Downloads & Free Reading Options - Results

Map 4. Location of Ground Plots for Sampling Blowdown. Blowdown-BarkBeetle Survey. Map is from: Final Report on the 1952 Blowdown-Bark-Beetle Survey in the Douglas-fir Region of Oregon and Washington. Prepared by: Pacific Northwest Forest and Range Experiment Station, US Forest Service; and Portland Forest Insect Laboratory, Bureau of Entomology and Plant Quarantine. Portland, Oregon. July 1952. 7 pages. Photo by: Unknown Map creation date: October 1952 Credit: USDA Forest Service, Region 6, State and Private Forestry, Forest Health Protection. Source: Aerial Survey Program digital collection. Image provided by USDA Forest Service, Region 6, State and Private Forestry, Forest Health Protection: www.fs.usda.gov/main/r6/forest-grasslandhealth

Map 4. Location of Ground Plots for Sampling Blowdown. Blowdown-BarkBeetle Survey. Map is from: Final Report on the 1952 Blowdown-Bark-Beetle Survey in the Douglas-fir Region of Oregon and Washington. Prepared by: Pacific Northwest Forest and Range Experiment Station, US Forest Service; and Portland Forest Insect Laboratory, Bureau of Entomology and Plant Quarantine. Portland, Oregon. July 1952. 7 pages. Photo by: Unknown Map creation date: October 1952 Credit: USDA Forest Service, Region 6, State and Private Forestry, Forest Health Protection. Source: Aerial Survey Program digital collection. Image provided by USDA Forest Service, Region 6, State and Private Forestry, Forest Health Protection: www.fs.usda.gov/main/r6/forest-grasslandhealth

In this paper, generalized exponential-type estimator has been proposed for estimating the population variance using mean auxiliary variable in singlephase sampling. Some special cases of the proposed generalized estimator have also been discussed. The expressions for the mean square error and bias of the proposed generalized estimator have been derived. The proposed generalized estimator has been compared theoretically with the usual unbiased estimator, usual ratio and product, exponential-type ratio and product, and generalized exponential-type ratio estimators and the conditions under which the proposed estimators are better than some existing estimators have also been given. An empirical study has also been carried out to demonstrate the efficiencies of the proposed estimators.

In this paper, generalized exponential-type estimator has been proposed for estimating the population variance using mean auxiliary variable in singlephase sampling. Some special cases of the proposed generalized estimator have also been discussed. The expressions for the mean square error and bias of the proposed generalized estimator have been derived. The proposed generalized estimator has been compared theoretically with the usual unbiased estimator, usual ratio and product, exponential-type ratio and product, and generalized exponential-type ratio estimators and the conditions under which the proposed estimators are better than some existing estimators have also been given. An empirical study has also been carried out to demonstrate the efficiencies of the proposed estimators.

In this paper, generalized exponential-type estimator has been proposed for estimating the population variance using mean auxiliary variable in singlephase sampling. Some special cases of the proposed generalized estimator have also been discussed. The expressions for the mean square error and bias of the proposed generalized estimator have been derived. The proposed generalized estimator has been compared theoretically with the usual unbiased estimator, usual ratio and product, exponential-type ratio and product, and generalized exponential-type ratio estimators and the conditions under which the proposed estimators are better than some existing estimators have also been given. An empirical study has also been carried out to demonstrate the efficiencies of the proposed estimators.

This article is from PLoS ONE , volume 9 . Abstract Background: Injection drug use has been the major cause of HIV/AIDS in China in the past two decades. We measured the prevalences of HIV and hepatitis C virus (HCV) prevalence and their associated risk factors among current injection drug users (IDUs) in Ruili city, a border region connecting China with Myanmar that has been undergoing serious drug use and HIV spread problems. An estimate of the number of current IDUs is also presented. Methods: In 2012, Chinese IDUs who had injected within the past six months and aged ≥18 years were recruited using a respondent-driven sampling (RDS) technique. Participants underwent interviews and serological testing for HIV, HBV, HCV and syphilis. Logistic regression indentified factors associated with HIV and HCV infections. Multiplier method was used to obtain an estimate of the size of the current IDU population via combining available service data and findings from our survey. Results: Among 370 IDUs recruited, the prevalence of HIV and HCV was 18.3% and 41.5%, respectively. 27.1% of participants had shared a needle/syringe in their lifetime. Consistent condom use rates were low among both regular (6.8%) and non-regular (30.4%) partners. Factors independently associated with being HIV positive included HCV infection, having a longer history of injection drug use and experience of needle/syringe sharing. Participants with HCV infection were more likely to be HIV positive, have injected more types of drugs, have shared other injection equipments and have unprotected sex with regular sex partners. The estimated number of current IDUs in Ruili city was 2,714 (95% CI: 1,617–5,846). Conclusions: IDUs may continue to be a critical subpopulation for transmission of HIV and other infections in this region because of the increasing population and persistent high risk of injection and sexual behaviours. Developing innovative strategies that can improve accessibility of current harm reduction services and incorporate more comprehensive contents is urgently needed.

