0:00

Once we have indicated or we have highlight some

Â issues rise to the quality of composite indicators.

Â We are going now, just as a help for you,

Â a sort of overall quality of what we would like to have from a composite indicator.

Â These are basically five issues that are described in the slide we are showing you now.

Â Basically, these issues are the following: first of all, a composite indicator,

Â the mathematical model that this represent in it,

Â must be a good representation of reality.

Â Second, the indicators that are present in the model,

Â they must take large or small values.

Â It is much more interesting to have

Â indicators that are very large and very small values than

Â indicators that are close to zero because basically this variability is going to

Â help them to understand the final evolution of the composite indicator.

Â It's important to have a good direction with enough strength.

Â Third point, which is also important,

Â is the relative importance of the different partial indicators. What do I mean by this?

Â This is basically referred to the system of weights.

Â Weights need really to indicate which is the importance of

Â these partial indicators in the final result of the composite indicators.

Â This is really a crucial issue in terms of the choice of

Â composite indicators and we will take rather quite a lot of time

Â in the next sections of the course just to describe how

Â to elaborate the weights and what is

Â the importance of defining the weights in a proper way.

Â There is also an important issue related to

Â the mathematical aggregation we are having in mind.

Â Probably with the discussion we had before

Â about the ordinality and the cardinality questions,

Â you realize already how important are the correct definition

Â of the mathematical expressions in the composite index and

Â the different possibilities we have by assuming

Â cardinality or ordinality and the consequences of that.

Â Finally, we have not discussed yet about possibly one of the most important issues

Â within the choice of or the elaboration of composite indicator which are the data.

Â Data, if we go now to the next slide,

Â are always difficult and always hard to work with.

Â Why? There is, first of all,

Â a first choice we need to make between quality and accuracy.

Â Sometimes when building up composite indicators,

Â we would like to have the best data in the world. What does it mean?

Â We want data that are available soon.

Â We want data of high quality and we

Â want to understand really what is going on in the production of this data.

Â Unfortunately, this does not happen many times and

Â usually we have to choose or we have to select data not

Â by its accuracy or its quality but only because

Â this type of data are available at that time we are

Â going to have to work the composite indicator.

Â Let me give you a very simple example that can clarify this.

Â Imagine we are designing a composite indicator of economic activity,

Â sort of leading economic indicator,

Â and we want to have available result for next month.

Â Unfortunately, of the composite of

Â the partial indicators we have already designed to be a part of this composite indicator,

Â some of them are not available for next month.

Â What can we do then? Do we need to abandon the idea of creating a composite indicator?

Â Maybe this is not just the case,

Â maybe what we have to do is to select another data issue

Â or another data that are not of such best quality we would like to have,

Â but at some point it's useful for our purpose.

Â Where do the data come from?

Â Basically, we have two sources of data in our analysis.

Â First, we could get data from experiments.

Â Usually, composite indicators in social sciences are not

Â that lucky as in experimental sciences so we cannot,

Â in social science, construct or design experiments.

Â There is, of course you know,

Â a branch of economics,

Â the number experimental economics that does this,

Â but it's not generalized.

Â And of course we cannot hope that we are going to have the source of data

Â from many different dimensions that we need to.

Â If this is, unfortunately the case,

Â then we need to go to a second source of data which is what we call the survey data.

Â Survey data are coming either from private institutions or from public institutions.

Â Of course, some private institutions have got a lot of reputation and we

Â definitely can take advantage of their work and use

Â these data for our elaboration of the composite estimators.

Â But, in general, our recommendation is to take data from public institutions.

Â Why? Basically because, usually public institutions when they produce data,

Â they are sealed, they are stamped with the name of official statistics.

Â An official statistics has some sort of properties or

Â conditions that make them much interesting and much reliable to work with.

Â Just to have a look to the point I'm talking to you about,

Â please go to the next slide.

Â We have taken the job to summarize

Â what we call the European Statistics Code of Practice.

Â We have tried to summarize the European Statistics Code of Practice. What is this?

Â This is a code that was approved by the European Commission and is

Â actually a sort of benchmark of quality of public statistics.

Â We basically distinguish among

Â three different dimension on these public statistics on this code.

Â What has been called the institutional environment,

Â what has been called the

Â statistical processes and the dimension finally of statistical output.

Â In the next slide, you will find what are the main issues related to

Â institutional environment but its not really of our interest here in this course.

Â I would like to focus your attention basically on the two other dimensions.

Â For this, if you please go to the next slide,

Â we would like to point out that for statistical processes,

Â the European Commission points out the attention on four different issues.

Â First of all, sound methodology.

Â The methodology that it has been designed to produce public statistics,

Â official statistics must be well-detailed and must be technical enough.

Â Second, there must be

Â the corresponding appropriate statistical procedures in terms of sampling design,

Â in terms of inference.

Â Third, there must not be excessive burden for the representatives.

Â That is, the official statistical office

Â cannot ask you 20 times in differing ways for the same data.

Â If the official institution has already one data from you in this direction,

Â he should take this, not take the others.

Â Finally, there must be an appropriate relationship with the cost of the operation.

Â Now, let us go to the next slide where we show you

Â what are these European Code of Practice for the statistical output.

Â This is mainly the most interesting part in terms of

Â elaborating the composite indicator because there

Â is where we will see what are

Â the appropriate characteristics of data we need to use for these composite indicators.

Â So basically, the data must be relevant.

Â Data must be of interest of the public opinion of the different European Union states.

Â Second, the data must be accurate and must be reliable.

Â These two words probably they are already familiar to you and I mentioned

Â them at the beginning of this section of

Â the course related with the composite indicators.

Â I will repeat them again many times because they

Â are crucial when we are talking about production of data.

Â There is a third issue that is also very important,

Â which is time and punctuality of the statistic product.

Â If I have a compromise to obtain a leading economic indicator

Â for next month and the national bureau of

Â statistics of my country is going to produce

Â some indicator I need for this composite indicator,

Â for this leading economic indicator,

Â I need to have it on time and this is the compromise the statistical offices is made.

Â Finally, an important issue is also the transparency and the accessibility

Â of the data and this is already something you understand why.

Â So then as a summary of all the section,

Â I would like to point out basically three items that you should keep in mind.

Â What do we want from a good composite indicator?

Â First, we want to have good data to feed it.

Â Second, we want to have appropriate indicators.

Â And finally, we want to have an economic framework,

Â statistical economic framework, that makes somehow indicators fit in the whole frame.

Â