Challenges for the Modern Economist

Lars Vilhuber
2016-05-18

Challenges for the Modern Economist

Big data (but what is it really?)
Data availability and accessibility (or its disappearing act)
The conundrum of confidentiality and privacy
Replicability (because of all of the above)

Caveats

I don't run my own surveys
I occasionally create official statistics (bias!)
I did my Ph.D. in the 1990s

Big data

or rather…

Alternate data sources

What is "big" data?

Big data is:

8 GB?
7.5 TB?
309.3 million people, measured once?
150 million people, measured 80 times?
16,721,787,543 tables?
100 countries, 5-15 times?
19.3 billion records / 50TB?
112 weekly data points?

Representative big data is:

I can't run it on my laptop
2 years worth of stock trades?
10 questions / population/ 1 country?
3 variables for 98% of one country's workforce?
30+ variables for same?
1% samples of 100 countries' censuses?
10% of tweets?
1 variable for 10% of Twitter users?

What is "big" data?

8 GB? I can't run it on my laptop, my RA might
7.5TB? 2 years worth of stock trades
309.3 million people, measured once? 10 questions on US decennial census
150 million people, measured 80 times? LEHD US linked employer-employee data
16,721,787,543 tables? QWI (derived from LEHD)
100 countries, 5-15 times? *IPUMS
19.3 billion records reduced to 112 weekly data points? = 10% of tweets over 24 months, UM Economic Indicators from Social Media (now up to twice that)

This brings up the question: How do we collect data?

How do we collect data?

	Surveys	Administrative	Organic Data
Aim	Informational	Administer programs	… something else (Twitter?)
Who	Trained professionals designing, fielding, analyzing surveys	Trained professionals running a bureaucracy, collecting necessary data	Trained professionals optimizing revenue
Core	Well established science, defining population, frame	Definition of population, frame critical, but ex-post	Population and frame often unclear
Stats	Primary purpose is to create statistics	Statistics about populations is secondary purpose	Public statistics at best incidental, possibly self-serving

New challenges

treating admin/organic as a noisy data source, different from surveys
designing administrative data collection with statistics in mind
handling large data flows in commonly accepted ways
novel confidentiality issues <!– - reconceptualizing multiciplity of data sources –>

Data collection in surveys

“Respondent load should always be considered when planning a statistical collection and there should be policies and practices in place to manage relationships with respondents. The aim should always be to keep reporting load to the minimum and to maintain the high quality of collections.”

Australian National Statistical Service

Data collection in administrative data

Incentives

Clients cannot get service without filling form
Coercion

Monsters

Data collection discrepancies

Survey

where did you work (precise lat/long) in the past 10 years?
who did you work for in the past 10 years?

Administrative

IRS Form W4, line 8
CRA-ARC T4, box 54

Data collection discrepancies

Eliminating discrepancies: