Response and nonresponse
Filter results by
Search HelpKeyword(s)
Survey or statistical program
Results
All (8)
All (8) ((8 results))
- Articles and reports: 11-522-X20010016257Description:
This paper discusses in detail issues dealing with the technical aspects of designing and conducting surveys. It is intended for an audience of survey methodologists.
This paper describes the methods used to increase the response rates of a generalist and specialist physician survey. The means of delivery (regular versus priority mail) and notification of inclusion in a draw for cash prizes were randomized using a 2 x 2 factorial design. While neither priority delivery nor notification of a cash prize sufficiently overcame whatever obstacles exist in this population, both approaches had a positive, though limited, effect on the response rate of the physicians. However, a subsequent mailing of a prepaid cash incentive (delivered by courier) was particularly effective in increasing the representation of the generalist subsample.
Release date: 2002-09-12 - Articles and reports: 11-522-X20010016258Geography: CanadaDescription:
This paper discusses in detail issues dealing with the technical aspects of designing and conducting surveys. It is intended for an audience of survey methodologists.
To fill statistical gaps in the areas of health determinants, health status and health system usage by the Canadian population at the health region levels (sub-provincial areas or regions of interest to health authorities), Statistics Canada established a new survey called the Canadian Community Health Survey (CCHS). The CCHS consists of two separate components: a regional survey in the first year and a provincial survey in the second year. The main purpose of the regional survey, for which collection took place between September 2000 and October 2001, was to produce cross-sectional estimates for 136 health regions in Canada, based on a sample of more than 134,000 respondents. This article focuses on the various measures taken at the time of data collection to ensure a high level of quality for this large-scale survey.
Release date: 2002-09-12 - Articles and reports: 11-522-X20010016266Description:
This paper discusses in detail issues dealing with the technical aspects of designing and conducting surveys. It is intended for an audience of survey methodologists.
The key measure of Census quality is the level of response achieved. In recent censuses around the world, this level has been in the high nineties percentage range. This was also true of the 1991 Census in Britain (98%). However, what was particularly noticeable about this Census was the differential response rate and the difficulty in effectively measuring this rate. The United Kingdom set up the One Number Census program in order to research and develop a more effective methodology to measure and account for under-enumeration in the 2001 Census. The key element in this process is the Census Coverage Survey - a significantly larger and redesigned post-enumeration survey.
This paper describes the planning and design of the Census Coverage Survey with particular emphasis on the implementation of the proposed field methodology. It also provides a high-level overview of the success of this survey.
Release date: 2002-09-12 - 4. Correcting for non-response in indirect sampling ArchivedArticles and reports: 11-522-X20010016267Description:
This paper discusses in detail issues dealing with the technical aspects of designing and conducting surveys. It is intended for an audience of survey methodologists.
In practice, a list of the desired collection units is not always available. Instead, a list of different units that are somehow related to the collection units may be provided, thus producing two related populations, UA and UB. An estimate for UB needs to be created, however, the sampling frame provided is only for the UA population.
One solution for this problem is to select a sample from UA (sA) and produce an estimate for UB using the existing relationship between the two populations. This process may be referred to as indirect sampling. To assign a selection probability, or an estimation weight, for the survey units, Lavallée (1995) developed the generalized weight share method (GWSM). The GWSM produces an estimation weight that basically constitutes an average of the sampling weights of the units in sA.
This paper discusses the types of non-response associated with indirect sampling and the possible estimation problems that can occur in the application of the GWSM.
Release date: 2002-09-12 - 5. Using national registrations to correct for selective non-response: political preference of ethnic groups ArchivedArticles and reports: 11-522-X20010016268Description:
This paper discusses in detail issues dealing with the technical aspects of designing and conducting surveys. It is intended for an audience of survey methodologists.
This paper deals with non-response bias, discussing a few approaches in this field. It is demonstrated that non-response bias as to voter turnout is lower in a survey on living conditions than in a purely political survey. In addition, auxiliary information from registrations is used to investigate non-response and its bias among ethnic groups. Response rates among ethnic minority groups are rather low, but there is no evidence that response rates are less in lower social class areas. Correcting for limited socioeconomic deviations does not affect the distributions of political preference.
Release date: 2002-09-12 - 6. Hot deck imputation for the response model ArchivedArticles and reports: 11-522-X20010016275Description:
This paper discusses in detail issues dealing with the technical aspects of designing and conducting surveys. It is intended for an audience of survey methodologists.
Hot deck imputation, in which missing items are replaced with values from respondents, is often used in survey sampling. A model supporting such procedures is the model in which response probabilities are assumed equal within imputation cells. In this paper, an efficient version of hot deck imputation is described, as are the variance of the efficient version derived under the cell response model and an approximation to the fully efficient procedure in which a small number of values are imputed for each non-respondent, respectively. Variance estimation procedures are presented and illustrated in a Monte Carlo study.
