Date

28 Apr 2017

Attendees

Agenda

1) Use Case reminder

2) Where we are on our road map.

3) Open Action Items

4) JIRA Issues Review - https://jira.edmcouncil.org/projects/IND/issues/IND-17?filter=allopenissues

5) Todays content discussion.

SMIF OWL-UML

SKOS

RDF/S

6) For next week.

Proceedings:

Reviewed the latest version of the statistical quantities that we've been working on - (1) need to relate standard deviation to variance, (2) need to revise the definition of mean per http://www.statcan.gc.ca/edu/power-pouvoir/glossary-glossaire/5214842-eng.htm#p but without the term "arithmetic" and then create the two subclasses for arithmetic and geometric mean.

Reviewed related definitions around median and mode – need to understand whether or not it is important to add these for the purposes of most of the banks participating in FIBO.

Reviewed the definition of market spread – need to understand whether that should be a child of difference or variance.

Once we've addressed the issues above, can close IND-17.

Also reviewed outstanding actions with respect to common interest rates and market indices – requested input from DB, Credit Suisse, and SS. An initial pointer from Gareth Isaac (DB) for the interest rates included in FpML is http://www.fpml.org/coding-scheme/floating-rate-index-2-0.xml. From Mike Pool, the suggestion with respect to market indices is to address parameterization of the indices – by vendor, by product, by market, by sector, by commodity, etc., for example to enable us to model the various kinds of indexes that traders focused on specific sectors use, such as the DJ Transportation Average. In general we should at least cover the ones that are used in financial news, including DJIA, S&P 500, NASDAQ, FTSE, and then some examples using the parameterization.

Also reviewed Pete's open issue with respect to changing certain has value restrictions to someValues from – need to either honor his pull request or make a similar change using our standard process.

Decisions:

Action items

Lucy Opsitnik (Unlicensed) sent definition of "estimate":

Definition of Estimation (and estimate), from http://www.statcan.gc.ca/pub/12-587-x/12-587-x2003001-eng.pdf, which could be a source for other needs. Estimation is the means by which the statistical agency obtains values for the population of interest so that it can draw conclusions about that population based on information gathered from only a sample of the population. An estimate may be a total, mean, ratio, percentage, etc.

Page 119 of the above document states, "Summary measures of the population such as totals, averages and proportions are typically estimated for a wide range of characteristics collected from the sample units." Elisa, this might be the most straightforward way to define estimate, as a "summary measure of a population..."

Definition of Estimate from OECD: In the strict sense, an estimate is the particular value yielded by an estimator in a given set of circumstances. (OECD glossary of statistical terms: https://stats.oecd.org/glossary/detail.asp?ID=5059).

If you send the deck with all the definitions I'll forward it to our methodology team here.

Browser not supported