stacks

Web Calculator v023 & v025
- Quick Peak at the new upcoming calculator
**Current Projector Calculator** -- http://www.eliteprojectorcalculator.com

Coder's Top Projector Picks of 2012 --http://www.avsforum.com/avs-vb/showthread....

coderguy is online now  
post #103 of 164 Old 11-04-2011, 12:01 PM
Advanced Member
 
jim2100's Avatar
 
Join Date: Aug 2011
Posts: 762
Mentioned: 0 Post(s)
Tagged: 0 Thread(s)
Quoted: 0 Post(s)
Liked: 34
Quote:
Originally Posted by Geof View Post

You're right...the data is not obtainable and that includes the true lamp failure rate. Now we can presume all lamps in the 2 or more failure category are bad but it's just that...a presumption. We could also presume they count just once. So, depending on how you want to spin it you can come up with several answers. In reality there is only 1 truth but there is not enough data to conclude what that is.

Well, there is actually more than one truth, because there is more than one possible question. If you change your question a bit, you can make it less difficult to obtain a reasonable answer.

The most useful question about this problem -- where useful includes the concept that it is possible to obtain an approximate answer given available resources -- is something like:

What is the probability that a randomly selected projector will have a lamp failure on its first (factory) lamp before the lamp reaches 500 hours?

This question has the disadvantage that it could include lamp failures due to faulty projectors (with good lamps) as well as failures due to bad lamps. But it has the advantage that given a reasonably selected sample of projectors, you have a chance at getting a good estimate of the true answer by asking owners whether they had their first lamp fail within 500 hours. And I think it is a question to which many prospective owners might like to know the answer.

If you want to glean more information from the sample, you could go back to the people who had their first lamp fail within 500 hours, and ask them the same question about their second lamp (same projector). If you find that the probability estimate is higher than the original one (first lamp failure) by a statistically significant amount, then you can conclude that some projectors do significantly increase the chance of having a lamp failure. Unfortunately, you may have trouble getting a large enough sample size for this second question. Well, unless there are A LOT of failures in your original sample. Which I suppose could be the case for the 2010 JVC projectors. Or, you might find that almost all of the first lamp failures also have second lamp failures, which would obviously be a strong indicator that most lamp failures are due to faulty projectors rather than faulty lamps. Which suggests a possible poll question: Only answer if you had a factory lamp failure with less than 500 hours and replaced the lamp in the same projector. The second lamp: (a) failed with less than 500 hours (b) is still working fine after more than 500 hours (c) is working fine but with less than 500 hours so far
jim2100 is offline  
post #104 of 164 Old 11-04-2011, 12:14 PM - Thread Starter
AVS Special Member
 
Geof's Avatar
 
Join Date: Feb 1999
Location: Eden NY
Posts: 6,020
Mentioned: 0 Post(s)
Tagged: 0 Thread(s)
Quoted: 13 Post(s)
Liked: 34
There is only one question I think needs answering and that is...what is the failure rate of the lamp (and that has but 1 truth). We can find out all sorts of things by asking more questions but given the limitations of this poll I'm not inclined to make this a science project. Given that we have 21 double/triple replacement bulbs and have no clue if any of those projectors are responsible I maintain that anything we do, or could ask, won't get us there because we have no way of verifying (at this time) if the projectors themselves are the culprit.

Again, this is a simple poll. More data is required to refine the results. You're welcome to it.....

Geof
Geof is offline  
post #105 of 164 Old 11-04-2011, 12:21 PM
Advanced Member
 
jim2100's Avatar
 
Join Date: Aug 2011
Posts: 762
Mentioned: 0 Post(s)
Tagged: 0 Thread(s)
Quoted: 0 Post(s)
Liked: 34
Quote:
Originally Posted by Geof View Post

Again, this is a simple poll. More data is required to refine the results. You're welcome to it.....

