Social Question

iamthemob's avatar

Are statistics worthless in examining social issues, or is there something to them?

Asked by iamthemob (17121 points ) September 4th, 2010

So…“there are lies, damn lies, and statistics.” I’m all for statistics when we’re talking about the hard sciences. However, the more I see them used, and the more I want to use them, to show how some policy does some thing that helps a social issue, or that it does harm…the less I feel like they make sense.

Statistics are often used by people advocating for either side of a complex social issue to show that there is evidence of a causal link between, lets say, gay marriage and increased tax revenue; or gun ownership and a reduction in crime. I personally was always committed to the fact that states with the death penalty were actually those with the higher crime rates than abolitionist states.

Also, we are also given numbers referred to statistics that are not – people using percentages to show causality or something less drastic. Of course, correlation is not causality, and if you don’t know what the sampling procedure was, or how certain variables were controlled for, you’re left with a sense that something’s been proven when it really hasn’t.

So, can we or should we use statistics in our arguments? If so, what kind and how? How can we introduce them in a responsible manner? And should we be outraged at news outlets and reporters who reference numbers as proof in an deceptive way? And do any of them ever really do anything but?

Observing members: 0 Composing members: 0

19 Answers

ETpro's avatar

They must be examined with due diligence. It is easier to fudge statistics to get the result you want on social issues than on others like economics or military success where metrics measure more objective things. But it is difficult to study social change in any meaningful way without turning to statistics. Just be careful how they are gathered and interpreted.

iamthemob's avatar

@ETpro

But I wonder where they’ve been used and it’s been helpful. The more I think about it…the more they all just seem like junk except to show where a problem might be (this area has more crime than this).

After that, I think that statistics are less useful than community involvement and common sense.

YARNLADY's avatar

When viewed by a professional, in context, statistics can be very useful tools. To the uninformed, they can be used to trick people.

iamthemob's avatar

@YARNLADY

I agree…but it seems like rarely do people understand them when they use them. Again, me included.

So shouldn’t the standard be to keep them out of the argument? Unfortunately, I feel like they end up making people think there’s proof to their opinion. And then it’s so much harder to change if it’s a dangerous one…

…aren’t they, therefore, really, really dangerous?

YARNLADY's avatar

@iamthemob I frequently use sources that contain statistics to bolster my point.

iamthemob's avatar

@YARNLADY

So your answer is no.

Why do you think they add more benefit than harm, then. And can you give an example of a good statistic on the kind of social issue you think appropriate, and how it was presented clearly?

YARNLADY's avatar

Things that actually lend themselves to being counted, such as death rates/causes; voters eligible/registered/voting; crimes committed/solved; prison recidivism.

The statistics about opinions such as % of atheists or % of people who benefit from AA are useless.

iamthemob's avatar

Sure. Those are the ones I said I think are safe.

But those are really rarely the ones people use. More often, people use them to show causality instead of showing an issue – here’s the solution, otherwise, not the problem.

And placing one next to another gets more confusing unless it’s clear that they describe similarly situated populations but for the issue discussed.

Ben_Dover's avatar

Statistics are bogus. They are just a neat way to dehumanize a study.

Seaofclouds's avatar

Statistics are useful in some situations. In nursing, for example, we use statistics in evidence based practice so that we can give our patients the best care. Those statistics are gathered through research and have standards that have to be met before they are accepted by the nursing community.

Statistics can be used with social issues as well, you just have to look at how the information for the statistics was gathered and analyzed. Sure, there are some statistics out there that are padded to meet the researchers bias, that’s why you should look for other studies that either prove or disprove the study.

ETpro's avatar

@Ben_Dover In my experience, those that reject statistics as useless do so because they yearn to implement policies that a simple observation of outcome would refute.

Ben_Dover's avatar

@ETpro Statistics are useless because they take the humanity out of the equation.

Also, each of us being unique individuals makes statistics moot, for the most part…and not applicable to most situations as well.

ETpro's avatar

@Ben_Dover We aren’t going to see eye to eye on that, so let’s agree to disagree.

Dr_Lawrence's avatar

This question confounds the issue of polls and surveys with the issues of statistical analysis and how they are reported and (mis)interpreted.

Poor methodology and inappropriate use of the results of even well designed and executed research are problems, not statistics!

When those ignorant of research methodology and the proper use of statistics make pronouncements, the results are usually misleading, if not laughable.

iamthemob's avatar

@Dr_Lawrence

My concern is isn’t this USUALLY how they’re used?

But also, generally, I see how they can be used by professionals to indicate areas in need of analysis or to suggest further research…but that’s not really for public consumption.

And I totally agree that’s what the question does. However, that’s what happens in people’s mind generally. Poll results are so often CALLED statistics, and people don’t realize that statistical analysis requires a series of controls from the beginning and a specific set of mathematical tools in order to indicate causality. But so often – percentages are statistics, correlation is causality.

I just feel like statistics should not be something for public consumption, even really informal debate like here, because they are too easily mid-defined and misunderstood. My personal concern lies with the fact that people here “statistics show” and “surveys indicate” and here numbers and think “Well, Q.E.D.” and now we have a stronger assumption that’s harder to debate.

Dr_Lawrence's avatar

Popular use of information for which most members of the public are ill equipped is irresponsible and is frequently used to mislead and confuse others.

Media outlets are frequently guilty of promoting misuse of even good research, let alone when pseudo-scientific research reports are discussed.

People should avoid expressing opinions on things they do not understand. Knowing what you don’t know is a prerequisite to learning.

iamthemob's avatar

@Dr_Lawrence

I wouldn’t go so far as to say people should avoid expressing opinions on things they don’t understand. I think it’s problematic to say that you understand something fully at any point when it comes to most social issues. Opinions, if someone is open about them, are what we hold true now…but can change as we get more information. I think having an opinion means we admit we don’t know.

Because of that, I think that everyone should express them as much as possible, as long as it’s not a statement but a contribution. Knowing isn’t a prerequisite to learning so much as asking is…and that’s how we should view the expression of opinions.

wundayatta's avatar

@iamthemob Your beef, it seems to me, is with the media, not scientists. Scientists use the scientific method, and there are mechanisms in place that try to detect fraud, sloppiness, misinterpretation and malfeasance in the research.

However, scientists can not control how their results are used or interpreted, especially when someone from the media gets the wrong idea, and runs with it. Once things are out in the public,it is really hard to correct misunderstandings.

The other element in this equation is the education level of people. It seems that there are not a lot of people numerate enough to understand statistics, or even research methods. But then, education is one of the big problems, and researchers conduct statistical analyses of the data they collect in order to try to figure out what best practices are.

Of course, politicians appeal to common sense, all the time. Often, common sense is not sensible. But only research can show us that. Usually the research is performed using statistical analysis. That’s because what people think is “common sense” is usually based on their personal experience—experience that actual is not at all representative of the world we live in.

Finally, I think there is one thing that would help people get a lot more out of statistics, and that is if the press reported variance as well as mean. As you note, the average dehumanizes things. But I would argue that variance brings the human back into the matter.

If you focus only on the average… well, no one is going to be average. The figure is a kind of magical one. It is purely conceptual, since the average is not necessarily shared by a large number of people.

However, if you understand variance, you can begin to see that variation, in some cases, is quite high. That means that the average must be interpreted very cautiously. If there is less variation, then people will not see themselves as all that different from the “average” and it will make more sense to them.

But of course variance is rarely, if ever reported. So people see this average and they all see themselves as different from the average, and so the statistics seem bogus.

But it is not the scientists jobs to educate the masses. It is their job to communicate in terms that people with an appropriate education can understand. The media also has a responsibility to cover scientific stories using reporters who can both understand what they are covering and explain it to people who are not equipped to understand it.

And that’s not even bringing up the role of politicians. But I have written enough for now. Maybe some other time.

iamthemob's avatar

@wundayatta

Finally, I think there is one thing that would help people get a lot more out of statistics, and that is if the press reported variance as well as mean. As you note, the average dehumanizes things

This is an interesting solution. I like where that goes.

Personally, I don’t think that the media should ever really talk about it. Because there’s always a tendency to sensationalize in the media. And doing that with stats is just dangerous.

Answer this question

Login

or

Join

to answer.
Your answer will be saved while you login or join.

Have a question? Ask Fluther!

What do you know more about?
or
Knowledge Networking @ Fluther