We live in an uncertain and complex world, yet we continually have to make decisions in the present with uncertain future outcomes. Indeed, we should be on the look-out for "black swans" - low-probability high-impact events. To study, or not to study? To invest, or not to invest? To marry, or not to marry? While uncertainty makes decision-making difficult, it does at least make life exciting! If the entire future was known in advance, there would never be an element of surprise. Whether a good future or a bad future, it would be a known future. In this course we consider many useful tools to deal with uncertainty and help us to make informed (and hence better) decisions - essential skills for a lifetime of good decision-making. Key topics include quantifying uncertainty with probability, descriptive statistics, point and interval estimation of means and proportions, the basics of hypothesis testing, and a selection of multivariate applications of key terms and concepts seen throughout the course.
1.3 Uncertainty in the News
Loading...
Из курса от партнера University of London
Probability and Statistics: To p or not to p?
69 оценки
Посмотрите похожие видео
В Coursera собрались лучшие преподаватели мира. Вот несколько рекомендаций лично для вас:
Из урока
Dealing with Uncertainty and Complexity in a Chaotic World
Познакомьтесь с преподавателями
Dr James AbdeyAssistant Professorial Lecturer, LSE
University of London
Now there's a perception out there about probability and statistics that,
these are somewhat dry disciplines detached from reality somewhat abstract.
Well, I would like to dissipate that myth by really bringing the subject to life.
So here we are going to consider uncertainty in the news.
Now, a useful exercise for you is to do any internet search on
any new site of your choice and just search for the term uncertainty.
Now, I'm willing to bet there will be many articles which are
generated dealing with the aspects of uncertainty.
Quite often, of course it will depend on your choice of news site but it's likely that
these articles will be related to the economic or political sphere.
Indeed, in recent times,
we've seen some black swan events.
So black swan events are low probability but high impact events.
So we saw in fairly recent history,
two black swan events in quite quick succession.
June 2016, United Kingdom held
a referendum to decide whether or not to leave the European Union.
There was an expectation that the remain side would win the vote however,
the leave side won by a small margin of about four percentage points.
This was an expected.
And that single event,
has unleashed a whole wave of uncertainty.
Fast forward at five months to November 2016,
the U.S. presidential election between Hillary Clinton and Donald Trump.
An expectation of a Clinton victory but Donald Trump did prevail.
So yet again, a low probability but high impact event.
I say, low probability events.
If one actually took a look at the prediction markets
ahead of both the referendum and the presidential election,
the prediction markets were pricing in an implied probability of
about 75% for a remain victory in the Brexit referendum.
Similarly, for a Clinton victory in the presidential election.
And given the binary nature of these votes,
it was either going to be leave or remain and Clinton and Trump were
the only viable presidential candidates in that election.
That clearly meant, 25% implied probabilities for a leave vote or a Trump presidency.
Now, is a 25% chance event really that unlikely?
Well, imagine you toss a fair coin, cool.
Say you have two outcomes heads and tails equally likely if it's a fair coin.
So getting a 25% probability event,
really equates to tossing a fair coin twice
and let's say getting two heads in succession.
Now, if you think of it like that,
you get a coin out of your pocket now and toss it,
some of you will get two heads in succession and you will
perhaps not be that surprised by that result.
Well, that really equates to the same likelihood that the prediction markets had
of a Trump and a leave victories in those respective votes.
So uncertainty.
Well indeed, the financial markets,
indeed the political establishment did not expect these events to occur but they have.
So I would encourage you to have a look at how
the financial markets responded to this new information.
Indeed, we talk about uncertainty in the news.
Well, it's called news,
it's not called olds because we're looking at
new information rather than old information being delivered in any news reports.
So when we look at the financial markets,
they could be the stock markets,
they could be the foreign exchange markets,
what are the markets actually doing when you see prices moving around?
Well, I'd like you to think of this as the reaction of markets to new information.
Indeed, in our first video when we looked at the Monte Hall problem,
there, you were looking at revising your beliefs in light of new information.
