Written By:
- Date published:
5:30 am, August 24th, 2009 - 76 comments
Categories: Social issues, unemployment -
Tags:
But a job is much more than an economic phenomena, nice to have, sometimes lost. Work is about dignity, a sense of worthiness. For most of history, unemployment – not having a task to do if one wanted to – has been a temporary rarity. It was only industralisation that allowed the creation of a surplus pool of labour, the involuntarily unemployed. Wanting to work but not being able to get it is an unpleasant experience, as many of you will know. One can feel hopeless, useless, and frustrated – it’s not something that people cope with well. It tends to lead to more negative social behaviour – more substance abuse, more crime, more mental illness, more violence against others and against oneself.’
I wrote about this a while back in the context of the crime figures, which show a near perfect link between the unemployment rate and crime rate – crime goes up 5% for every 1% increase in unemployment (or, coincidentally, 20,000 for crimes for 20,000 more unemployed).
It was the release of the latest self-harm figures on Friday that got me thinking about this again. I got the suicide data for the last 20 years and compared them to unemployment.
There’s a strong correlation – 0.45 for the general population, 0.6 for young men – that’s a very strong indication that one causes the other). The trend is that for every one percent increase in unemployment the suicide rate goes up 0.24 per 100,000, which is 20 people per year. The increase is four times as strong for young men. Not being able to get work can be the final straw for some people, and young men are especially vulnerable.
This is why I get so pissed off when people talk about unemployment as if it’s some unfortunate mishap, nothing serious, one of those things that happens in capitalism. Unemployment is a root cause of social malaise and individual tragedy.
That’s why it’s so important that government’s commit to full employment programmes and actually do their utmost to realise them. It’s not just so they can afford a nice standard of living, it’s so people can have dignity, feel they’re worthwhile, that they are a part of society, that they’re contributing, that life is worth living.
(*the nature of modern economies with 10% of jobs disappearing and being replaced every year, people moving city, entering and leaving the workforce, there must always be a ‘churn’ level of unemployment – 2-3%)
Blood on their hands. Are you reading this Paula? John?
That’s too far. I’m not saying that National are conscious of this outcomes of unemployment. I think they just don’t see unemployment in these terms, and if they were I would hope they would put a hell of a lot more effort into getting unemployment down.
Marty, why don’t you just say what you’re trying to deduce from your faux-causation, that Mr English is evil, that he doesn’t care about unemployment, that he wants unemployment to rise, and he wants young people without a job to kill themselves?
No that’s not my point.
My point is that a full employment policy is about more than giving people an income.
I don’t think English is evil, I just think the right’s thinking is shallow and ignores the social consequences of unemployment. That’s not surprising because admitting that individual’s behaviour is influenced by external events and not simply generated within goes against the moral basis of rightwing ideology.
If you think my conclusion that suicides and other negative social outcomes are increased by unemployment is wrong, come up with argument – don’t just call it ‘faux’ – you’re meant to be a banker you should be smarter than simply denying the evidence before your eyes just because it’s inconvenient to your ideology.
Marty, I’m not a banker and never have said that I am. Secondly I don’t know what a “banker’s ideology” is.
The fact that Conor Joe jumped to the same conclusion as I was writing my post confirms that you were intending that people draw the link that they in fact drew, that Mr English is somehow responsible for increased suicide because of his policies.
Just a bank clerk who can spend a great deal of time on his employer’s computer trolling blog sites and responding with NACT nemes every 15 minutes!!
Good on you, irascible.
I see now that Marty’s post has been greeted with the condemnation it deserves there’s little left to do other than attack other commenters.
Tim’s just a very hard worker. He’s on the blogs all day and then stays up all night doing his bank auditing work.
And before anyone starts accusing him of impropriety, how he stays up all night is his own business. As long as he can afford it and he’s not harming anyone else let’s just let him get on with his work please.
Tim is creating an argument at the fringe.
The theme of the post is that unemployment is a terrible, destructive thing and National is doing far too little about it.
I agree that it is not a deliberate strategy, at least I think this is the case, but it is the sign of the complete indifference of this administration to ordinary people that they are so inactive.
Let’s get back to the theme of the post which is about damage, rather than engage in an argument about where the damage is intentional or not.
I see now that Marty’s post has been greeted with the condemnation it deserves
I’ve known about the link between unemployment and increased young male sucide since sometime in the early 1990’s when it was pointed out to me (with evidential data) in a Church sponsored forum on Social and Economic Development. Over the last few years I’ve made mention of it once or twice and have always been howled down by the rabid right.
Fact is Marty is correct about the correlation with social harm.
Fact is that this govt has done NOTHING towards stemming the rise of unemployment.
Fact is that this govt has done NOTHING to improve pay or conditions, improve skills training or education opportunities, what little they have done has pushed the balance of workplace power to the employers’ favour.
