State of Connecticut Home Follow Us on FacebookFollow Us on TwitterFollow Us on Flickr
Connecticut Department of Labor Home Occupational Employment & Wages Home
Home About Publications FAQ Glossary Contact
State of Connecticut - 2017 Occupational Employment & Wages (OES)
  STATE OF CONNECTICUT - OCCUPATIONAL EMPLOYMENT & WAGES METHODOLOGY 1st Quarter 2017  
OES Wages Home |  Scope | Response | Concepts | State Data | Estimation Methodology | Reliability of Estimates

SCOPE

The Occupational Employment Statistics (OES) survey is a semi-annual survey measuring occupational employment and wage rates for wage and salary workers in nonfarm establishments. In November 2003, the OES survey changed from an annual survey of 7,000 establishments to a semiannual survey of 3,500 establishments. Currently, the OES survey samples 3,000 establishments in May and November of each year and, over 3 years, contacts approximately 18,000 establishments. The full three-year sample allows the production of estimates at fine levels of geographic, industrial, and occupational detail.

The OES survey covers all full-time and part-time wage and salary workers in nonfarm industries. The survey does not include the self-employed, owners and partners in unincorporated firms, household workers, or unpaid family workers.

In 1999, the OES survey began using the Office of Management and Budget's occupational classification system, the Standard Occupational Classification system (SOC). The OES survey categorizes workers in one of about 800 detailed occupations. Together, these detailed occupations comprise 22 major occupational groups. The major groups of the SOC system are as follows:

  • Management occupations
  • Business and financial operations occupations
  • Computer and mathematical occupations
  • Architecture and engineering occupations
  • Life, physical and social science occupations
  • Community and social services occupations
  • Legal occupations
  • Education, training, and library occupations
  • Arts, design, entertainment, sports, and media occupations
  • Healthcare practitioners and technical occupations
  • Healthcare support occupations
  • Protective service occupations
  • Food preparation and serving related occupations
  • Building and grounds cleaning and maintenance occupations
  • Personal care and service occupations
  • Sales and related occupations
  • Office and administrative support occupations
  • Farming, fishing, and forestry occupations
  • Construction, and extraction occupations
  • Installation, maintenance, and repair occupations
  • Production occupations
  • Transportation and material moving occupations
  • Military specific occupations (not surveyed in OES)

RESPONSE

The statewide response rate for the May 2016 survey was 63 percent for sampled establishments, covering 75 percent of sampled employment.

top

CONCEPTS

Most of the data were collected electronically, either by email or over the Internet. Survey schedules or solicitation letters were initially mailed out to all sample establishments. Three additional mailings were sent to non-respondents at approximately four-week intervals. Telephone follow-ups and, in some cases, personal visit follow-ups were made for those nonrespondents considered critical to the success of the survey.

Employment is the estimate of total wage and salary employment in an occupation.

Wages for the OES survey are straight-time, gross pay, exclusive of premium pay. Base rate, cost-of-living allowances, guaranteed pay, hazardous-duty pay, incentive pay including commissions and production bonuses, tips, and on-call pay are included. Excluded are back pay, jury duty pay, overtime pay, severance pay, shift differentials, nonproduction bonuses, employer cost of supplementary benefits, and tuition reimbursements.

The survey collects the wage information in twelve intervals that are defined both as hourly rates and the corresponding annual rates, where the annual rates are constructed by multiplying the hourly wage rate for the interval by the typical work year of 2,080 hours. In reporting, the respondent can reference either the hourly or the annual rate, but is instructed to report the hourly rate for part-time workers. Wage interval endpoints are determined by using the wage rate data collected by the Bureau of Labor Statistics' National Compensation Survey (NCS).

RangeHourlyAnnual
AUnder $9.25Under $19,240
B$9.25 - $11.74$19,240 - $24,439
C$11.75 - $14.74$24,440 - $30,679
D$14.75 - $18.74$30,680 - $38,999
E$18.75 - $23.99$39,000 - $49,919
F$24.00 - $30.24$49,920 - $62,919
G$30.25 - $38.49$62,920 - $80,079
H$38.50 - $48.99$80,080 - $101,919
I$49.00 - $61.99$101,920 - $128,959
J$62.00 - $78.74$128,960 - $163,799
K$78.75 - $99.99$163,800 - $207,999
L$100.00 and over$208,000 and over

top

STATE DATA

Data are collected for the universe of state government agencies, rather than a sample of employment. State government operations are surveyed every year, with the data collected and processed with the rest of the survey responses.

top

ESTIMATION METHODOLOGY

The OES survey samples approximately 3,000 establishments semiannually in two panels. One panel is sampled in the second quarter, the other in the fourth quarter. Approximately 18,000 establishments are sampled over a six-panel cycle. While estimates can be made from a single panel or a single year of data, the OES survey is designed to produce estimates at a desired level of precision using six panels. A six-panel sample allows the production of estimates at fine levels of geographical, industrial, and occupational detail. For the May 2016 OES survey, estimates are based on data collected from establishments in May 2016, November 2015, May 2015, November 2014, May 2014 and November 2013.

Combining multiple years of data has statistical advantages. Significant reductions in sampling error can be achieved by taking advantage of a full three years of data, which covers over 70 percent of the employment in Connecticut. While there are significant advantages, the limitation associated with this estimation procedure is that it requires "wage-updating" for the earlier years of data. For "wage-updating" purposes, the OES program has been using the Bureau of Labor Statistic's Employment Cost Index (ECI) to update wage rate data from previous panels before combining them with the current panel. The wage updating process assumes that: (1) each occupation's wage rate, as measured in earlier panels, shifts across time at the same pace as the broader occupational division that encompasses it and (2) geography and industry are not major factors in the wage updating process. The Bureau has conducted research over the past several years on the accuracy of updating wage rates using the ECI. In this research, the ECI wage-updating approach was compared to alternative modeling approaches. Current research results support the continued use of ECI wage-updating.

In addition, a "nearest neighbor" hot deck imputation procedure was used to impute occupational employment totals for establishments that reported no employment data. For establishments that reported or imputed occupational employment totals but did not report an employment distribution across the wage intervals, a variation of mean imputation was used to impute the distribution. During estimates processing, OES employment estimates are benchmarked to the mean of employment totals extracted from the Bureau of Labor Statistic's November 2015 and May 2016 Quarterly Micro Files.

top

RELIABILITY OF ESTIMATES

Estimates calculated from a sample survey are subject to two types of error: sampling and non-sampling.

Sampling error occurs when estimates are calculated from a subset of the population (i.e., a sample) instead of the full population. When a subset of the population is sampled, it is very likely that the sample estimate of the characteristic of interest will differ from the population value of that characteristic. Differences between the sample estimate and the population value will vary depending on the sample selected. This variability can be estimated by calculating the standard error (SE) of the sample estimate. The OES survey uses the relative standard error (RSE) of a sample estimate to measure sampling error. RSE is defined as the sample error of a sample estimate divided by the sample estimate itself. This statistic provides the user with a measure of the relative precision of the sample estimate. Relative standard errors (RSEs) are calculated for both occupational employment and mean wage rate estimates. In general, estimates based on many establishments have lower RSEs than estimates based on few establishments.

Non-sampling error occurs for a variety of reasons, none of which are directly connected to sampling like sampling error. Examples of non-sampling error include: nonresponse, data incorrectly reported by the respondent, mistakes made in entering collected data into the database, mistakes made in editing and processing the collected data.

top
Go Connecticut LMI Home State of Connecticut Department of Labor - Office of Research
200 Folly Brook Boulevard, Wethersfield, CT 06109 / Phone: 860-263-6285
LMI Home | CTDOL Home | CT.gov | Feedback | Disclaimer | Privacy Policy | Accessibility Policy
This workforce product was funded by a grant awarded by the U.S. Department of Labor's Employment and Training Administration. (more)
Go to the State of Connecticut website