Specifically, my opening of a particular door allowed you to
revise your probabilities of where the sports car was.
And indeed in a similar light,
the financial markets update their beliefs about the future economic prospects,
say of a particular country in light of real world events.
Be they political in nature,
or economic in nature, geopolitical in nature.
Indeed, look at how the oil price
fluctuates depending on what's going on let's say in the Middle East.
That's as tensions arise and subside between various oil producing nations.
We see the oil price react as a result.
So in periods of great uncertainty,
one can anticipate there being much more volatility in the financial markets.
Now, in due course in this move,
we're going to see some useful descriptive statistics.
Things like means, variances, standard deviations.
And we once introduced a useful exercise for you to
consider how the average level of various stock markets,
or currencies have changed in light of major events
and also how the volatility of these prices have also reacted.
Now, of course, I talk about economic spheres and political spheres,
but are these really mutually exclusive?
Should we think of economics and politics as silos with no interconnection at all?
Well, I think that's a rather simplistic and naive view of the world.
Clearly, political events will drive economic events as well.
The economic policy of a particular government, or a president,
will perhaps affect the economic path and trajectory of a particular country.
Indeed, in those news articles,
you may come across some related to
central banks and their decisions about monetary policy.
Should they increase interest rates,
or lower them, or leave them unchanged?
Of course, they're having to make a decision today about
which interest rates to have and hence whether to have maybe
a tighter or looser monetary policy without the certainty of
knowing what the future direction of the particular economy might be.
Interestingly, it's been said that an interest rate change will take
about 18 months to have a full impact on the economy.
To fully work its way through to the main street.
So if you think about that,
having to base a decision today on interest rates,
you've got to anticipate what the world is going to be like in 18 months time.
Now clearly that's a very difficult call to make.
So the monetary policy decision makers in a particular country,
will have to weigh up all types of evidence.
Evidence about consumer confidence,
business confidence, expectations of the general public about inflation,
how this is going to impact wage negotiations if there
was perhaps some collective bargaining by unions,
and many other factors besides.
So you can perhaps start to appreciate the complex world in which we live,
yet for things like monetary policy setting,
indeed fiscal policy setting,
the tax and spend decisions of a government,
that's going to be decisions taken in the present but
with a far reaching consequences into the future.
If one considers for example,
the national debt levels of a particular country.
And then, the market's reaction to whether these debt levels are sustainable or not.
You've only got to look at the Eurozone post,
the 2008 economic and financial crisis,
or the debt levels of particular countries sustainable or not?
I mean, now you'll hear a lot in the media about Brexit.
Prior to that referendum vote,
there was a lot of talk in the media about Grexit.
Would Greece be ejected from the Eurozone?
Well, some still some major problems within the Eurozone
that perhaps have come- dropped out of the main headlines,
but many of those problems are still at present.
So there's huge uncertainties in the macro economy and of course,
that's a heavily tied in with political decision making as well.
So uncertainty in the news.
Going forward, I'm a news junkie and I really implore you to
be abreast and up to speed with our current affairs.
And whenever you come across articles,
look for that word uncertainty and think about things.
What are the key variables which are deemed to be uncertain in those particular articles?
And of course, the uncertainty about those variables are likely to have
no common impacts on other variables as well.
So probability and statistics could be a very dry discipline indeed.
However, uncertainty is a real world phenomenon.
And decisions taken by politicians around the world,
are clearly going to have consequences for the everyday lives of individuals.
And of course, politicians are having to take
decisions under huge amounts of uncertainty.
So this does really bring home the importance of probability and statistics and
hence a strong understanding of probability and
statistics to really appreciate the concept of decision making under uncertainty.
Ознакомьтесь с нашим каталогом
Присоединяйтесь бесплатно и получайте персонализированные рекомендации, обновления и предложения.
Coursera делает лучшее в мире образование доступным каждому, предлагая онлайн-курсы от ведущих университетов и организаций.
© Coursera Inc., 2019 Все права защищены.