OK so Bill English does not literally have blood on his hands, and probably does not eat babies for breakfast… but if a govt pursues policies that demonstably leaves a trail of dead young men in it’s wake… who is accountable?
BK drinkwater explains the quality of thinking in this post.
He’s right. You go on seek and see what jobs there are. All those jobs before were created by the bubble that’s recently burst.
Crap as always confused, in my sector, highly skilled and highly paid, suitable jobs on seek have gone from 5 to 10 per day last year to 0 to 2 this year.
I applied for some of those jobs last year and none of them were anything to do with any kind of bubble.
If more people are employed elsewhere because of the bubble, you will need more specialist people, IT engineers, no? It’s not directly related, no, indirectly, yes.
That the housing bubble drove unemployment down doesn’t mean we can’t have a full employment policy now
OK Marty G you have done a great job of showing us that unemployment is a bad thing, now how about some suggestions of how the government can ‘fix’ this.
Just in case you haven’t noticed we are in the middle of a world wide recession. I doubt it would have made any difference if National or Labour were in government.
The Greens’ New Deal is the obvious starting place. National has already taken a small slice of it with their watered down insulation programme.http://www.greens.org.nz/sites/default/files/Green_New_Deal_Economic_Stimulus_12_June.pdf
ieuan
“how about some suggestions of how the government can ‘fix’ this”
I thought this is what we paid that nice Mr Key to do.
Nah, he’s the Minister of Tourism. We pay him to be a tourist.
Penal Rates: Double time for more than 6 hours per day or 30 hours per week and watch the unemployment rates drop (and probably a decent boost to investment in productive capital as well).
Marty- Excellent article based on rational argument and supported by hard figures. Lack of empathy by those not touched by job insecurity results in a callous disregard for others. It never fails to amaze me how some people don’t seem to develop any sense of social responsibility towards others.
Thanks Di. It’s disappointing that people won’t acknowledge the facts in front of their eyes – we know that unemployment leads to depression, we know that depression leads to suicide but the idea that a full employment policy helps reduce suicide gets rejected because a full employment policy goes against their ideology
I see the question as- Is it more important to have social and economic harmony and fairness or to have people paying lower taxes?
It depends upon which economic philosophy you follow. My belief is that economic growth follows from a strong, healthy, well educated well paid secure middle class, which can never happen under a low tax, low spending regime.
Of course those with a different social and economic philosophy will disagree- which they should be respected for. They do need to back up what they say, however.
It gets worse when you look at youth employment.
I: we know there is a recession on. The government appears to not know. At least they haven’t done anything of substance to deal with the unemployment. They have instead concentrated on increasing it with their policies in the public sector, and attacking beneficeries wanting to retrain
worse ghz useless
Marty – looking at those graphs, you fit a linear function to what appears to be non-linear data. I bet you’ll get a better fit with a non-linear function (eg quadratic). If so, the conclusion would be slightly different. It looks like an asymptote is spoiling things for you a bit.
Oh, and maybe ease off on the “strong indication that one causes the other” bit. Every semi-literate armchair scientist knows that “correlation does not equal causation” and that catchphrase will be an immediate knee-jerk reaction to this sort of data. Don’t get me wrong, I think there probably is a causal relationship between unemployment and suicide, but I’m not sure if that is a direct relationship, or one that is mediated by one or a number of other variables.
capcha – tested
I think you have to remember that these posts are written for a general audience. everyone can understand what a scatter graph is, most people will have an idea of what correlation means, but start getting into anything too complex and you just look like you’re manipulating data for your own purposes.
personally, I like that the Standard backs up its arguments with data like this, it’s sure a contrast to the likes of Kiwiblog, where it’s all absolute claims and sometimes a few highly selective numbers thrown in.
You can’t deny that the data indicates strongly that the two things are linked, and that means either one is a cause (not the only cause, of course) of the other or there’s a hidden common cause – which doesn’t make sense in this context. And the nice thing about this data is it backs up with a little research would suggest – unemployment increases depression, depression is a major factor in suicidies, therefore we would expect suicides to increase with unemployment.
Marty – great post. I was a volunteer telephone counsellor for a few years when unemployment was high in the 90s. I have no doubt there is a causative relationship between unemployment and suicide.
Researcher – rather than jump straight in and apply a non-linear relationship, the first thing I would test would be the relationship between the trend from the previous data points and the suicide rate. In other words, for the same level of unemployment, if the trend was rising unemployment I would check if the suicide rate to be higher, whereas if the unemployment rate was falling I would check whether the suicide rate was lower. Having said that, I think the graphs prove the point well enough as they are.
I suspect that Marty is using something primitive like excel open office spreadsheet charts.
I’d take a bet that they don’t have any good non-linear data fitting. But since I haven’t used the charts in there for a decade…..