This article is from PLoS ONE , volume 9 . Abstract Background: Injection drug use has been the major cause of HIV/AIDS in China in the past two decades. We measured the prevalences of HIV and hepatitis C virus (HCV) prevalence and their associated risk factors among current injection drug users (IDUs) in Ruili city, a border region connecting China with Myanmar that has been undergoing serious drug use and HIV spread problems. An estimate of the number of current IDUs is also presented. Methods: In 2012, Chinese IDUs who had injected within the past six months and aged ≥18 years were recruited using a respondent-driven sampling (RDS) technique. Participants underwent interviews and serological testing for HIV, HBV, HCV and syphilis. Logistic regression indentified factors associated with HIV and HCV infections. Multiplier method was used to obtain an estimate of the size of the current IDU population via combining available service data and findings from our survey. Results: Among 370 IDUs recruited, the prevalence of HIV and HCV was 18.3% and 41.5%, respectively. 27.1% of participants had shared a needle/syringe in their lifetime. Consistent condom use rates were low among both regular (6.8%) and non-regular (30.4%) partners. Factors independently associated with being HIV positive included HCV infection, having a longer history of injection drug use and experience of needle/syringe sharing. Participants with HCV infection were more likely to be HIV positive, have injected more types of drugs, have shared other injection equipments and have unprotected sex with regular sex partners. The estimated number of current IDUs in Ruili city was 2,714 (95% CI: 1,617–5,846). Conclusions: IDUs may continue to be a critical subpopulation for transmission of HIV and other infections in this region because of the increasing population and persistent high risk of injection and sexual behaviours. Developing innovative strategies that can improve accessibility of current harm reduction services and incorporate more comprehensive contents is urgently needed.

c1977

Nonresponse is present in almost all surveys and can severely bias estimates. It is usually distinguished between unit and item nonresponse: in the former, we completely fail to have information from a unit selected in the sample, while in the latter, we observe only part of the information on the selected unit. Unit nonresponse is usually dealt with by reweighting: each unit selected in the sample has associated a sampling weight and an unknown response probability; the initial sampling weight is multiplied by the inverse of estimated response probability. Item nonresponse is usually dealt with by imputation. By noting that for a particular survey variable, we just have observed and unobserved values, in this work we exploit the connection between unit and item nonresponse. In particular, we assume that the factors that drive unit response are the same as those that drive item response on selected variables of interest. Response probabilities are then estimated by using a logistic regression with a latent covariate that measures such will to respond and that can explain part of the unknown behavior of a unit to participate in the survey. The latent covariate is estimated using latent trait models. Such approach is particularly relevant for sensitive items and, therefore, can handle non-ignorable nonresponse. Auxiliary information known for both respondents and nonrespondents can be included either in the latent variable model or in the logistic model. The approach can be also used when auxiliary information is not available, and we focus here on this case. The theoretical properties of the proposed estimators are sketched and simulations studies are conducted to illustrate their finite size sample performance.

Nonresponse is present in almost all surveys and can severely bias estimates. It is usually distinguished between unit and item nonresponse: in the former, we completely fail to have information from a unit selected in the sample, while in the latter, we observe only part of the information on the selected unit. Unit nonresponse is usually dealt with by reweighting: each unit selected in the sample has associated a sampling weight and an unknown response probability; the initial sampling weight is multiplied by the inverse of estimated response probability. Item nonresponse is usually dealt with by imputation. By noting that for a particular survey variable, we just have observed and unobserved values, in this work we exploit the connection between unit and item nonresponse. In particular, we assume that the factors that drive unit response are the same as those that drive item response on selected variables of interest. Response probabilities are then estimated by using a logistic regression with a latent covariate that measures such will to respond and that can explain part of the unknown behavior of a unit to participate in the survey. The latent covariate is estimated using latent trait models. Such approach is particularly relevant for sensitive items and, therefore, can handle non-ignorable nonresponse. Auxiliary information known for both respondents and nonrespondents can be included either in the latent variable model or in the logistic model. The approach can be also used when auxiliary information is not available, and we focus here on this case. The theoretical properties of the proposed estimators are sketched and simulations studies are conducted to illustrate their finite size sample performance.

Nonresponse is present in almost all surveys and can severely bias estimates. It is usually distinguished between unit and item nonresponse: in the former, we completely fail to have information from a unit selected in the sample, while in the latter, we observe only part of the information on the selected unit. Unit nonresponse is usually dealt with by reweighting: each unit selected in the sample has associated a sampling weight and an unknown response probability; the initial sampling weight is multiplied by the inverse of estimated response probability. Item nonresponse is usually dealt with by imputation. By noting that for a particular survey variable, we just have observed and unobserved values, in this work we exploit the connection between unit and item nonresponse. In particular, we assume that the factors that drive unit response are the same as those that drive item response on selected variables of interest. Response probabilities are then estimated by using a logistic regression with a latent covariate that measures such will to respond and that can explain part of the unknown behavior of a unit to participate in the survey. The latent covariate is estimated using latent trait models. Such approach is particularly relevant for sensitive items and, therefore, can handle non-ignorable nonresponse. Auxiliary information known for both respondents and nonrespondents can be included either in the latent variable model or in the logistic model. The approach can be also used when auxiliary information is not available, and we focus here on this case. The theoretical properties of the proposed estimators are sketched and simulations studies are conducted to illustrate their finite size sample performance.

Predictive mean matching imputation is popular for handling item nonresponse in survey sampling. In this article, we study the asymptotic properties of the predictive mean matching estimator of the population mean. For variance estimation, the conventional bootstrap inference for matching estimators with fixed matches has been shown to be invalid due to the nonsmoothess nature of the matching estimator. We propose asymptotically valid replication variance estimation. The key strategy is to construct replicates of the estimator directly based on linear terms of the estimator, instead of individual records of variables. Extension to nearest neighbor imputation is also discussed. A simulation study confirms that the new procedure provides valid variance estimation.

An emergency environmental sampling survey was performed at Cibolo, TX on 21 Sep 90. The purpose of the survey was to sample, analyze, and determine the appropriate disposition of approximately 60 drums containing unknown materials. Sampling strategies were implemented in order to adequately and properly identify the contents of each drum. Each drum was either sampled individually or, when feasible, composited with another drum. The analyses prescribed for this project are designed to determine if the drums contain unused material, recycleable material, or waste product. The analyses will also determine if the waste products are hazardous or nonhazardous. The analytical methods used are presented in the table. The appropriate analysis for each drum was determined based upon visual inspection of the material through a disposable composite liquid waste sampler. Gas Chromatograph/Mass Spectrometer chemical identification and hazardous waste characteristics analyses were performed on materials which appeared to be unused. Energy recovery analyses were performed on materials which appeared to be uncontaminated waste oil. Toxicity characteristic leachate procedure analyses were performed on all unknown wastes, unsegregated wastes (i.e., waste oil and antifreeze), and paint and thinner wastes. A volatile organics screen was performed on some solvents that appeared to be uncontaminated.

An emergency environmental sampling survey was performed at Cibolo, TX on 21 Sep 90. The purpose of the survey was to sample, analyze, and determine the appropriate disposition of approximately 60 drums containing unknown materials. Sampling strategies were implemented in order to adequately and properly identify the contents of each drum. Each drum was either sampled individually or, when feasible, composited with another drum. The analyses prescribed for this project are designed to determine if the drums contain unused material, recycleable material, or waste product. The analyses will also determine if the waste products are hazardous or nonhazardous. The analytical methods used are presented in the table. The appropriate analysis for each drum was determined based upon visual inspection of the material through a disposable composite liquid waste sampler. Gas Chromatograph/Mass Spectrometer chemical identification and hazardous waste characteristics analyses were performed on materials which appeared to be unused. Energy recovery analyses were performed on materials which appeared to be uncontaminated waste oil. Toxicity characteristic leachate procedure analyses were performed on all unknown wastes, unsegregated wastes (i.e., waste oil and antifreeze), and paint and thinner wastes. A volatile organics screen was performed on some solvents that appeared to be uncontaminated.

Includes bibliography

Includes bibliography

According to Hansen, Madow and Tepping [J. Amer. Statist. Assoc. 78 (1983) 776--793], "Probability sampling designs and randomization inference are widely accepted as the standard approach in sample surveys." In this article, reasons are advanced for the wide use of this design-based approach, particularly by federal agencies and other survey organizations conducting complex large scale surveys on topics related to public policy. Impact of Bayesian methods in survey sampling is also discussed in two different directions: nonparametric calibrated Bayesian inferences from large samples and hierarchical Bayes methods for small area estimation based on parametric models.

According to Hansen, Madow and Tepping [J. Amer. Statist. Assoc. 78 (1983) 776--793], "Probability sampling designs and randomization inference are widely accepted as the standard approach in sample surveys." In this article, reasons are advanced for the wide use of this design-based approach, particularly by federal agencies and other survey organizations conducting complex large scale surveys on topics related to public policy. Impact of Bayesian methods in survey sampling is also discussed in two different directions: nonparametric calibrated Bayesian inferences from large samples and hierarchical Bayes methods for small area estimation based on parametric models.

According to Hansen, Madow and Tepping [J. Amer. Statist. Assoc. 78 (1983) 776--793], "Probability sampling designs and randomization inference are widely accepted as the standard approach in sample surveys." In this article, reasons are advanced for the wide use of this design-based approach, particularly by federal agencies and other survey organizations conducting complex large scale surveys on topics related to public policy. Impact of Bayesian methods in survey sampling is also discussed in two different directions: nonparametric calibrated Bayesian inferences from large samples and hierarchical Bayes methods for small area estimation based on parametric models.

According to Hansen, Madow and Tepping [J. Amer. Statist. Assoc. 78 (1983) 776--793], "Probability sampling designs and randomization inference are widely accepted as the standard approach in sample surveys." In this article, reasons are advanced for the wide use of this design-based approach, particularly by federal agencies and other survey organizations conducting complex large scale surveys on topics related to public policy. Impact of Bayesian methods in survey sampling is also discussed in two different directions: nonparametric calibrated Bayesian inferences from large samples and hierarchical Bayes methods for small area estimation based on parametric models.

According to Hansen, Madow and Tepping [J. Amer. Statist. Assoc. 78 (1983) 776--793], "Probability sampling designs and randomization inference are widely accepted as the standard approach in sample surveys." In this article, reasons are advanced for the wide use of this design-based approach, particularly by federal agencies and other survey organizations conducting complex large scale surveys on topics related to public policy. Impact of Bayesian methods in survey sampling is also discussed in two different directions: nonparametric calibrated Bayesian inferences from large samples and hierarchical Bayes methods for small area estimation based on parametric models.

A model-assisted semiparametric method of estimating finite population totals is investigated to improve the precision of survey estimators by incorporating multivariate auxiliary information. The proposed superpopulation model is a single-index model which has proven to be a simple and efficient semiparametric tool in multivariate regression. A class of estimators based on polynomial spline regression is proposed. These estimators are robust against deviation from single-index models. Under standard design conditions, the proposed estimators are asymptotically design-unbiased, consistent and asymptotically normal. An iterative optimization routine is provided that is sufficiently fast for users to analyze large and complex survey data within seconds. The proposed method has been applied to simulated datasets and MU281 dataset, which have provided strong evidence that corroborates with the asymptotic theory.

A model-assisted semiparametric method of estimating finite population totals is investigated to improve the precision of survey estimators by incorporating multivariate auxiliary information. The proposed superpopulation model is a single-index model which has proven to be a simple and efficient semiparametric tool in multivariate regression. A class of estimators based on polynomial spline regression is proposed. These estimators are robust against deviation from single-index models. Under standard design conditions, the proposed estimators are asymptotically design-unbiased, consistent and asymptotically normal. An iterative optimization routine is provided that is sufficiently fast for users to analyze large and complex survey data within seconds. The proposed method has been applied to simulated datasets and MU281 dataset, which have provided strong evidence that corroborates with the asymptotic theory.

A model-assisted semiparametric method of estimating finite population totals is investigated to improve the precision of survey estimators by incorporating multivariate auxiliary information. The proposed superpopulation model is a single-index model which has proven to be a simple and efficient semiparametric tool in multivariate regression. A class of estimators based on polynomial spline regression is proposed. These estimators are robust against deviation from single-index models. Under standard design conditions, the proposed estimators are asymptotically design-unbiased, consistent and asymptotically normal. An iterative optimization routine is provided that is sufficiently fast for users to analyze large and complex survey data within seconds. The proposed method has been applied to simulated datasets and MU281 dataset, which have provided strong evidence that corroborates with the asymptotic theory.

This article is from International Journal of Health Geographics , volume 11 . Abstract Background: Mortality estimates can measure and monitor the impacts of conflict on a population, guide humanitarian efforts, and help to better understand the public health impacts of conflict. Vital statistics registration and surveillance systems are rarely functional in conflict settings, posing a challenge of estimating mortality using retrospective population-based surveys. Results: We present a two-stage cluster sampling method for application in population-based mortality surveys. The sampling method utilizes gridded population data and a geographic information system (GIS) to select clusters in the first sampling stage and Google Earth TM imagery and sampling grids to select households in the second sampling stage. The sampling method is implemented in a household mortality study in Iraq in 2011. Factors affecting feasibility and methodological quality are described. Conclusion: Sampling is a challenge in retrospective population-based mortality studies and alternatives that improve on the conventional approaches are needed. The sampling strategy presented here was designed to generate a representative sample of the Iraqi population while reducing the potential for bias and considering the context specific challenges of the study setting. This sampling strategy, or variations on it, are adaptable and should be considered and tested in other conflict settings.

This article is from International Journal of Health Geographics , volume 11 . Abstract Background: Mortality estimates can measure and monitor the impacts of conflict on a population, guide humanitarian efforts, and help to better understand the public health impacts of conflict. Vital statistics registration and surveillance systems are rarely functional in conflict settings, posing a challenge of estimating mortality using retrospective population-based surveys. Results: We present a two-stage cluster sampling method for application in population-based mortality surveys. The sampling method utilizes gridded population data and a geographic information system (GIS) to select clusters in the first sampling stage and Google Earth TM imagery and sampling grids to select households in the second sampling stage. The sampling method is implemented in a household mortality study in Iraq in 2011. Factors affecting feasibility and methodological quality are described. Conclusion: Sampling is a challenge in retrospective population-based mortality studies and alternatives that improve on the conventional approaches are needed. The sampling strategy presented here was designed to generate a representative sample of the Iraqi population while reducing the potential for bias and considering the context specific challenges of the study setting. This sampling strategy, or variations on it, are adaptable and should be considered and tested in other conflict settings.

This item represents a case in PACER, the U.S. Government's website for federal case data. If you wish to see the entire case, please consult PACER directly.

This comment emphasizes the importance of model checking and model fitting when making inferences about finite population quantities. It also suggests the value of using unit level models when making inferences for small subpopulations, that is, "small area" analyses [arXiv:1108.2356].

Pre-analysis plan for phase 2 of our examination of the validity of survey samples collected using Facebook advertisements. This phase includes survey data collection in Indonesia and replicates the analyses conducted in Phase 1 in Mexico and Kenya.

A technique was developed for producing organic fibers by dispersing solutions of organic polymers into air. The dried fibers could be collected to form a mat which served as a highly efficient filter either with or without compression. A solution of polystyrene in methylene chloride produced fibers which seemed to be particularly promising for use as filters, and this system was studied in detail. Filter efficiencies were determined for solid aerosol particles in the size range 0.01 to 1 microns in diameter. A survey was made of the leading sources of organic filter material available on laboratory, pilot plant, and commercial scales. Significant information was obtained on the processing of organic filters, together with an understanding of the present state of the art of organic filter production, and of the future potential in this field.

This study ascertained the principals' provision of incentive for secondary schools' improvement in Oyo State. Two research questions guided the study and two null hypotheses were tested. The descriptive survey research design was adopted for the study. The population of the study was 8,701 which comprised 969 principals and 7,732 teachers in public secondary school principals in Oyo State. Proportionate Stratified sampling technique was used to draw 871 respondents made up of 97 principals and 774 teachers. Two versions of a 19 item researchers' developed instrument titled "Principals' Incentive Practices for Schools' Improvement Questionnaire (PIPSIQI)" and "Principals' Incentives Practices for Schools Improvement Questionnaire (PIPSIQII)" were used for data collection. Mean rates and standard deviation were used to answer the research questions, while t-test was used to test the null hypotheses at 0.05 level of significance. The findings of the study revealed among others that principals and teachers agreed that involving staff in decision making process to enhance their commitment in implementing the instructional programme, prompt attention to teachers on-the-job problems, praising teachers for excellent performance, assigning responsibility with commensurate authority to give teachers opportunity to demonstrate their skills and maintaining mutual relationship among others are teachers' incentive practices provided by secondary school principals in Oyo State. Based on the findings, it was recommended among others that there is need for State Ministry of Education to regularly organize interactive workshops that include both principals and teachers for working out modalities for improvement on provision of incentives for teachers. Conclusions were drawn and other recommendations were made.

This study ascertained principals' application of communication skills as a correlates of teachers' job performance in secondary schools in Anambra State. Three research questions guided the study and three hypotheses were tested at 0.05 level of significance. Correlation survey research design was adopted for the study. The population of the study comprised 6,396 secondary school teachers in Anambra State. Multi-stage sampling technique was used to sample 665 teachers for the study. The researchers-developed two sets of questionnaire titled "Principals' Communication Skills Questionnaire (PCSQ)" and "Teachers' Job Performance Questionnaire (TJPQ)" were used for data collection. The instruments were validated by three experts comprising two lecturers from the Department of Educational Management and Policy, and the other a specialist in Measurement and Evaluation all from the Faculty of Education, Nnamdi Azikiwe University, Awka. The reliability of the instruments were ascertained using Cronbach alpha and it yielded reliability co-efficient of 0.81, 0.78 and 0.76 for the three parts of PCSQ and 0.77 for TJPQ. The researchers together with five research assistants collected data for the study. A 98% return rate was recorded. Data analysis was done using Pearson's Product Moment Correlation Coefficient to answer the research questions and t-test to test the hypotheses. The findings of the study revealed among others that there is a moderate relationship between principals' application of verbal skill and teachers' job performance in secondary schools in Anambra State. It was also found out that there is significant relationship between principals' application of feedback skill and teachers' job performance in secondary schools in Anambra State. Based on the findings, it was recommended among others that Ministry of Education should sponsor principals to workshops, seminars and conferences to enable them up-date their knowledge and communication skills in order to create conducive school environment that would enhance teachers' job performance.

A Phase I sampling survey of cultural resources at the Camp Ripley Military Reserve in Morrison County, Minnesota was conducted in the fall of 1986 by the Institute for Minnesota Archaeology (IMA). This survey was authorized by the St. Paul District, Corps of Engineers as part of a program to assist the Army National Guard in preserving and managing cultural resources in the reserve. The IMA survey verified 8 find spots and 21 prehistoric and historic sites and gathered data on other sites in the Camp Ripley area. The nature and location of these resources hints that past human behavior was influenced by the natural environment in ways that can be measured from the material record. The developing pattern appears to fit site-environment models from adjacent regions of Minnesota.

Get involved! The Big Microplastic Survey is has been designed as a global citizen science project that anyone can participate in. It will gather scientific data and information about the microplastics problem from around the world and is aimed at individuals and organisations that have access to the coast, rivers and lakes and want to get involved. Visit [microplasticsurvey.org](https://microplasticsurvey.org/about-the-project) for more information! This shovel is designed with the project's sample sizes in mind: it is 10x10x2 cm, so you can quickly scoop up your samples to survey a beach for microplastics! This is a great project for kids, since the survey has been designed to be easily replicated by anyone!

Fractional imputation (FI) is a relatively new method of imputation for handling item nonresponse in survey sampling. In FI, several imputed values with their fractional weights are created for each missing item. Each fractional weight represents the conditional probability of the imputed value given the observed data, and the parameters in the conditional probabilities are often computed by an iterative method such as EM algorithm. The underlying model for FI can be fully parametric, semiparametric, or nonparametric, depending on plausibility of assumptions and the data structure. In this paper, we give an overview of FI, introduce key ideas and methods to readers who are new to the FI literature, and highlight some new development. We also provide guidance on practical implementation of FI and valid inferential tools after imputation. We demonstrate the empirical performance of FI with respect to multiple imputation using a pseudo finite population generated from a sample in Monthly Retail Trade Survey in US Census Bureau.

Discussion of "Impact of Frequentist and Bayesian Methods on Survey Sampling Practice: A Selective Appraisal" by J. N. K. Rao [arXiv:1108.2356]

Discussion of "Impact of Frequentist and Bayesian Methods on Survey Sampling Practice: A Selective Appraisal" by J. N. K. Rao [arXiv:1108.2356]

Discussion of "Impact of Frequentist and Bayesian Methods on Survey Sampling Practice: A Selective Appraisal" by J. N. K. Rao [arXiv:1108.2356]

The cross-classified sampling design consists in drawing samples from a two-dimension population, independently in each dimension. Such design is commonly used in consumer price index surveys and has been recently applied to draw a sample of babies in the French ELFE survey, by crossing a sample of maternity units and a sample of days. We propose to derive a general theory of estimation for this sampling design. We consider the Horvitz-Thompson estimator for a total, and show that the cross-classified design will usually result in a loss of efficiency as compared to the widespread two-stage design. We obtain the asymptotic distribution of the Horvitz-Thompson estimator, and several unbiased variance estimators. Facing the problem of possibly negative values, we propose simplified non-negative variance estimators and study their bias under a super-population model. The proposed estimators are compared for totals and ratios on simulated data. An application on real data from the ELFE survey is also presented, and we make some recommendations. Supplementary materials are available online.

This article is from BMC Infectious Diseases , volume 14 . Abstract Background: The HIV prevalence and incidence among men who have sex with men (MSM) are high. Unprotected anal intercourse (UAI) with male regular partners (RP) is an important but under-emphasized risk behavior. The current study aimed to describe the prevalence of UAI with regular partner and the associated multi-dimensional factors with UAI among MSM in Hong Kong, China. Methods: Respondent Driven Sampling method was used to recruit participants. A total of 285 participants were recruited, of whom 211 (75.1%) had had anal sex with RP in the last six months and their data were analyzed in this report. Weighed data were presented and logistic regression methods were fit. Results: Participants’ high risk behaviors in the last six months included high prevalence of having had UAI with RP (45.8%), having had non-regular male sex partners (NRP: 27.3%) and UAI with such partners (18.9%). Adjusted for socio-demographic variables, factors associated with UAI with RP included: 1) substances use prior to having anal sex (65.7% versus 43.8%; AOR =2.36; 95% CI =1.07-5.18), 2) worry that condom use symbolizes mistrust (67.9% versus 44.3%; AOR = 2.91; 95% CI =1.19-7.10), 3) a lower perceived degree of the RP’s acceptance of condom use (91.7% versus 38.3%; AOR = 22.70; 95% CI =6.20-83.10), and 4) a higher level of impulsivity (61.1% versus 35.0%; AOR =4.02; 95% CI = 1.62-9.97). Two of these four variables, substances use (ORm = 2.28, 95% CI = 1.01-5.16) and perceived lower level of RP’s acceptance of condom use (ORm = 17.22; 95% CI = 5.06-58.62) were selected by the forward stepwise logistic regression model. Conclusions: MSM with RP in Hong Kong is subjected to high risk of HIV transmission. Risk factors of UAI are multi-dimensional and interventions need to take into account factors of structural, interpersonal and individual levels.

This paper is devoted to establishing exponential bounds for the probabilities of deviation of a sample sum from its expectation, when the variables involved in the summation are obtained by sampling in a finite population according to a rejective scheme, generalizing sampling without replacement, and by using an appropriate normalization. In contrast to Poisson sampling, classical deviation inequalities in the i.i.d. setting do not straightforwardly apply to sample sums related to rejective schemes, due to the inherent dependence structure of the sampled points. We show here how to overcome this difficulty, by combining the formulation of rejective sampling as Poisson sampling conditioned upon the sample size with the Escher transformation. In particular, the Bennett/Bernstein type bounds established highlight the effect of the asymptotic variance of the (properly standardized) sample weighted sum and are shown to be much more accurate than those based on the negative association property shared by the terms involved in the summation. Beyond its interest in itself, such a result for rejective sampling is crucial, insofar as it can be extended to many other sampling schemes, namely those that can be accurately approximated by rejective plans in the sense of the total variation distance.

This paper is devoted to establishing exponential bounds for the probabilities of deviation of a sample sum from its expectation, when the variables involved in the summation are obtained by sampling in a finite population according to a rejective scheme, generalizing sampling without replacement, and by using an appropriate normalization. In contrast to Poisson sampling, classical deviation inequalities in the i.i.d. setting do not straightforwardly apply to sample sums related to rejective schemes, due to the inherent dependence structure of the sampled points. We show here how to overcome this difficulty, by combining the formulation of rejective sampling as Poisson sampling conditioned upon the sample size with the Escher transformation. In particular, the Bennett/Bernstein type bounds established highlight the effect of the asymptotic variance of the (properly standardized) sample weighted sum and are shown to be much more accurate than those based on the negative association property shared by the terms involved in the summation. Beyond its interest in itself, such a result for rejective sampling is crucial, insofar as it can be extended to many other sampling schemes, namely those that can be accurately approximated by rejective plans in the sense of the total variation distance.

This paper is devoted to establishing exponential bounds for the probabilities of deviation of a sample sum from its expectation, when the variables involved in the summation are obtained by sampling in a finite population according to a rejective scheme, generalizing sampling without replacement, and by using an appropriate normalization. In contrast to Poisson sampling, classical deviation inequalities in the i.i.d. setting do not straightforwardly apply to sample sums related to rejective schemes, due to the inherent dependence structure of the sampled points. We show here how to overcome this difficulty, by combining the formulation of rejective sampling as Poisson sampling conditioned upon the sample size with the Escher transformation. In particular, the Bennett/Bernstein type bounds established highlight the effect of the asymptotic variance of the (properly standardized) sample weighted sum and are shown to be much more accurate than those based on the negative association property shared by the terms involved in the summation. Beyond its interest in itself, such a result for rejective sampling is crucial, insofar as it can be extended to many other sampling schemes, namely those that can be accurately approximated by rejective plans in the sense of the total variation distance.

This paper is devoted to establishing exponential bounds for the probabilities of deviation of a sample sum from its expectation, when the variables involved in the summation are obtained by sampling in a finite population according to a rejective scheme, generalizing sampling without replacement, and by using an appropriate normalization. In contrast to Poisson sampling, classical deviation inequalities in the i.i.d. setting do not straightforwardly apply to sample sums related to rejective schemes, due to the inherent dependence structure of the sampled points. We show here how to overcome this difficulty, by combining the formulation of rejective sampling as Poisson sampling conditioned upon the sample size with the Escher transformation. In particular, the Bennett/Bernstein type bounds established highlight the effect of the asymptotic variance of the (properly standardized) sample weighted sum and are shown to be much more accurate than those based on the negative association property shared by the terms involved in the summation. Beyond its interest in itself, such a result for rejective sampling is crucial, insofar as it can be extended to many other sampling schemes, namely those that can be accurately approximated by rejective plans in the sense of the total variation distance.

This paper is devoted to establishing exponential bounds for the probabilities of deviation of a sample sum from its expectation, when the variables involved in the summation are obtained by sampling in a finite population according to a rejective scheme, generalizing sampling without replacement, and by using an appropriate normalization. In contrast to Poisson sampling, classical deviation inequalities in the i.i.d. setting do not straightforwardly apply to sample sums related to rejective schemes, due to the inherent dependence structure of the sampled points. We show here how to overcome this difficulty, by combining the formulation of rejective sampling as Poisson sampling conditioned upon the sample size with the Escher transformation. In particular, the Bennett/Bernstein type bounds established highlight the effect of the asymptotic variance of the (properly standardized) sample weighted sum and are shown to be much more accurate than those based on the negative association property shared by the terms involved in the summation. Beyond its interest in itself, such a result for rejective sampling is crucial, insofar as it can be extended to many other sampling schemes, namely those that can be accurately approximated by rejective plans in the sense of the total variation distance.

Since the introduction of social media, hundreds of studies have tried to assess how adolescents are affected by these media (for meta-analyses, see e.g., Huang, 2017; Liu & Baumeister, 2016; Liu, Wright, & Hu, 2018). To measure social media use, most of these studies have used retrospective surveys: Adolescents were asked to estimate the time they spent on social media in general (e.g., in a typical week) or within a specific time frame (e.g., in the previous week). In addition, a small but increasing number of studies have used experience sampling methodology (ESM) to measure social media use (Griffioen, Rooij, Lichtwarck-Aschoff, & Granic, 2020). In these studies, respondents used their cell phones to estimate the time they spent on social media in the previous hour or since the last survey (e.g., Beyens, Pouwels, van Driel, Keijsers, & Valkenburg, 2020). When relying on self-report measures, it is of utmost importance that such measures are accurate, indicating that they prevent systematic under- and over-reporting (Scharkow, 2016). In addition, these instruments should be valid, indicating that they measure what they are supposed to measure (i.e., validity) (Bryman, 2012; Flake & Fried, in press). After all, inaccurate and invalid self-report measures of social media use can lead to inaccurate estimations of social media effects (Scharkow, 2016).

Since the introduction of social media, hundreds of studies have tried to assess how adolescents are affected by these media (for meta-analyses, see e.g., Huang, 2017; Liu & Baumeister, 2016; Liu, Wright, & Hu, 2018). To measure social media use, most of these studies have used retrospective surveys: Adolescents were asked to estimate the time they spent on social media in general (e.g., in a typical week) or within a specific time frame (e.g., in the previous week). In addition, a small but increasing number of studies have used experience sampling methodology (ESM) to measure social media use (Griffioen, Rooij, Lichtwarck-Aschoff, & Granic, 2020). In these studies, respondents used their cell phones to estimate the time they spent on social media in the previous hour or since the last survey (e.g., Beyens, Pouwels, van Driel, Keijsers, & Valkenburg, 2020). When relying on self-report measures, it is of utmost importance that such measures are accurate, indicating that they prevent systematic under- and over-reporting (Scharkow, 2016). In addition, these instruments should be valid, indicating that they measure what they are supposed to measure (i.e., validity) (Bryman, 2012; Flake & Fried, in press). After all, inaccurate and invalid self-report measures of social media use can lead to inaccurate estimations of social media effects (Scharkow, 2016).

Since the introduction of social media, hundreds of studies have tried to assess how adolescents are affected by these media (for meta-analyses, see e.g., Huang, 2017; Liu & Baumeister, 2016; Liu, Wright, & Hu, 2018). To measure social media use, most of these studies have used retrospective surveys: Adolescents were asked to estimate the time they spent on social media in general (e.g., in a typical week) or within a specific time frame (e.g., in the previous week). In addition, a small but increasing number of studies have used experience sampling methodology (ESM) to measure social media use (Griffioen, Rooij, Lichtwarck-Aschoff, & Granic, 2020). In these studies, respondents used their cell phones to estimate the time they spent on social media in the previous hour or since the last survey (e.g., Beyens, Pouwels, van Driel, Keijsers, & Valkenburg, 2020). When relying on self-report measures, it is of utmost importance that such measures are accurate, indicating that they prevent systematic under- and over-reporting (Scharkow, 2016). In addition, these instruments should be valid, indicating that they measure what they are supposed to measure (i.e., validity) (Bryman, 2012; Flake & Fried, in press). After all, inaccurate and invalid self-report measures of social media use can lead to inaccurate estimations of social media effects (Scharkow, 2016).

71 pages ; 24 cm

Calibration methods have been widely studied in survey sampling over the last decades. Viewing calibration as an inverse problem, we extend the calibration technique by using a maximum entropy method. Finding the optimal weights is achieved by considering random weights and looking for a discrete distribution which maximizes an entropy under the calibration constraint. This method points a new frame for the computation of such estimates and the investigation of its statistical properties.