Release date: 2002-09-12 - Articles and reports: 11-522-X20010016280Description:
This paper discusses in detail issues dealing with the technical aspects of designing and conducting surveys. It is intended for an audience of survey methodologists.
Survey response rates serve as one key measure of the quality of a data set. However, they are only useful to a statistical agency in the evaluation of ongoing data collections if they are based on a predefined set of formulas and definitions that are uniformly applied across all data collections.
In anticipation of a revision of the current National Center for Education Statistics (NCES) statistical standards, several agency-wide audits of statistical practices were undertaken in the late 1990s. In particular, a compendium documenting major survey design parameters of NCES surveys was drafted. Related to this, NCES conducted a targeted audit of the consistency in response rate calculations across these surveys.
Although NCES has had written statistical standards since 1988, the audit of the reported response rates from 50 survey components in 14 NCES surveys revealed considerable variability in procedures used to calculate response rates. During the course of the response rate audit, the Statistical Standards Program staff concluded that the organization of the 1992 Standards made it difficult to find all of the information associated with response rates in the standards. In fact, there are references to response rate in a number of separate standards scattered throughout the 1992 Statistical Standards.
Release date: 2002-09-12 - 8. A statistical analysis of response rates ArchivedArticles and reports: 11-522-X20010016297Description:
This paper discusses in detail issues dealing with the technical aspects in designing and conducting surveys. It is intended for an audience of survey methodologists. The Danish National Institute of Social Research is an independent institution under the Ministry of Social Affairs. The Institute carries out surveys on social issues on encompassing a broad range of subjects. The Sustainable Financing Initiative Survey (SFI-SURVEY) is an economically independent section within the institute. SFI-SURVEY carries out scientific surveys both for the Institute, for other public organizations, and for the private sector as well. The SFI-SURVEY interviewer body has 450 interviewers spread throughout Denmark. There are five supervisors, each with a regional office, who are in contact with the interviewer body. On a yearly basis, SFI-SURVEY conducts 40 surveys. The average sample size (gross) is 1,000 persons. The average response rate is 75%. Since January 1999, the following information about the surveys have been recorded: · Type of method used (face-to-face or telephone) · Length of questionnaire (interviewing time in minutes) · Whether or not a folder was sent to the respondents in advance · Whether or not an interviewer instruction meeting was given · Number of interviews per interviewer per week · Whether or not the subject of the survey was of interest to the respondents · Interviewing month · Target group (random selection of the total population or special groups)
Release date: 2002-09-12
Data (0)
Data (0) (0 results)
No content available at this time.
Analysis (8)
Analysis (8) ((8 results))
- Articles and reports: 11-522-X20010016257Description:
This paper discusses in detail issues dealing with the technical aspects of designing and conducting surveys. It is intended for an audience of survey methodologists.
This paper describes the methods used to increase the response rates of a generalist and specialist physician survey. The means of delivery (regular versus priority mail) and notification of inclusion in a draw for cash prizes were randomized using a 2 x 2 factorial design. While neither priority delivery nor notification of a cash prize sufficiently overcame whatever obstacles exist in this population, both approaches had a positive, though limited, effect on the response rate of the physicians. However, a subsequent mailing of a prepaid cash incentive (delivered by courier) was particularly effective in increasing the representation of the generalist subsample.
Release date: 2002-09-12 - Articles and reports: 11-522-X20010016258Geography: CanadaDescription:
This paper discusses in detail issues dealing with the technical aspects of designing and conducting surveys. It is intended for an audience of survey methodologists.
To fill statistical gaps in the areas of health determinants, health status and health system usage by the Canadian population at the health region levels (sub-provincial areas or regions of interest to health authorities), Statistics Canada established a new survey called the Canadian Community Health Survey (CCHS). The CCHS consists of two separate components: a regional survey in the first year and a provincial survey in the second year. The main purpose of the regional survey, for which collection took place between September 2000 and October 2001, was to produce cross-sectional estimates for 136 health regions in Canada, based on a sample of more than 134,000 respondents. This article focuses on the various measures taken at the time of data collection to ensure a high level of quality for this large-scale survey.
Release date: 2002-09-12 - Articles and reports: 11-522-X20010016266Description:
This paper discusses in detail issues dealing with the technical aspects of designing and conducting surveys. It is intended for an audience of survey methodologists.
The key measure of Census quality is the level of response achieved. In recent censuses around the world, this level has been in the high nineties percentage range. This was also true of the 1991 Census in Britain (98%). However, what was particularly noticeable about this Census was the differential response rate and the difficulty in effectively measuring this rate. The United Kingdom set up the One Number Census program in order to research and develop a more effective methodology to measure and account for under-enumeration in the 2001 Census. The key element in this process is the Census Coverage Survey - a significantly larger and redesigned post-enumeration survey.
This paper describes the planning and design of the Census Coverage Survey with particular emphasis on the implementation of the proposed field methodology. It also provides a high-level overview of the success of this survey.
