GDT -- Support Statement Part B 12-20-2017 v5

SUPPORTING STATEMENT

UNITED STATES INTERNATIONAL TRADE COMMISSION QUESTIONNAIRE

Inv. Nos. 332-562 and 332-563

Global Digital Trade 2: The Business-to-Business Market, Key Foreign Trade Restrictions, and U.S. Competitiveness; and Global Digital Trade 3: The Business-to-Consumer Market, Key Foreign Trade Restrictions, and U.S. Competitiveness

Part B-Collection of Information Employing Statistical Methods

1. Response universe, sample sources, and sampling strata

Survey objectives

In a letter dated January 13, 2017, the U.S. Trade Representative (USTR) directed the Commission to produce two reports that analyze the impact of regulatory and policy measures in key foreign markets on (1) the ability of U.S. firms to develop and/or supply digital products and services abroad, and (2) the competitiveness of U.S. firms engaged in the sale of digital products and services, as well as on international trade and investment flows associated with digital products and services. The USTR specified that the Commission’s report be based on a review of available data, including a survey of U.S. firms in selected industries particularly involved in digital trade.

Respondent universe

The respondent universe includes all companies in industries that are particularly involved in the development and supply of digitals products and services. The USITC has identified 52,863 such firms for its sampling frame, of which 13,000 will be sampled. The sampling unit is the firm rather than the establishment.

To examine the effect of policy and regulatory measures, it is necessary to include a broad list of firms that are currently doing business in foreign markets, as well as those that are not, but are potentially interested in doing so. As a result, the response universe will include firms with a potential for digital trade and not only firms that are currently facing these measures in certain markets.

The potential respondent universe represents the sum of firms, net of duplicative records, identified in the Bureau van Dijk’s Orbis database in industries likely to engage in digital trade, membership lists from relevant associations, and firms that are registered with the EU-US Privacy Shield. These industries include selected sectors based on NAICS as discussed below.

Because the focus of this study is on firms with international presence and these tend to be larger than the average firm, the response universe was restricted to firms with 20 or more employees or more than $7.5 million in revenue, with some exceptions.

Sample design

Survey respondents will be selected through a stratified random sampling methodology that stratifies firms through a combination of industry and size. There will be 33 strata by industry/size. Size cutoffs were determined by the Small Business Association’s size standards by NAICS. Firms with neither employment nor revenue data have been combined into their own strata by industry.

Industries comprise the following 10 sectors: (1) Online commercial and retail services, and payment services, (2) telecommunications, (3) web, software, and hardware services, (4) transport and delivery services, (5) media and publishing, (6) finance, (7) insurance, (8) travel and hospitality, (9) other selected services, (10) manufacturing.¹

Table 1 presents the sampling frame—the population of firms in each stratum. Table 2 presents the sample size for each stratum. Thirteen thousand (13,000) firms will be sampled.

Based on results of past surveys conducted by the Commission for other investigations, we expect the response rate to range from 40–60 percent,² which would result in 5,200–7,800 surveys received from the sampled companies (assuming 13,000 surveys sent out). Responses in previous and ongoing USITC surveys have not differed significantly by firm size or across industries. Thus, a uniform response rate has been assumed for all strata.

TABLE 1 Sampling frame – Population per stratum

Industry	Small	Medium/ Large	Very large	Unknown size	Total
Online commercial and retail services, and payment services	244	161	44	197	646
Telecommunications	935	75	121	557	1,688
Web, software, and hardware services	5,154	1,220	708	5,314	12,396
Transport and delivery services	1,555	1,359	943	3,453	7,310
Media and Publishing	2,099	462	372	1,410	4,343
Financea	—	1,357	145	—	1,502
Insurancea	—	1,362	45	—	1,407
Travel and hospitality	2,069	1,607	507	1,828	6,011
Other selected services	3,104	4,754	849	4,037	12,744
Manufacturingb	4,816				4,816
Total					52,863

^a Within the finance and insurance industries, small firms and those with an unknown size will not be surveyed as it is unlikely that they will be within the scope of the request.
^b Within the manufacturing industry, only firms that have an indication of having foreign affiliates, and those with 10,000 or more employees, are included in the population.

TABLE 2 Number of firms in the sample by stratum

Industry	Small	Medium/ Large	Very large	Unknown size	Total
Online commercial and retail services, and payment services	70	161	44	197	472
Telecommunications	100	69	121	366	656
Web, software, and hardware services	2,113	1,220	708	531	4,572
Transport and delivery services	75	204	802	345	1,426
Media and Publishing	100	85	372	456	1,013
Financea	—	355	145	—	500
Insurancea	—	400	45	—	445
Travel and hospitality	139	241	431	366	1177
Other selected services	110	713	722	404	1,949
Manufacturingb	790				790
Total					13,000

^a Within the finance and insurance industries, small firms and those with an unknown size will not be surveyed as it is unlikely that they will be within the scope of the request.
^b Within the manufacturing industry, only firms that have an indication of having foreign affiliates, and those with 10,000 or more employees, are included in the population.

2. Collection of information employing statistical methods

1. Statistical methodology for stratification and sample selection

A stratified sample is being implemented for this collection. The goal of the stratification scheme is to develop a set of strata that minimizes the variance of responses (such as level of employment and type of activities) within each stratum. Because no pro-forma reliable data exist on the size and scope of the number of firms that are engaged in digital trade, the minimum size of firms included in the population and the classification of size within industries for the stratification scheme were based on information gathered from industry representatives and the best judgment of USITC experts.

Because some firms had no data for both the number of employees and revenue, the approach to sampling could not rely on either of these variables. Thus, the sample size for each stratum were calculated using Cochran’s sample size formula for categorical data along with an oversampling correction with an anticipated return rate of 50 percent.³ The sampling rate by stratum was then adjusted to sample at least 10 percent of each stratum.

The sample size for stratum h is calculated by the formula

where is the t-value at for two tails, as an estimate for variance, and as an acceptable margin of error for categorical data.

The formula for Cochran’s oversampling correction is

where N is the size of stratum h.

2. Estimation Procedure

Survey estimates will be based on weighted data. The weighting procedure will incorporate a sample selection weight, a nonresponse adjustment factor, and if necessary, a poststratification weighting factor. There is an equal probability of selection within each stratum.

• Sample selection weighting: Because the sampling rates are based on two criteria, as discussed above, the selection weight factor will account for both the probability of selection within a particular industry and size, and any oversampling of firms.

• Nonresponse adjustment: The nonresponse adjustment factor is designed to attenuate bias due to differential response rates. This adjustment will be calculated using firm characteristics, if warranted. See the section below on accuracy and reliability of information collected for further discussion.

• Poststratification weighting: If necessary, a poststratification weighting factor will be used to attenuate bias due to sample frame noncoverage, overcoverage, or omissions. Population information from Census data, such as the number of firms in each NAICS industry and in each size category (organized by number of employees), may be used to conduct poststratification. Although the best effort has been made to obtain a representative sample, the distribution of firms across industries is not known with certainty in advance.

The general weighting formula can be represented as

, (1)

where is the sample selection weight for stratum h, is the nonresponse adjustment factor for stratum h, and is the poststratification weight of stratum h. is the weight applied to all observations in stratum h. This formula may be adjusted to include a firm-specific weighting component if non-response is determined to be related to factors aside from the factors used to design the strata.

Standard estimation procedures will be used as in Heeringa et al (2010).⁴ For example, the formula used to estimate the population attribute of interest is found in equation 2. Per standard notation, the total estimate for industry , , from a stratified random sample, is given by

, (2)

where h denotes an individual stratum, N_h equals the population of stratum h, and equals the average of the attribute of interest of the sampled items in stratum h. For example, could represent the average amount of revenue within each stratum.

The variance estimate for sampling without replacement is given by

(3)

where s² equals the standard deviation of the attribute of interest within stratum h, and n_h is the sample size for stratum h.