Every semi-literate armchair scientist knows that “correlation does not equal causation’
But neither does correlation imply no causation either. What it tells you is that you have to do some digging to find a plausible mechanism to explain the correlation.
The most common cause of suicide is depression, which in itself is a deep manifestation of a sense of hopelessness, lack of purpose and despair about things ever improving.
The really interesting clue in the data is that the correlation is much stronger for young men than young women. Young men in their 20’s are especially vulnerable to unemployment linked depression, because more than anything else their prospects of finding a life partner and establishing a family, are linked in the long run to that first critical job, their first important steps on the career ladder.
So while there is always a steady stream of self-harm and suicides, across all age groups, and for many different reasons…. there is very good reason to think that periods of high youth unemployment directly result in an increase in suicides in young men.
“But neither does correlation imply no causation either”
I know, I said that in an earlier post about BMI. I’m just saying that we should be careful when making claims about “strong indication that one causes the other”. It invites the inevitable response. I completely agree with your second sentence.
“There’s a strong correlation 0.45 for the general population, 0.6 for young men that’s a very strong indication that one causes the other”
Absolute rubbish. Correlation say absolutely nothing about causation. Any stats book will point this out.
^^ Note the kneejerk RWNJ reaction just as predicted.
No, causation is not what correlative data shows. There might well be other merits to the argument, but that doesn’t change the fundamental point that you have to explain it, you can’t legitimately just rely on a similarity between two sets of numbers and say “see?”
It doesn’t take a rocket scientist to understand this, and it’s wrong to assume that anyone who points out that the numbers don’t say what they’re claimed to necessarily rejects the argument or is opposed to it. The criticism is of Marty’s methods and exposition, not of the problem.
Marty’s own ‘people who point out the flaws in my analysis clearly have no sympathy for suicide victims or the unemployed’ upthread is similarly idiotic. One can be both compassionate and in favour of the correct use of data; in fact, I’d argue that that’s the best way to be.
L
No, causation is not what correlative data shows.
Yes but it’s still never grounds to dismiss a possible causation either. What it tells you is to look for a plausible mechanism linking the two sets of data; and in this case it’s not terribly hard to provide one.
What you can also deduce is that if you want to reduce the incidence of the terrible tragedy of suicide, then reducing youth unemployment is quite effective and useful, even if the mechanism remains unclear or unproven.
I agree it’s not grounds to dismiss a correlation, but I don’t see Paul doing that – all I see is him pointing out the bleeding obvious; that the data doesn’t say that, and the mechanism of which you speak isn’t credibly outlined, so the post doesn’t really contain anything except opinion backed up by some handwaving (which, to be fair, is almost a definition of a blog post).
The case Marty has made makes sense, but is weakened by the misuse of the data and the absence of proper explication. It could be a lot stronger.
L
Lew. Where does Marty say that?
Marty’s pointed out a strong correlation. there’s an obvious reason why there would be a causative link. The data hasn’t been wrongly used, it’s been used to illustrate that underlying fact that nobody has denied – unemployment increases suicides.
I don’t get what your problem is. Apart from the need to feel superior and nitpick.
BR, the point is that unemployment may well increase suicides, but this data doesn’t show that. It might show that in conjunction with some other information, but that information isn’t provided.
In the comment I paraphrased Marty from from “It’s disappointing that people won’t acknowledge the facts in front of their eyes we know that unemployment leads to depression, we know that depression leads to suicide but the idea that a full employment policy helps reduce suicide gets rejected”.
It doesn’t follow that someone pointing out a flaw in your methodology opposes your conclusions. It simply doesn’t. Using data and terminology properly is really important, expecially when you rely on the data to make your case for you, rather than relying on argumentation or other sorts of evidence. Pointing it out isn’t about being superior, it’s necessary. There’s an incredible amount of bad statistical analysis out there which is used to justify everything from climate modelling to product choices. Misapplying statistics like this is part of the problem – the argument is probably a good one, and would be so much stronger if it were correctly put.
L
I can see you come the revolution. Riding around on your high horse telling the rest of us that we’re doing it wrong.
Marty’s data shows that there’s a strong correlation between the unemployment rate and the suicide rate. The Right has an ideological reason to deny the conclusion that naturally arises from that, so they have.
You (predictably) get on your high horse pointing out the correlation doesn’t prove causation and no-one’s arguing but you better have some other explanation for the correlation if you think that the logical conclusion isn’t the one we should adopt.
You haven’t even made an argument about how these statistics are supposedly misapplied. All you’ve managed is a high school maths class mantra. I’m surprised you’re not claiming Marty’s argument is invalid because the axes don’t start at zero too.
Good on you for admitting that Marty didn’t claim that the Right have no sympathy for the victims of suicide. One mistake admitted. Only a few more to go.