As I've mentioned previously, I don't care for these polls (in most cases) due to the high selection bias. But I am planning a project for new RS45 owners to look at factory lamp failures. It won't answer your one and only question, though (BTW, if you only care about the answer to one question, shouldn't it be a more profound question? )
jim2100 is offline  
post #106 of 164 Old 11-04-2011, 01:48 PM - Thread Starter
AVS Special Member
 
Geof's Avatar
 
Join Date: Feb 1999
Location: Eden NY
Posts: 6,020
Mentioned: 0 Post(s)
Tagged: 0 Thread(s)
Quoted: 13 Post(s)
Liked: 34
Quote:
Originally Posted by jim2100 View Post

(BTW, if you only care about the answer to one question, shouldn't it be a more profound question? )

Well, okay...
Why is the answer to Life, the Universe, and everything = 42?

From Hitchhikers Guide to the Galaxy

Geof
Geof is offline  
post #107 of 164 Old 11-04-2011, 03:47 PM
Senior Member
 
console's Avatar
 
Join Date: Dec 2003
Posts: 240
Mentioned: 0 Post(s)
Tagged: 0 Thread(s)
Quoted: 1 Post(s)
Liked: 10
I posted NO lamp issues with my X3 but it should be noted that recent professional ISF calibration at 225 hours yielded only 370 Lumens (14fL). Don't watch 3D. So far only use Normal lamp. Image seems bright enough but with iris wide open. Want to purchase spar bulb+housing for eventual (hopefully eventual) dimming but on hold waiting for best shot at hoped for bulb improvements.
console is offline  
post #108 of 164 Old 11-05-2011, 04:20 AM
AVS Addicted Member
 
coderguy's Avatar
 
Join Date: Dec 2006
Posts: 10,074
Mentioned: 1 Post(s)
Tagged: 0 Thread(s)
Quoted: 60 Post(s)
Liked: 159
Last thoughts...

Any method that any of us have to collect this data can only be analyzed by a fairly complex statistical model. From what I have seen so far is that there isn't anyone in here with the experience to design the model properly, because every post immediately became about one variable, and in this type of analysis, the one variable method is not useful.

I'm not sure if I will ever add it into my program because it looks like about 20-30 hours of modeling work just for some simple things to be found. It could be as much work as 500 hours of modeling unfortunately, that is too much.

Also, another point that has been missed is testing the data, which is everything in statistics. Without doing the proper testing, much of the stuff assumed in here isn't even valid, just assumptions.


Quick and Easy Shelf Mount Method for both one projector or dual stacks

Web Calculator v023 & v025
- Quick Peak at the new upcoming calculator
**Current Projector Calculator** -- http://www.eliteprojectorcalculator.com

Coder's Top Projector Picks of 2012 --http://www.avsforum.com/avs-vb/showthread....

coderguy is online now  
post #109 of 164 Old 11-05-2011, 10:36 AM
AVS Special Member
 
zombie10k's Avatar
 
Join Date: Dec 2007
Posts: 7,780
Mentioned: 1 Post(s)
Tagged: 1 Thread(s)
Quoted: 390 Post(s)
Liked: 411
Coder - JVC could save you a lot of time trying to figure this out if they just fix the problem so we don't have to have polls like this on projectors that cost 8K MSRP with a $400+ lamp.
zombie10k is online now  
post #110 of 164 Old 11-05-2011, 10:39 AM
AVS Addicted Member
 
coderguy's Avatar
 
Join Date: Dec 2006
Posts: 10,074
Mentioned: 1 Post(s)
Tagged: 0 Thread(s)
Quoted: 60 Post(s)
Liked: 159
True.

Could also have saved me a lot of aggravation from a particular poster that kept trying to scrutinize everything I said because I don't have time in a forum to elaborate every detail of a formula.

I was expecting that people would give me the benefit of the doubt in knowing if I attempted something, I would be thorough, given my OCD nature that people know me by in here


Quick and Easy Shelf Mount Method for both one projector or dual stacks

Web Calculator v023 & v025
- Quick Peak at the new upcoming calculator
**Current Projector Calculator** -- http://www.eliteprojectorcalculator.com

Coder's Top Projector Picks of 2012 --http://www.avsforum.com/avs-vb/showthread....

coderguy is online now  
post #111 of 164 Old 11-05-2011, 10:57 AM
Advanced Member
 
jim2100's Avatar
 
Join Date: Aug 2011
Posts: 762
Mentioned: 0 Post(s)
Tagged: 0 Thread(s)
Quoted: 0 Post(s)
Liked: 34
Quote:
Originally Posted by coderguy View Post

Could also have saved me a lot of aggravation from a particular poster that kept trying to scrutinize everything I said because I don't have time in a forum to elaborate every detail of a formula.

Or you could save yourself aggravation by not posting nonsense about things that you do not understand.

I had to laugh about your "last thoughts". Yeah, right, how many times have you said that? I'm sure more nonsense is coming.

Let's hear some more about your great ability to pull useful information out of biased data, but of course you will not ACTUALLY compute any useful information, because you do not have time. Yeah, that's the reason, you don't have time. It must be all that time you spend writing long nonsense posts.
jim2100 is offline  
post #112 of 164 Old 11-05-2011, 11:04 AM
AVS Addicted Member
 
coderguy's Avatar
 
Join Date: Dec 2006
Posts: 10,074
Mentioned: 1 Post(s)
Tagged: 0 Thread(s)
Quoted: 60 Post(s)
Liked: 159
Send it to the complaint department.


Quick and Easy Shelf Mount Method for both one projector or dual stacks

Web Calculator v023 & v025
- Quick Peak at the new upcoming calculator
**Current Projector Calculator** -- http://www.eliteprojectorcalculator.com

Coder's Top Projector Picks of 2012 --http://www.avsforum.com/avs-vb/showthread....

coderguy is online now  
post #113 of 164 Old 11-05-2011, 11:14 AM
Advanced Member
 
jim2100's Avatar
 
Join Date: Aug 2011
Posts: 762
Mentioned: 0 Post(s)
Tagged: 0 Thread(s)
Quoted: 0 Post(s)
Liked: 34
Quote:
Originally Posted by coderguy View Post

I also find it funny that his last idea was taken from what I had posted last night about interviewing people that had lamp failures in a smaller subset of data, but I deleted the posts last night because I knew it was too detailed of a model and no-one would bother taking anything overly complex in here seriously since most of us do not do this stuff for a living (although for me it is part of what I do but not exactly the same).

What happened to "last thoughts"? Couldn't resist posting more nonsense, huh? Now you are whining about me stealing your idea? What idea would that be, exactly? I saw no such post from you. Surely you saved it and can post it again.
jim2100 is offline  
post #114 of 164 Old 11-05-2011, 11:16 AM
AVS Addicted Member
 
coderguy's Avatar
 
Join Date: Dec 2006
Posts: 10,074
Mentioned: 1 Post(s)
Tagged: 0 Thread(s)
Quoted: 60 Post(s)
Liked: 159
I never used the word steal, that is a word you selectively picked, you like to put words and ideas into people's posts.


Quick and Easy Shelf Mount Method for both one projector or dual stacks

Web Calculator v023 & v025
- Quick Peak at the new upcoming calculator
**Current Projector Calculator** -- http://www.eliteprojectorcalculator.com

Coder's Top Projector Picks of 2012 --http://www.avsforum.com/avs-vb/showthread....

coderguy is online now  
post #115 of 164 Old 11-05-2011, 11:24 AM
Advanced Member
 
jim2100's Avatar
 
Join Date: Aug 2011
Posts: 762
Mentioned: 0 Post(s)
Tagged: 0 Thread(s)
Quoted: 0 Post(s)
Liked: 34
Quote:
Originally Posted by coderguy View Post

I deleted before you could get to it so I didn't have to listen to why everything I say is a bad idea, that simple...

Good move. Deleting posts with bad ideas cuts down on your aggravation and wasted time. I suggest you go back and delete all your other posts with bad ideas, too!
jim2100 is offline  
post #116 of 164 Old 11-05-2011, 11:30 AM
AVS Addicted Member
 
coderguy's Avatar
 
Join Date: Dec 2006
Posts: 10,074
Mentioned: 1 Post(s)
Tagged: 0 Thread(s)
Quoted: 60 Post(s)
Liked: 159
It was almost as bad as your idea of random sampling the entire population


Quick and Easy Shelf Mount Method for both one projector or dual stacks

Web Calculator v023 & v025
- Quick Peak at the new upcoming calculator
**Current Projector Calculator** -- http://www.eliteprojectorcalculator.com

Coder's Top Projector Picks of 2012 --http://www.avsforum.com/avs-vb/showthread....

coderguy is online now  
post #117 of 164 Old 11-05-2011, 11:42 AM
Advanced Member
 
jim2100's Avatar
 
Join Date: Aug 2011
Posts: 762
Mentioned: 0 Post(s)
Tagged: 0 Thread(s)
Quoted: 0 Post(s)
Liked: 34
Quote:
Originally Posted by coderguy View Post

It was almost as bad as your idea of random sampling the entire population

Taking a random sample from a population means to select (randomly!) one or more subjects, out of all possible subjects, for study and analysis. That is one of the fundamental ideas from statistics. So it is obvious that neither "bad" nor "your" (quoted above) applies.

Did you think "random sampling the entire population" meant getting data from every possible subject?
jim2100 is offline  
post #118 of 164 Old 11-05-2011, 11:44 AM
AVS Addicted Member
 
coderguy's Avatar
 
Join Date: Dec 2006
Posts: 10,074
Mentioned: 1 Post(s)
Tagged: 0 Thread(s)
Quoted: 60 Post(s)
Liked: 159
Yah, and how you going to do that, from a forum?
Or you going to pay telemarketers?

What is the point of posting ideas that cannot be executed without a great amount of money or time expended.
You would never get enough data to cover the entire population of the world's JVC users of this projector, it's a ridiculous assertion sub-sampling randomly on such a small sample to determine upon such a large population variable.

From the WIKI:
Conceptually, simple random sampling is the simplest of the probability sampling techniques. It requires a complete sampling frame, which may not be available or feasible to construct for large populations. Even if a complete frame is available, more efficient approaches may be possible if other useful information is available about the units in the population.


Quick and Easy Shelf Mount Method for both one projector or dual stacks

Web Calculator v023 & v025
- Quick Peak at the new upcoming calculator
**Current Projector Calculator** -- http://www.eliteprojectorcalculator.com

Coder's Top Projector Picks of 2012 --http://www.avsforum.com/avs-vb/showthread....

coderguy is online now  
post #119 of 164 Old 11-05-2011, 11:53 AM
Advanced Member
 
jim2100's Avatar
 
Join Date: Aug 2011
Posts: 762
Mentioned: 0 Post(s)
Tagged: 0 Thread(s)
Quoted: 0 Post(s)
Liked: 34
Are you referring to the RS45 lamp project that I am planning? If so, random samples are obviously not feasible. But as I already explained, the idea is to get a list of volunteers who have the projector on order but have not received it yet. That should reduce selection bias of the type that people who have had failures are more likely to respond to a poll such as this one (as compared to people whose lamps have not failed).
jim2100 is offline  
post #120 of 164 Old 11-05-2011, 11:57 AM
AVS Addicted Member
 
coderguy's Avatar
 
Join Date: Dec 2006
Posts: 10,074
Mentioned: 1 Post(s)
Tagged: 0 Thread(s)
Quoted: 60 Post(s)
Liked: 159
That method is also far too tedious, good luck with that in tracking all the variables of each individual that need to be tracked over time, the execution would have to be near perfect because the sample size is too small for the amount of work required per each individual. It would also take almost 5 years to complete based on the average use of how much a person uses their projector, and how many people will drop out during the time given because they lost interest.

You need multiple types of mixed samples and cross-analysis of multiple variables with industry standard data to get anywhere in this, that is step # 1.


Quick and Easy Shelf Mount Method for both one projector or dual stacks

Web Calculator v023 & v025
- Quick Peak at the new upcoming calculator
**Current Projector Calculator** -- http://www.eliteprojectorcalculator.com

Coder's Top Projector Picks of 2012 --http://www.avsforum.com/avs-vb/showthread....

coderguy is online now  
Reply Digital Hi-End Projectors - $3,000+ USD MSRP

Tags
Jvc Rs50u

Thread Tools
Show Printable Version Show Printable Version
Email this Page Email this Page


Forum Jump: 

Posting Rules  
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts

BB code is On
Smilies are On
[IMG] code is On
HTML code is Off
Trackbacks are Off
Pingbacks are Off
Refbacks are Off