3. Degree of accuracy needed for the purpose described in the justification

A sample size of 13,000 is needed to achieve estimates of +/- 5 percent at 90 percent confidence. It is expected that it will be feasible to produce statistically significant results for the majority of survey items at the aggregate level at a 90 percent confidence level, both for the continuous and categorical variables. For example, table 3 provides the maximum margin of error for a binary question, given alternative response rates.

TABLE 3 Margin of error for 90 percent confidence interval

	Response rates, percent
Measure	40	50	60
Number of respondents	5,200	6,500	7,800
Standard error, percent	0.69	0.62	0.57
Margin of error, percent	1.14	1.02	0.93

Note: This assumes a maximum margin of error of 50 percent for a binary question.

4. Unusual problems requiring specialized sampling procedures

No unusual problems were encountered.

5. Any use of periodic (less frequent than annual) data collection cycles to reduce burden.

This data collection is currently only intended to occur once, and therefore will not be repeated on a periodic basis. As such, the total recurring annual cost burden is zero.

3. Methods to maximize response rates and deal with non-response

a. Maximizing response rates

Commission staff will employ several techniques to increase the response rates of questionnaire recipient firms. Recipients will receive separate notices that (1) notify them that their firm was selected for the survey, (2) direct them to complete the survey, and (3) remind them, if necessary, to complete the survey before the deadline. Once the submission deadline has passed, firms that still have not responded will receive an additional reminder. Each of these communications will include a phone number and email address of a person who can help firms with filling out the questionnaire or answer their questions regarding the survey and/or study. Commission staff may also contact firms directly, via phone or email, to urge them to complete the survey and to answer any questions they may have regarding this information collection or study, in general. Commission staff may also contact firms, via phone or email, to correct information or fill in incomplete responses, or solicit additional information about a response. The burden associated with follow up calls or emails is included in the total response burden amount.

In addition to pre-contact and follow-up, the questionnaire itself has been designed to be as clear and succinct as possible to gather the specific material requested by the USTR. (See discussion of testing below.) This clarity and brevity should reduce burden and improve response rates. The questionnaire will clearly point out that firms are obligated by law to respond. Finally, the ability to access, fill out, and submit the survey electronically may also increase response rates.

b. Accuracy and reliability of information collected

The sample methodology has been designed to be as accurate and reliable as possible, based on Commission experience in past surveys. The sampling frame has been chosen to include firms in industries that are providing and selling digital products and services in foreign markets.

Response rates in similarly scoped USITC surveys have recently approached 60 percent. The USITC will examine survey responses to detect and correct for any non-response bias. The team will first examine conditional response rates for groups of firms based on characteristics available in the data frame that are hypothesized to impact outcomes of interest. These may include variables such as firm size, industry, NAICS code, or location. Any differences in response rates can be further investigated through logistic regression analysis, using firm characteristics as predictors, and whether or not a recipient responded to the survey as a binary outcome. If the results of the logistic regression indicate that one or more of the characteristics investigated above affects the propensity of a survey recipient to respond to the survey, then those characteristics will be examined to determine whether they are associated with differences in the outcome variables under study, across the dataset of survey responses collected. If any sources of non-response bias are found, they can be controlled for by the development of weights, which can then be used in concert with weighting based on population stratification, in the extrapolation of results to the entire population.

The Commission expects that all sampled information will yield reliable data that can be generalized to the universe studied.

4. Tests of procedures or methods to minimize burden or improve utility

The Commission sought comments on the questionnaire with industry representatives of several relevant industries through field testing. These representatives provided feedback in areas such as availability of data, reporting burden, product coverage and definitions, clarity of instructions, disclosure, and reporting format. The Commission also went through a period of cognitive testing to make sure the questions, and the intent behind them, are clear. See part A for the comments field and cognitive testers made and the subsequent changes made to the questionnaire.

In addition to field testing, the questionnaire has been made available for public comment. Notice of the draft questionnaire was published in the Federal Register. It has also been extensively reviewed within the Commission. Industry analysts and economists have reviewed the questionnaire to ensure it requests information needed to adequately answer questions posed in the study while imposing a minimum burden on the responding businesses.