Release date: 2002-09-12 - 4. Correcting for non-response in indirect sampling ArchivedArticles and reports: 11-522-X20010016267Description:
This paper discusses in detail issues dealing with the technical aspects of designing and conducting surveys. It is intended for an audience of survey methodologists.
In practice, a list of the desired collection units is not always available. Instead, a list of different units that are somehow related to the collection units may be provided, thus producing two related populations, UA and UB. An estimate for UB needs to be created, however, the sampling frame provided is only for the UA population.
One solution for this problem is to select a sample from UA (sA) and produce an estimate for UB using the existing relationship between the two populations. This process may be referred to as indirect sampling. To assign a selection probability, or an estimation weight, for the survey units, Lavallée (1995) developed the generalized weight share method (GWSM). The GWSM produces an estimation weight that basically constitutes an average of the sampling weights of the units in sA.
This paper discusses the types of non-response associated with indirect sampling and the possible estimation problems that can occur in the application of the GWSM.
Release date: 2002-09-12 - 5. Using national registrations to correct for selective non-response: political preference of ethnic groups ArchivedArticles and reports: 11-522-X20010016268Description:
This paper discusses in detail issues dealing with the technical aspects of designing and conducting surveys. It is intended for an audience of survey methodologists.
This paper deals with non-response bias, discussing a few approaches in this field. It is demonstrated that non-response bias as to voter turnout is lower in a survey on living conditions than in a purely political survey. In addition, auxiliary information from registrations is used to investigate non-response and its bias among ethnic groups. Response rates among ethnic minority groups are rather low, but there is no evidence that response rates are less in lower social class areas. Correcting for limited socioeconomic deviations does not affect the distributions of political preference.
Release date: 2002-09-12 - 6. Hot deck imputation for the response model ArchivedArticles and reports: 11-522-X20010016275Description:
This paper discusses in detail issues dealing with the technical aspects of designing and conducting surveys. It is intended for an audience of survey methodologists.
Hot deck imputation, in which missing items are replaced with values from respondents, is often used in survey sampling. A model supporting such procedures is the model in which response probabilities are assumed equal within imputation cells. In this paper, an efficient version of hot deck imputation is described, as are the variance of the efficient version derived under the cell response model and an approximation to the fully efficient procedure in which a small number of values are imputed for each non-respondent, respectively. Variance estimation procedures are presented and illustrated in a Monte Carlo study.
Release date: 2002-09-12 - Articles and reports: 11-522-X20010016280Description:
This paper discusses in detail issues dealing with the technical aspects of designing and conducting surveys. It is intended for an audience of survey methodologists.
Survey response rates serve as one key measure of the quality of a data set. However, they are only useful to a statistical agency in the evaluation of ongoing data collections if they are based on a predefined set of formulas and definitions that are uniformly applied across all data collections.
In anticipation of a revision of the current National Center for Education Statistics (NCES) statistical standards, several agency-wide audits of statistical practices were undertaken in the late 1990s. In particular, a compendium documenting major survey design parameters of NCES surveys was drafted. Related to this, NCES conducted a targeted audit of the consistency in response rate calculations across these surveys.
Although NCES has had written statistical standards since 1988, the audit of the reported response rates from 50 survey components in 14 NCES surveys revealed considerable variability in procedures used to calculate response rates. During the course of the response rate audit, the Statistical Standards Program staff concluded that the organization of the 1992 Standards made it difficult to find all of the information associated with response rates in the standards. In fact, there are references to response rate in a number of separate standards scattered throughout the 1992 Statistical Standards.
Release date: 2002-09-12 - 8. A statistical analysis of response rates ArchivedArticles and reports: 11-522-X20010016297Description:
This paper discusses in detail issues dealing with the technical aspects in designing and conducting surveys. It is intended for an audience of survey methodologists. The Danish National Institute of Social Research is an independent institution under the Ministry of Social Affairs. The Institute carries out surveys on social issues on encompassing a broad range of subjects. The Sustainable Financing Initiative Survey (SFI-SURVEY) is an economically independent section within the institute. SFI-SURVEY carries out scientific surveys both for the Institute, for other public organizations, and for the private sector as well. The SFI-SURVEY interviewer body has 450 interviewers spread throughout Denmark. There are five supervisors, each with a regional office, who are in contact with the interviewer body. On a yearly basis, SFI-SURVEY conducts 40 surveys. The average sample size (gross) is 1,000 persons. The average response rate is 75%. Since January 1999, the following information about the surveys have been recorded: · Type of method used (face-to-face or telephone) · Length of questionnaire (interviewing time in minutes) · Whether or not a folder was sent to the respondents in advance · Whether or not an interviewer instruction meeting was given · Number of interviews per interviewer per week · Whether or not the subject of the survey was of interest to the respondents · Interviewing month · Target group (random selection of the total population or special groups)
Release date: 2002-09-12
Reference (0)
Reference (0) (0 results)
No content available at this time.
- Date modified: