Toilet Lid Noise and Corticosteroids?

This. I have been guilty of crafting bad surveys many times. But the more you know, the more you realize how, say a politically party for example, can really skew the questions to mitigate or exaggerate public opinion. And it's really happening on a subconscious level.

 

If you read my examples, you will see that in many/most cases we are not talking about self-fulfilling prophecy (e.g., people are shocked by the noise, their stress goes up as they are worried about getting a spike, and T spikes). People are exposed to noise that they think is safe, and THEN they are surprised when their T spikes right after the noise.

 

If you read my post(s) you would know that your examples are (1) biased and thus flawed and do not count (2) we may not be aware of the stress involved and (3) are completely ignorant of any mitigating circumstances.

 

I believe I already told you that those examples might not count if the goal is to estimate the risk, but they certainly count if the goal is to show that the risk exists.

Good point, but the best judges of that are the people who have had the experience, and their judgement is that the noise was to blame.

 

No. What worked for the other 95%? If you polled the other 95% of people with T they may say noise helped. You don't know. At any level. And making statement otherwise is dangerous. At MOST you can say: "in my case blah". You can not say, "in my experience browsing this forum...." Any and all conclusions are irrelevant, baseless, without validation, and possible even detrimental. And that is the scary part.

Says who? We may be the worst people to ask.

 

Nope, the best judges aren't the people who have had the experience (based on the second part of your sentence behind the comma, you are using "judging" to mean "explaining").
The people who have had the experience are invaluable to provide data about the experience, but they are rarely the best people to explain it.

 

No, it's not. It seems to be about a hypothesis test that you have in mind but haven't been clear about. As far as I can tell, you have in mind a null hypothesis that P >= 0.5 where P is the population proportion of people who believe their ENT was more effective than the forum. Thus the alternative is P < 0.5. Beyond that, your thinking is convoluted. What you appear to be talking about is related to the probability of a Type 1 error [Pr(reject null|null is true)]. Now, your example [Pr(P_hat<.1|P>.5) where P_hat is the sample proportion] is more specific, but not in a way that is really useful. So what you really need is a p-value, not a confidence interval. This is very basic.

The other issues are not minor, they are fundamental conceptual issues that matter once one gets to survey design and survey sampling. They are, however, beyond what one would learn in a basic statistics class.

No, the true population of interest is people visit the forum, not members. After all, individuals may be helped (or harmed) by what they read here without becoming members and they have in many/most cases seen an ENT. Thus they are also in a position to evaluate whether the information they found on the site was more or less useful than the ENT they saw. So, you still have the wrong population.

However, let's take the population as registered members. This poll (and the same is almost certainly true for any poll on this web site) will not provide unbiased information about even that population.

To see this, let's think about when a sample of members would provide unbiased information about a population parameter for the population of members: 1) if it were a random sample, or 2) if it were non-random but non-non-random in some intentional way - e.g., a stratified sample - or in a way that is completely unrelated to the outcome of interest.

Neither of these is satisfied in this case. You certainly did not randomly sample the population or draw a stratified sample. You are therefore relying on people to choose to respond, i.e., you have a choice based sample. Given that one of the most socially reinforced (and least controversial) statements one can make on this forum is that "my ENT knows nothing", the sample of people who answer the poll is almost certainly biased and is thus related to the outcome of interest.

It's actually worse than that because on any given day the people participating in the forum (and thus likely respondents) are a selected sample of people who have ever registered. I think the best analogy is to a hospital. If you walk around the various wards of a hospital and take a sample of patients (a stock sample) you will find patients who are on average worse off (less healthy and in the midst of longer stays in the hospital) than what you would find if you sampled patients upon admission (a flow sample). The latter patients would on average be healthier and would have shorter completed stays in the hospital. The reason is that most patients, even those who are admitted, will have short stays and will be relatively healthy. In contrast, when you sample people in the hospital without regard to admission date, you will find a much less healthy population because the unhealthy people 'accumulate' in the hospital.

With some exceptions of people who are "better" who stick around to help others, the sample of people on line at any given time, and thus the people"eligible" for your poll, is like the stock sample in the hospital analogy and is negatively selected relative to the population of members or visitors. (It's actually a bit more interesting because the analogy breaks down in one way - new members here are on average in great distress and would likely appear "worse" than they will ultimately turn out to be, but this only exacerbates the problem because the 'eligible' sample is then composed of people in crisis and a selected sample of longer term members.)

Thus, the sample of registered daily visitors is a non-random sample of all members and even more so of visitors, and the sample of people who feel drawn to answer a particular poll on ENTs is biased.

Consequently, the results of your poll, or any poll on this site, do not provide unbiased estimates of population parameters even when the population is members of this site.

I've thankfully never had to develop my own survey, but I work with survey data regularly and think a lot about how the data are generated - both in terms of how the surveys are developed and administered and how questions are answered.

 

I’ve given up trying to explain the issues with the polls and surveys we often see on here touted as proof of something. Not just the surveys either, but the assumptions of causation about anything. A couple of times I have used this analogy which I picked up from a professor:

You could link the yellowing of a persons teeth directly as a cause of lung cancer, and obviously you’d be wrong. The data analysis would show that each time a person is observed to have yellow teeth that there is a striking ratio at which those people go on to develop lung cancer. Of course, this is nonsense, as we are missing the vital link which is smoking. Once we find this missing link we can clearly see that smoking is the determining factor that causes both.

This is all overly simplified as there is usually a complex myriad of things happening in any given observation.

 

I don't see how merits on this topic can be evaluated without a discussion of the cost effect factor ratios that would include clinics, hospital management and insurance companies where they all use complex metric analysis. And this is just touching the surface with care treatment cost benefit ratios that would include many advance terms with hundreds of pages of direct and indirect discussion. Some research can be done on this by searching the administration of healthcare where cost and treatment are analyzed. Healthcare considers tinnitus as secondary to disease or state of condition.

If one has a physical ear problem including an ear infection, throat infection, ear wax, ETD then seeing an ENT is needed. With tinnitus at least one visit should be made.

 

Surveys and polls are pretty useless from a scientific point of view, so not sure why you’re debating it. They’re about getting the vox pop and no matter how carefully crafted, are open to subjective interpretation by the respondent. The number of respondents is tiny on TT anyway which makes the results pretty irrelevant. They’re anecdotal.

 

That's the thing - nobody says that. And between February 2017 and the present I don't remember ever reading anyone saying that. If that were "a thing", someone would have mentioned it (and believe me, I would have noticed), but they only mention the other side of it. The other side also makes sense - as in "noise is what gave us T, so noise can make T even worse." I can't imagine a plausible explanation for your theory (for which there is also zero observations/empirical evidence).

The sufferers themselves. You said that we don't know their other health conditions/circumstances, etc. Well - they have the most information about it, and they tell us that it is the noise.

Our sample proportion is 10%. To point out how unlikely this is to happen if the population proportion were to be over 50%, I was saying that if we were to use the confidence interval approach to hypothesis testing of the hypothesis that the population proportion equals 0.5, the hypothesis would be rejected. In other words, those minor problems that you had pointed out would make the confidence interval wider, but 0.1 would still be safely deep inside of the rejection region (the p-value associated with 0.1 is below the level of significance).

I never intended to publish that post in a peer-reviewed statistics journal. The problems might not be minor but, without a doubt, they are not big enough to produce a sample proportion of 0.1, when the population proportion is 0.5 (or higher). This is a topic that people feel strongly about. They are not going to vote for something opposite of their beliefs just because the there were more options for the opposite of their beliefs, or because some options had some words capitalized.

I don't have the wrong population. My population is the right one - people posting on this forum. If someone uses the wrong population, that has nothing to do with me.

Thank you for your hospital analogy. I will want to remember it.

Of course you are right. But I am still not completely convinced that if in reality the majority are happy with their ENTs, all of the biases could get us to only 10% saying that they are happy (and a similar number of people reporting that their ENT's advice made them worse).

We had already discussed the possibility that a third factor causes both the noise and a T spike. Stress was suggested as that third factor. I responded that in most posts that I quote the person thinks that the noise is safe, is NOT stressed out by the noise, and then is surprised by the T spiking.

A sample with over 40 observations is not THAT small...

 

@kelpiemsp, just wanted to say it’s good to see more rationality on here.

 

Not an argument.

 

But you’re using testimonials from TT; the select few who sign up because they are anxious about their condition and are generally stressed out. If they’re not feeling any stress and anxiety then why are they here? Why sign up for support?

We can become accustomed to cortisol over time to the point that it becomes our new norm. It doesn’t necessarily mean that we aren’t stressed out because we don’t feel anything. It’s not the acute feeling (butterflies in stomach, panic attack, sweating etc), but it can still be present within a person and still be an issue. It’s just simmering beneath the surface until a stressor triggers a full blown attack. In our case, the stressor is any loud sound, and if a persons mind is conditioned to react (by reading loads of threads on here) then it will. Our limbic system will jump into action once the amygdala triggers the alarm. Cue some adrenaline and more cortisol and at this point it becomes a trained response; almost a reflex.

Obviously this is only one side of the coin. There are sounds out there that can legitimately damage our ears, but they are much harder to come by and aren’t really worth worrying about if they’re out of our control. We simply cannot revert to wearing hearing protection, 24/7, because of the tiniest chance that something ‘damagingly’ loud might occur. If one does take this path then we can refer back to my first paragraph and then you have yourself a vicious circle. You will be in a place, mentally, where you’ll always be on high alert, just waiting for all the dangers. I’m talking from experience here as well because when I went through this stage I was miserable. I even caused myself further damage by going into an MRI that was off the charts (I’d say an anomaly in terms of loudness), but I’m still in a better place mentally than I was when I feared everything.

I know we’re all different, but I can’t see how it can ever be good to live in fear.

 

In this case I wasn’t joining in the discussion. Just giving credit where I thought it was due.

@Bill Bauer, you seem like a good person overall, and I know we have our disagreements, but it’s nothing personal at all.

 

Is this
https://www.tinnitustalk.com/thread...-what-happens-in-our-brain.27158/#post-329423
what kids call "rationality", these days?

They ARE stressed out. If this stress were to cause spikes, then those spikes would not always be happening Just after one is exposed to noise (that one thought was actually safe to be exposed to). If the timing of the spikes had no relation to the times one had been exposed to noise, the sufferers would not make posts here linking the two.

You are right - it is an impossible choice. Either be on high alert and possibly get T from all of the stress, or don't be on high alert, and risk getting a new acoustic trauma and a T spike... Heads - you lose; tails - you lose. Life with T sucks...

 

But it’s much more complex than that. The noise triggers a response which is like flicking a switch that sends our thoughts into overdrive. It is far from normal. The reaction often is the spike; our thoughts become more inward and a certain ‘monitoring’ and ‘checking’ behaviour takes over. It’s all about perception.

I know from my hellish experiences that when I lived in fear I spiked all the time. I’d hear a loud bang and I’d feel the world falling in on me and this inevitably made my T feel a lot louder. You are triggering a fight or flight response which raises your awareness and heightens your senses. This includes the auditory system. There will be cases that cause real ‘spikes’, but I’d say most the threads started on here are predominantly fear related. A learned response.

 

Thanks! I appreciate yours as well

 

So many people trying to help @Bill Bauer understand, it's great. I truly hope you get better.

 

Hopefully I'm not reiterating something already said here, but...

I always try to caveat what I say with "in my experience" or similar. We can't generalise based on the quirks and journey of an individual. There is too much personal opinion presented as fact, but this is a problem of the internet as a whole rather than a specific TT issue.

The snapshot of opinions on TT is in no way broadly representative of tinnitus. Whenever I present anything about TT I always state that what we have here on the website is representative of the "suffering" group, and not the population as a whole. And then you are whittling further, by representing the members of that group who are willing to become involved in a forum and willing to share their story.

Taking the above, a poll on an isolated thread available for voting on by an isolated group has nigh on zero meaning.

Our surveys on the other hand are representative of both the "suffering" group and the "searching for help" group, potentially accessing anyone who visits. Nobody finds TT unless they fit within these groups. People who are getting along fine do not search the internet for tinnitus help. The data is valid, but we have to understand that any results give us a snapshot of these groups and adjust accordingly.

The next step is to follow a journey with respondents and gather longitudinal data. It's not going to be easy because experience tells us that people with tinnitus who improve do not want to be reminded of it.

 

Not an argument.

 

End of Thread.

 

I’m getting deja vu again, just1morething.