The sampling methodology and procedures in this survey are quite similar to those in prior USITC survey work. Prior studies, for example, also have had populations drawn from Orbis; have also stratified by industry and size; and have used similar methods of survey distribution and data collection. Although the USITC has not specifically tested the methodology and procedures of the current Global Digital Trade survey, prior surveys have provided implicit tests of its practicability and utility.

5. Contact information

Collection and analysis of the data will be the responsibility of the Office of Analysis and Research Services, the Office of Economics, and the Office of Industries within the Commission. The project leaders are Dan Kim and Alissa Tafti (Inv. No. 332-562) and Ricky Ubee and Christopher Robinson (Inv. No. 332-563). The survey team can be reached by email at [email protected]. If you prefer to contact them by phone, please call 202-205-3342 or 202-205-3225.

Industries and their NAICS code composition

Online commercial and retail services, and payment services

454110	Business to business electronic markets
454111	Electronic shopping
454112	Electronic auctions

Telecommunications

517110	Wired telecommunications carriers
517210	Wireless telecommunications carriers (except satellite)
517911	Telecommunications resellers
517919	All other telecommunications

Web, software, and hardware services

511210	Software publishers
518210	Data processing, hosting, and related services
519130	Internet publishing and broadcasting and web search portals
541511	Custom computer programming services
541512	Computer systems design services
541513	Computer facilities management services
541519	Other computer related services

Transport and delivery services

481111	Scheduled passenger air transportation
488320	Marine cargo handling
488330	Navigational services to shipping
488390	Other support activities for water transportation
488510	Freight transportation arrangement
492110	Couriers and express delivery services

Media and publishing

511110	Newspaper publishers
511120	Periodical publishers
511130	Book publishers
511199	All other publishers
512110	Motion picture and video production
512120	Motion picture and video distribution
512191	Teleproduction and other postproduction services
512199	Other motion picture and video industries
515120	Television broadcasting
515210	Cable and other subscription programming
519110	News syndicates
519190	All other information services

Finance

522110	Commercial banking
522120	Savings institutions
522190	Other depository credit intermediation
522210	Credit card issuing
522220	Sales financing
522293	International trade financing
522294	Secondary market financing
522298	All other nondepository credit intermediation
522320	Financial transactions processing, reserve, and clearinghouse activities
523110	Investment banking and securities dealing
523120	Securities brokerage
523130	Commodity contracts dealing
523210	Securities and commodity exchanges
523910	Miscellaneous intermediation
523930	Investment advice
523991	Trust, fiduciary, and custody activities
523999	Miscellaneous financial investment activities
561450	Credit bureaus

Insurance

524113	Direct life insurance carriers
524114	Direct health and medical insurance carriers
524126	Direct property and casualty insurance carriers
524128	Other direct insurance (except life, health, and medical) carriers
524210	Insurance agencies and brokerages

Travel and hospitality

532111	Passenger car rental
561510	Travel agencies
721110	Hotels (except casino hotels) and motels

Other selected services

532230	Video tape and disc rental
541310	Architectural services
541330	Engineering services
541380	Testing laboratories
541430	Graphic design services
541611	Administrative management and general management consulting services
541618	Other management consulting services
541712	Research and development in the physical, engineering, and life sciences (except biotechnology)
541810	Advertising agencies
611420	Computer training

Manufacturers with a presence in a foreign market, and those with 10,000+ employees

31-33 Manufacturing

1 Although the agriculture and natural resources industries are not explicitly covered, they are selectable as primary industries in the questionnaire for the purposes of complete industry coverage in question 1.3.

2 The Commission anticipates a higher response rate than in previous surveys based on the use of a web-based questionnaire, which should reduce burden and be easier to respond to. However, since this collection method has not been used by the Commission in the past, a more conservative response rate was used in the calculation of sample size to avoid under sampling.

3 J. Bartlett, J. Kotrlik, and C. Higgins. “Organizational research: Determining appropriate sample size in survey research,” Information Technology, Learning, and Performance Journal 19, no. 1, 2001, 43.

4 S. Heeringa, B. West, and P. Berglund, Applied Survey Data Analysis, CRC Press, 2010.

14