SAMPLING AND ESTIMATION FOR ESTABLISHMENT SURVEYS
A two-day short course sponsored by the Joint Program in Survey Methodology

 

MAY 6-7, 2008
Presented at The Inn & Conference Center, Adelphi, MD

PHILLIP KOTT
Research Statistician

RICHARD VALLIANT
Senior Research Scientist, Survey Research Center, University of Michigan

COURSE OBJECTIVES

This short course provides an overview of sampling and estimation in surveys of establishments. It will examine the types of frames used, population parameters that are estimated, sample allocation methods, and estimation techniques.  Attendees will benefit most who have some familiarity with sampling applications and theory.

Practical exercises during the short course reinforce the lecture materials and handouts. Students should bring scientific calculators.

THE INSTRUCTORS
Phillip Kott
is a Research Statistician who received his Ph.D. in Economics from Brown University in 1979. He has worked on establishment surveys for over 25 years both as an economist and a mathematical statistician. At various Federal government agencies, he documented and expanded the mathematical formulae used in major survey programs and taken the lead in developing new sampling design and estimation strategies that make more efficient use of auxiliary information. He was an organizer of the first International Conference on Establishment Surveys and a co-editor of the book Business Survey Methods. He is currently an Associate Editor for both the Journal of Official Statistics and Survey Methodology.

Richard Valliant is Senior Research Scientist in the Survey Research Center, University of Michigan. He received his Ph.D. in Biostatistics at Johns Hopkins University in 1983 and has 30 years of experience in sample design and estimation using data from complex surveys. He is currently an Associate Editor of Survey Methodology and the Journal of Official Statistics and has been an associate editor of the Journal of the American Statistical Association. He is a fellow of the American Statistical Association and a faculty member of the University of Maryland and Johns Hopkins University. He is a co-author of the text, Finite Population Sampling and Inference: A Prediction Approach.

TENTATIVE SCHEDULE

Day 1
8:00 - 9:00 Check-In and Continental Breakfast

9:00 - 10:30

Introduction to Establishment Surveys
What are the features of establishment surveys and how do they differ from those of household surveys?
Types of data collected—production, sales, labor force, prices
Frames—lists, area, multiple frames
     Dynamic nature of frames—births, deaths, splits, mergers
Estimation Goals—cross-sectional estimates, longitudinal estimates, domains

10:30 - 10:45

Break
10:45 - 12:30 Stratification for Single Purpose and Multipurpose Sample Designs Types of strata—geography, industry, size
The uses of stratified simple random sampling
Determining sample sizes—full population estimates, domain estimates
Adjustments for sample losses (ineligible units, nonresponse, deaths)
Allocation routines—accounting for costs, stratum variances, precision goa

12:30 - 1:30

Lunch

1:30 - 3:00

Probability Proportionate to Size and Other Unequal Probability Sampling Schemes
The whys (models) and hows (systematic pps sampling, Poisson sampling, etc.)
Brewer and maximal Brewer allocation

3:00 - 3:15

Break

3:15 - 4:30

Sampling in Phases and Over Time
Two phase sampling
Overlap control
Rotating panels, permanent random numbers

 

Day 2
8:00 - 9:00 Check-In and Continental Breakfast

9:00 - 10:30

Ratio, Regression, and Other Calibration Estimators
Role of models in selecting estimators
Randomization versus model bias and randomization consistency
Expressing the ratio estimator as a regression estimator and both as calibration estimators
Should all calibration weights be positive? No less than one?

10:30 - 10:45

Break
10:45 - 12:30 Variance Estimation
Horvitz-Thompson, Yates-Grundy-Sen, and Hartley-Rao Estimators
Linearization techniques
Replication techniques

12:30 - 1:30

Lunch

1:30 - 3:00

Nonresponse Adjustment
Reweighing
Imputation—methods (hot deck, ratio, regression), specialized variance  estimators (adjusted jackknife and balanced repeated replication, multiple imputation).

3:00 - 3:15

Break

3:15 - 4:30

Other Issues
Non-probability samples
Outliers
Multiple frame and composite estimators

FELLOWSHIPS
The Joint Program in Survey Methodology strives to increase the number of survey professionals from groups traditionally under-represented in the field. As part of this effort, a limited number of competitive fellowships are available to African-Americans, Latinos, Hispanic Americans, and Native American Indians for the short course.
The registrant must be a US citizen or permanent resident. The applicants should submit:

  1. A 500-word essay describing their reasons for wanting to attend this short course and how their participation will enhance their chosen career path. The essay should indicate the applicant’s background (i.e. African-American, Latino, Hispanic American, or Native American Indian).
     

  2. A recommendation written by a person knowledgeable about the applicant’s aptitude and interest in survey methodology.
     

  3. The course online registration form.

If you are applying for a fellowship, please be certain to register early. Applications are due before April 7, 2008. JPSM will evaluate the applications and inform the successful applicants by April 14, 2008. The fellowship covers the registration fee, materials to be distributed during the course and the JPSM group continental breakfasts, lunches and breaks.

JPSM CITATION PROGRAMS 
The citation programs are built around the JPSM short courses. The JPSM Citation in Introductory Survey Methodology is designed to provide the working professional and interested students with state-of-the-art knowledge about current principles and practices for conducting complex surveys combined with practical skills of day-to-day utility. The JPSM Citation in Introductory Economic Measurement is designed for professional staff requiring a grounding in the principles and practices of economic measurement. Completion of the citation programs involves taking a semester-length JPSM credit-bearing course and eight JPSM short courses, of which four are specified core courses. For information on the Certificate and Citation Programs visit the website at http://www.jpsm.org or call 301-314-7911.

LOCATION
The course will be held at the University of Maryland Inn and Conference Center, College Adelphi, Maryland. It is located on University Boulevard at Adelphi Road, Route 193, adjacent to the College Park campus of the University. Convenient parking in the UMUC garage is included in the registration fee. For hotel room reservations, call the Conference Center at (800) 727-8622.

FEES & COURSE MATERIALS
The registration fee is $810. Full-time university students (with a supervising faculty advisor’s signature) and employees of JPSM sponsor/affiliate organizations are eligible for a reduced fee of $600. Lunch and refreshments are included in the fee. Participants will be provided with a notebook containing detailed course notes.

REGISTRATION
Online registration is required. Confirmation of registration and further instructions will be sent after the registration form has been processed. Registration is not firm until you receive a confirmation letter. Payment by credit card is required. Payment may be made online following receipt of the confirmation letter using the student's confirmation number. Please note your confirmation number. The registration deadline is April 25, 2008. Payment is required by April 25, 2008 or the registration will be cancelled.

Please notify JPSM as soon as possible if you need to cancel your registration. You will receive a full reimbursement if you cancel on or before April 25, 2008. If you cancel during the period April 28 - May 1, 2008, you will be charged a $100 administrative fee; the remainder of your course fee will be reimbursed. No reimbursements will be made for cancellations received on or after May 2, 2008. Minority Fellowship essays and letters of recommendation are due April 7, 2008 and should be faxed or mailed to the address below. Fellowship winners will be notified April 14, 2008. Questions about this course should be directed to (301) 314-7911, Fax: (301) 314-7912, JPSM, University of Maryland, 1218 LeFrak Hall, College Park, MD 20742.

INQUIRIES
Questions about this course should be directed to (301) 314-7911, Fax: (301) 314-7912, JPSM, University of Maryland, 1218 LeFrak Hall, College Park, MD 20742. http://www.jpsm.org.

EMAIL: jpsmshort@isr.umich.edu .
JPSM HOME PAGE: http://www.jpsm.org Click on "Short Courses".
COURSE LISTS, INFORMATION, REGISTRATION, PAYMENT AND CANCELLATION: 
http://projects.isr.umich.edu/jpsm/
SPONSOR AFFILIATE LIST:
https://projects.isr.umich.edu/jpsm/sponsorlist.cfm


Primary funding for JPSM is from the Interagency Council on Statistical Policy