BR, I haven’t made any sort of argument about the conclusion or whether it should be accepted or not. I agree with the point of the post, he just hasn’t done enough to prove it.
Why accept a lower threshold of proof for conclusions you agree with than those you don’t? People around here would be all over this post if it tried to argue a similarly strong correlation with an opposite end.
L
No-one is accepting a lower threshold of proof. Marty’s presented the data, presented graphs to us, told us what he thinks, and guess what everyone looking at the data and the facts around suicide and unemployment comes to the same conclusion.
Any week, you can go across to Kiwiblog and see Farrar malaciously presenting figures specifically skewed to suit his purposes. It’s transparent yet I don’t see you over there whinging.
This really is looking like some kind of personal thing against Marty, which is weird frankly. The guy’s putting up the data, he’s not being selective (if you check the source data, he’s gone back as far as the suicide numbers go in the report), he’s drawing a conclusion. He’s not even stating that it’s absolutely true just saying what everyone agrees – “that’s a very strong indication that one causes the other”. He’s trying to encourage debate drawing on the data, and I think it’s great.
I think you need to consider your own motives here, Lew.
BR, I don’t think Lew will necessarily appreciate me saying it, but I’ve always found his motives to be unimpeachable. A far cry from the ethics you displayed a few days ago when you did your best to advance a rumour that an MP was the other party involved with National’s president. That was one of the more disgusting things I’ve seen you say.
There’s a stronger correlation between homosexuality and suicide, so would it be reasonable for me to say that homosexuality causes suicide ?
BR, what are my motives, then? Is this the bit where you imply I’m a secret undercover faux-leftie planted by the VRWC to undermine the great juggernaut of the left, because I frequently disagree with The Standard writers and am often critical of Labour?
Criticism is necessary. Responding defensively to criticism and casting aspersions on the motives of criticisers – even when they agree with your substantive point – is a major failing in political movements on the left at present.
My major criticism is that Marty tends to play a bit fast and loose and to not look too closely at numbers with which he agrees with. It’s not personal against him – but a lack of analytical rigor is bad wherever it shows up.
As for why you don’t see me bagging Farrar’s numbers – I decided long ago that if I ever got a login at KB, I’d never be able to tear myself away from the stupid; I don’t have an account there (and won’t get one). I do, however, frequently bag him for other reasons. The Standard I had (and to some extent retain) higher hopes for.
L
BR is still right; it’s a statement of the obvious that correlation does not equal causation, but by itself that’s simply an easy and ultimately pointless thing to say.
Are you for instance going to suggest that increasing suicide rates cause increased unemployment? Or that it has something to do with cosmic rays? If you want to contribute a useful criticism you need to propose some plausible causative mechanism different to the one Marty and others here have suggested.
RL,
If you want to contribute a useful criticism you need to propose some plausible causative mechanism different to the one Marty and others here have suggested.
I think “use your terminology correctly and make sure your methods are rigorous” is very useful and apparently much-needed advice.
L
Tim. The big boys are talking go cry somewhere else.
Lew. I don’t think you’re a rightie. I think your need to criticise the Standard on trivial grounds is probably grounded in 1- your staunch defence of the sell-outs in the Maori Party because you believe in the ideal they’re meant to represent (fair enough) but can’t face up to the fact that they have sold out, and so you don’t like the Standard for putting the fact they’re sell-outs in your face 2- the relative success of your own blog’s approach which is aloof, intellectual, and hectoring compared to the earthier battler style of this blog
The Standard isn’t perfect. I wouldn’t expect it to be from a small group of writers giving their spare time but they know who the enemy is and, while they don’t refrain from criticising the left, they don’t make an occupation of stabbing their allies in the back.
pressz, got any numbers? If they point to a strong correlation, i would suggest that it’s in part because of the social ramifications in some communities of being gay.
as for my suggestion that unemployment increases suicide http://www.google.com/search?q=suicide+unemployment&rls=com.microsoft:en-nz:IE-SearchBox&ie=UTF-8&oe=UTF-8&sourceid=ie7&rlz=1I7GGLL_en
BR, ah, there’s your problem. You misunderstand my arguments, so it’s logical that you’d misunderstand my motivations. In turn:
1- your staunch defence of the sell-outs in the Maori Party because you believe in the ideal they’re meant to represent (fair enough) but can’t face up to the fact that they have sold out, and
I think it’s too early to call them as sell-outs, and I will happily do so if they prove unable to make any substantive gains in exchange for their support of this government. But remember, I’m not so much concerned with limited tactical policy wins as with strategic symbolic gains or gains in political infrastructure. They’re already well on the way to making just such a gain with the Foreshore and Seabed Act review, about which I think we’re due to hear back in the next week or so. I will be very concerned if they don’t take a stronger stance on the matter of mana whenua seats than what they have done so far. And none of this ‘non-voting representation’ stuff, either; that’d be inadequate.
However I’m patient, and I don’t necessarily think they should quit the government over the issue.
so you don’t like the Standard for putting the fact they’re sell-outs in your face
It’s not a fact.
To throw a bit of counter-motive speculation back at you: a lot of Labour partisans around here want the mÄori party to fail and for MÄori to come crawling back to Labour. That’s the thing which pisses me off most – people calling them done before they’ve even gotten going.
2- the relative success of your own blog’s approach which is aloof, intellectual, and hectoring compared to the earthier battler style of this blog
Well, for one thing it’s not my blog; I’m the second-to-most-recent poster to join and it was already well underway when I did. For another thing, it’s doing just what we want it to – the ‘earthiness’ of which you speak isn’t what we’re pitching for and we take efforts to discourage quantity in favour of quality. YMMV; if you don’t like it, kindly don’t bother with it.
I’m certainly not envious – I turned down an invitation to be a poster here in mid-2008.
L
BR, this is the thing:
they know who the enemy is and, while they don’t refrain from criticising the left, they don’t make an occupation of stabbing their allies in the back.
The ‘enemy’ for me isn’t just ‘those bad righties’ – it’s ‘people who misuse figures and draw spurious conclusions’ as well, regardless of how good their politics might be. I don’t give people a pass just because I agree with them, and if you want to maintain or improve the standard of thought and analysis within your political movement, neither should you.
L
…you can’t legitimately just rely on a similarity between two sets of numbers and say “see?’
Could I say, “See Hume”? 😉
Probably few would get it, but even so, that’s a bit of a departure from statistical analysis.
L
Paul. Where does Marty say that correlation equals causation? Correlation is suggestive of a link between the two variables. It says ‘go looking for the link’ or, if a link is already posited ‘hey, you might just be on to something’
Paul, you’ve done absolutely nothing to disprove this post’s thesis – that higher unemployment leads to bad things like suicidies increasing, and a full employment policy decreases them. You don’t do that because you can’t. Yet you can’t acknowledge the truth of the argument because that would froce you to admit your econo-centric, dehumanised ideology is bankrupt.
Instead you resort to an arrogant statements of the obvious. You’re not fooling anyone. Except yourself.
Note that he writes
“There’s a strong correlation 0.45 for the general population, 0.6 for young men that’s a very strong indication that one causes the other’
My point is that Marty does nothing to show that unemployment causes suicide. A correlation says nothing about the nature of the casual relationship. All that a Pearson correlation coefficient says is that there’s a some linear correlation between the two variables.
And at 0.6 its not a great one.
It could be that unemployment causes depression and thus suicide, it also could be that depression causes unemployment, it could also be that a third factor causes both or it could also be that the correlation is completely spurious.
Giving a correlation gets us nowhere.
And given the way he appears to do his regression, without controlling for anything else, and without giving even the most basic of stats for the regression, his result really isn’t worth much. If you don’t believe me try submitting this “analysis” to a journal for publication and see the reply you get.
Any stats book will explain this.
Paul. In terms of social indicators, 0.6 is strong.
The other ‘possible reasons’ for the correlation you’ve given don’t make any sense. How would depression cause measurable increases in unemployment? What would be the cause of the increase in depression?
The logical reason for the link is the one Marty gives.
You just can’t bear to acknowledge that because it means that employment is more than another economic indicator to be chucked into one of your formulas, it’s literally a matter of life and death.
PW – “Correlation says absolutely nothing about causation” is a bridge too far. Correlation indicates that some form of relationship exists, and provides guidance as to the nature of the relationship. With a bit of common sense it is not too difficult to make valid statements about cause, once a correlation is established.
In this case it could be – as suicide rates rise, unemployment also rises. Does this make sense to you, PW? It doesn’t make sense to me. Forgive my callousness in saying so, but technically suicide by an unemployed person would reduce the unemployment rate.
So another option is that unemployment, for an individual, increases the likelihood of suicide. Seems like a reasonable explanation to me, and fits nicely with my experience of dealing with suicide.
What I haven’t got yet from all the comments attacking the stats is what the alternative explanation is. Sure, there are intermediate steps (unemployment causes depression and it’s the depression that causes the suicide – the “guns don’t kill, people do” argument), and unemployment is usually one of a number of factors, but the end result is both the same and terrible.
And something can be done about it, either break the causative relationship, or keep unemployment low, but doing nothing is an appalling choice.
“PW “Correlation says absolutely nothing about causation’ is a bridge too far. ”
I would argue not. It could be that unemployment causes depression and thus suicide, it also could be that depression causes unemployment, it could also be that a third factor causes both or it could also be that the correlation is completely spurious.
All we know from the correlation coefficient is that there is some, may be worthless, linear relationship in the data.
It cold be any old thing, true. Care to argue for one Paul?
This whole pedantic argument just reinforces marty’s point:
In his second para he makes his case. Is it to a peer review level? No. But this is a fricken blog fer crissake.
National ran a fairly strong campaign theme that Kiwis were flocking to Aussie because of high taxes in NZ, and they did so on far less analysis than what marty has done here. This is the way people actually talk and think. Some shit is just fairly obvious. Like ‘not having a job is depressing’.
If you want to argue that psychological depression leads to both unemployment and suicide, go right ahead. Should be interesting to see you try. Wonder what causes these outbreaks of depression that just happen to coincide with the economic cycle.
Yes the relationship could be any old thing, that’s my point. Just saying we have a correlation between A and B says nothing about causation. A may cause B, B cause A or C cause A and B or all of the above. All are possible with exactly the same correlation between the variables.
Yes, it could be any of those things, until you apply a bit of common sense, or experience, of course.
My opinion is biased of course, but you get that after talking to people on the phone after they have overdosed and before the emergency services arrive.
Do you actually have an opinion on this, or are you just here to cast doubt?
or you could use google http://www.google.com/search?q=suicide+unemployment&rls=com.microsoft:en-nz:IE-SearchBox&ie=UTF-8&oe=UTF-8&sourceid=ie7&rlz=1I7GGLL_en
honestly, paul, trying thinking with your brain, not your jerking knee. I know don’t want to acknowledge the implications for policy if unemployment has profoundly negative social effects but you’re looking pretty dumb sitting there with your hands over your eyes saying ‘it could be anything, it could be anything’
captcha: aware
@Armchair Critic
Paul’s more pointing out some rather basic issues with correlation, though he should have pointed out more clearly that a empirically testable and/or valid mechanism is needed to explain the correlation.
I’d also disagree that the 0.40-0.60 correlation’s are “substandard”, but then I’m a biology undergrad and used to the messiness of biological data. Where correlation’s of similar strength thrown up in the initial analysis are useful for indicating whether or not there’s a relationship between two (or more) variables worth digging into the more esoteric forms of data analysis for, and indicating research directions.
Though briefly looking at the paper gomango mentions, (and fails to bloody link to) it appears that there’s no significant predictive power for unemployment levels on suicide rates across the OECD. But, as Paul sort of mentioned, other factors can come into play that may confound analyses, and need to be debugged, i.e. cultural factors may come more into play, though not having the time, nor the concentration (ADHD + sleep deprivation), and the econ/stats backgrounds I can’t read deeper into this…
And here’s the Magg paper;
http://www.kof.ethz.ch/publications/science/pdf/wp_207.pdf
Mind you, he couldn’t see that this cartoon was making a moral rather than an economic argument, so there you go.
“or you could use google http://www.google.com/search?q=suicide+unemployment&rls=com.microsoft:en-nz:IE-SearchBox&ie=UTF-8&oe=UTF-8&sourceid=ie7&rlz=1I7GGLL_en”
Marty. For a start none of the references in that search have anything to do with your “analysis”. Your regressions and your correlation shows causation notion still has problems. For example, I’m told that a youth in your data set is someone 15-24, so what’s with the increase in the slope of your youth regression? For 15-18 group unemployment doesn’t look like much of an issue since they are in school. Add to that the over 18s who are still in some form of education and thus unemployment isn’t an issue and I don’t see where the increase in the slope coefficient is coming from. It has to be down to those unemployed in the 18-24 group. It seems a big jump for just this group. The suicide rate could increase for the 15-24 group but for it to be due to just unemployment seems unlikely given the number in that group who are not in the labour force. Your “analysis” should have accounted for these factors.
To take just one example from your google search:
“Relationship between the Economy, Unemployment and Suicide”
Prepared by the Suicide Prevention Resource Center
November 12, 2008
It states
“Unemployment contributes to suicide risk, but does not “cause’ suicides on its own.
* Employment status is but one of dozens of factors that interact dynamically within individuals, communities, and societies and affect the risk for suicide.
* Although unemployment is associated with increased rates of suicide, many individuals may have lower rates of employment because of mental health and/or substance abuse problems, which are also associated with increased suicide rates.”
Notice that the relationship between unemployment and suicide is much more dynamic than your “analysis” would suggest. Also note the second point. Unemployment may be “caused ” by mental health issues that are associated with increased suicide rates. As I tried to point out, a correlation between unemployment and suicide doesn’t just mean “unemployment causes suicide”, the interactions between the two can run in both directions or be caused by a third factor.
Also the report says
“We can expect a sharp downturn in the economy to increase suicide risk, especially among working-age adults and older adults whose retirement security is threatened.”
Why then do you show the increase in suicide rate for the youth group? Your “analysis” seems to be missing something.
@NickS
I have a fair understanding of what Paul is saying, a good knowledge of statistics is my bread and butter.
The way I see it is that this is a post on a blog, not a university assignment. Marty’s post would still make sense without the graphs, the graphs improve it, more graphs or statistics would help to quell some of the debate about the validity of the statistics. But that debate was really a distraction from the real issue. And the point of the post remains the same, increasing unemployment in NZ apparently has some kind of relationship to increased suicide rates.
My main concern about the statistics is that the reporting of suicide may have changed over the period over which the data were gathered, as the stigma relating to suicide has decreased, but that is just a guess on my part.
Paul.
Where did anyone say that unemployment is a sole cause of suicide? i have argued that higher unemployment increases the numbers of suicides – it doesn’t have to be a sole cause in a single case for that to happen.
Still, at least now you’ve admitted that this the basis of your complaint is you don’t want to accept the conclusion.
I’ll try to explain it for you. Every human has a propensity to any given behaviour, whether that propensity is realised will depend on a multitude of factors.
You like reducing human behaviour to numbers so I’ll give you an analogy. Say everyone has a suicide score, when it hits 100, they kill themselves. Everyone will have different base scores and different added points due to events or circumstances in their lives. Let’s say unemployment is worth 10 points. It’s not in and of itself going to be a sole cause for anyone but for those who already have other pressures, it could push them over the line. So, with a general increase in unemployment you’re going to get some more people killing themselves.
Your ramblings about age brackets don’t make much sense but here’s how i got the numbers – the suicide numbers are straight from the report – the youth bracket in that report is 15-24. The unemployment numbers are the number of unemployed from the age groups 15-18 and 18-24 combined divided by the labour force (note labour force, not population) for those age groups. The trend line and it’s slope are determined by excel. The correlation equation also. I haven’t done anything to the numbers, its a straight up and down report of what they show.
And the fact is you can’t handle what they show because it conflicts with your ideology.
Thanks to NickS for the reference to this paper:
“And here’s the Magg paper;
http://www.kof.ethz.ch/publications/science/pdf/wp_207.pdf”
Let me note this statement from the conclusion to the paper:
“In general however, identified dependence of suicide rates on economic conditions is weak. Typically, significant effects are only present in some age-sex groups, while over-all societal suicide rates are unaffected by economic conditions. This result is consistent with Rodriguez-Andres (2005) and Gerdtham and Ruhm (2006). Both studies report that economic variables are insignificant once country fixed effects are accounted for.”
Not a problem Paul, but that’s merely the conclusions for the whole data set, of which, since I can’t focus for hell at present, haven’t dug into the methods to see if they looked at it country by country, which might be useful to use as a means to pick up the effects of cultural influences x unemployment. But also, as others have said here, what Marty’s pointed out is still troubling irrespective of quibbles over causation and needs to be dealt with via WINZ and other agencies to avoid, to put in terms you might understand more clearly, a loss of human capital and significant economic costs of the impacts of these suicides on friends, family and former co-workers. Not to forget either the long-term impacts of depression on the individual, both slight and severe, which I know alas all too well.
@Armchair Critic;
Sorry about that.
“I’ll try to explain it for you. Every human has a propensity to any given behaviour, whether that propensity is realised will depend on a multitude of factors.”
As I have already said
“It could be that unemployment causes depression and thus suicide, it also could be that depression causes unemployment, it could also be that a third factor causes both or it could also be that the correlation is completely spurious.”
What I was trying to point out to you, and now appear to have succeeded, is that the relationship between unemployment and suicide is not as simple as you originally claimed.
If it is a “multitude of factors” then why use simple regression? If there are a “multitude of factors” then at the very least multiple regression should be used to deal with the other factors than can effect the suicide rate. This brings me back to my original point, that was that your analysis, based as it is on simple regression and a correlation coefficient, doesn’t show the result you are claiming.
As to my discussion about age brackets not making much sense to you, I can believe that. This is just another way I tried to point out to you that the relationship between unemployment and suicide is due to a “multitude of factors”. The point is very simple. If you have a whole lot of people in your sample, some of whom will die due to suicide, but who cannot be unemployed, then it is not clear how unemployment could be a factor in suicide for that group. So one of the “multitude of factors” that should be controlled for is being in the work force and thus being able to be unemployed. If you are in school, for example, and attempt suicide, unemployment is unlikely to be one of the causes. So to get the true marginal effect of unemployment on suicide you may want to remove such people from your sample.
Also I said before what do the references in google search have to do with your “analysis’?
“And the fact is you can’t handle what they show because it conflicts with your ideology.”
What ideology?
Paul. You don’t think you have an ideology? You’re one of the most ideological bloggers out there. Your ideology dresses itself up in numbers to make a claim to rationality, that’s all.
I never claimed unemployment was the sole cause of suicide, read the post. I didn’t so a multiple regression because the point was simply to show that there is a relationship. I don’t have the raw data on suicides, so I couldn’t control for whether suiciders were in the workforce or not. It would stregnthen the data but not having it doesn’t invalidate it.
Look, it’s not a sociology exam, Paul, it’s a blog and we’re already beyond most people’s maths when we say ‘correlation’.
Can you imagine if I had to try to make a quick and nasty explanation of multiple regression at the same time? Half the righties would claim I was just playing tricks to make the numbers say what I want while you and Lew would still be nitpicking.
I was never good enough at stats so wont argue the data.
I will say however that the dialogue rings very true in terms of the large group of local teenaged males I know.
I’ll start with a disclaimer. I walked out of maths class in Year 10, never to return, because I’d woken up to the fact that nice malleable words were my thing, not these brittle “numbers”.
ben referenced BK Drinkwater’s analysis above. BK says, inter alia:
So isn’t that the problem? Don’t we need to be able to account for those other factors and then try to prove a correlation or otherwise?
Personally, I’d suspect the correlation would remain. I’ve experienced several of the other causative factors BK lists yet I have never felt as depressed or hopeless as when I experienced a lengthy period of unemployment. Because one could always find the cause of those other occurrences to be at least partially external — anything from “fate” to “my ex-partner’s a *****” — to help get through it, whereas seeing the “…other candidates were better suited to the position…” letters piling up feels like a rejection of who and what you are. Or perhaps that’s true only of people who define themselves primarily by their profession.
Surely this shows one thing unarguably — that we need better data on the characteristics of those who commit suicide. The MoH data Marty has used has an index for “deprivation” based on the residence of the person. That provides very little useful data on their background.
And, as a corollary, WINZ needs to be more concerned about the mental health of those with whom it is working. A survey of registered unemployed which asked about the effect of their plight — from demotivation to suicidal ideation — would surely be useful. And in the meantime, it wouldn’t hurt for WINZ offices to display publicity from the various helplines and other community initiatives, and perhaps to offer crisis counselling itself.
Everything you need to know about correlation:
http://en.wikipedia.org/wiki/File:Correlation_examples.png
There have been plenty of studies done on suicide and the employment rate and the outcome is not that supportive of the “high correlation” thesis. For instance Economic Correlates of Suicide Rates in OECD Countries, Thomas Maag found In general however, identified dependence of suicide rates on economic conditions is weak. and We do not find a significant association of suicide and inequality.
Personally though I’m inclined to believe there is some relatationship between feelings of self worth etc and suicide, employment being one facet of self worth, but there are a much wider range of things at play than just employment. Four suicides (three youth, one middle aged) that personally touched our network of friends on the north shore recently – 1 employed (youth), 1 self employed and two students. Not sure how employment affected any one of them.
And to be finickity about your data – how about testing the relationship you claim for significance – i think you’ll find you don’t have a) a strong enough correlation, and b) enough data points to claim any significant likelihood that there is a relationship. Thats a pretty easy test and can be done in about 3 minutes – would make your argument stronger.
Rex,
This is a far more compelling argument for the proposed solution than the original post, even though it contains no numbers at all.
L
lew I don’t know what your problem is mate and I’m beyond caring but don’t come on here and purposely misquote me on my blog just to make yourself feel good and don’t make bollocks attacks on my work.
and do some damn reading http://www.google.com/search?q=suicide+unemployment&rls=com.microsoft:en-nz:IE-SearchBox&ie=UTF-8&oe=UTF-8&sourceid=ie7&rlz=1I7GGLL_en
Marty, I’m not attacking you, I just wish you’d get the fucking method as right as you usually get the conclusions. Honestly, I agree with a lot of what you say, you just use spurious appeals to statistical authority to justify it, and that discredits what would otherwise be perfectly reasonable.
L
I think Lew and I have similar views on this.
My main issue is that when analyses and conclusions are not watertight and carefully expressed, you set yourself up for attack. This is particularly true for data that uses correlations to demonstrate associations. I know, I do it for a living. My research is constantly criticised by armchair ‘scientists’ because “correlation is not causation”. And yet I alway clearly point this out in my publications, and I never claim causal links, and I always suggest other explanations, and I never assume my interpretation is the only correct one. Of course, most armchair critics don’t actually read the papers, they just respond to a headline. Funnily, fellow scientists rarely criticise research on these grounds.Oh, and for those who are keen to learn, you might like to read up on the Bradford Hill criteria of causation.
And for those who think r=0.6 is small, it isn’t. It indicates that 36% of the variance in the association between suicide and unemployment is accounted for, in this data-set. That’s not a trivial figure. And no, that doesn’t mean 36% of suicides are due to unemployment, another easy trap to fall into. There are other statistics you can use to calculate the amount of suicide we might be able to attribute to unemployment.