Estimating distribution functions from survey data

Chambers, Ray; Dunstan, Ross

doi:10.1093/biomet/73.3.597

Cited by 213 publications

(136 citation statements)

References 10 publications

Supporting

Mentioning

136

Contrasting

Order By: Relevance

“…Note that the superscript CD in (7) refers to the fact that it is based on evaluating the area j expected value functional defined by integrating with respect to the area j version of the distribution function estimator proposed by Chambers and Dunstan (1986). Tzavidis et al (2008) note that, under simple random sampling within the small areas, predictor (7) can also be derived from the design-consistent and model-consistent estimator of the finite population distribution function proposed by Rao, Kovar and Mantel (1990).…”

Section: An Overview Of Unit Level Models For Small Area Estimationmentioning

confidence: 99%

Small area estimation via M-quantile geographically weighted regression

Salvati

Tzavidis

Pratesi

et al. 2010

TEST

View full text Add to dashboard Cite

Abstract.One popular approach to small area estimation when data are spatially correlated is to employ Simultaneous Autoregressive (SAR) random effects models to define the Spatial Empirical Best Linear Unbiased Predictor (SEBLUP). See Singh et al. (2005) and . SAR models allow for spatial correlation in the error structure. An alternative approach that incorporates the spatial information in the regression model is to use Geographically Weighted Regression (GWR). See Brunsdon et al. (1996) and Fotheringham et al. (1997). GWR extends the traditional regression model by characterising the relationship between the outcome variable and the covariates via local rather than global parameters. In this paper we investigate GWR-based small area estimation under the M-quantile modelling approach (Chambers and Tzavidis, 2006). In particular, we integrate the concepts of outlier-robust small area estimation and borrowing strength over space within a unified modelling framework by specifying an M-quantile GWR model that is a local model for the M-quantiles of the conditional distribution of the outcome variable given the covariates. This model is then used to define an outlier-robust predictor of the small area characteristic of interest that also accounts for spatial association in the data. An additional important spin-off from applying the M-quantile GWR small area model is more efficient synthetic estimation for out of sample areas. We demonstrate the usefulness of this framework through both model-based as well as design-based simulation, with the latter based on a realistic survey data set. The paper concludes with an application to environmental data for predicting average levels of the Acid Neutralizing Capacity at 8-digit Hydrologic Unit Code level in the Northeast states of the U.S.A.

show abstract

Section: An Overview Of Unit Level Models For Small Area Estimationmentioning

confidence: 99%

Small area estimation via M-quantile geographically weighted regression

Salvati

Tzavidis

Pratesi

et al. 2010

TEST

View full text Add to dashboard Cite

show abstract

“…Textbooks rarely discuss RTO other than to caution against dropping the constant term from a regression, but RTO is appropriate or even necessary in some circumstances. 24,25 Theoretically, RTO is a special case of regression with constant term. 26−30 In reality, before and after a peptide is eluted, the signal of the peptide should be null, therefore RTO is more appropriate than the regression with constant term.…”

mentioning

confidence: 99%

pQuant Improves Quantitation by Keeping out Interfering Signals and Evaluating the Accuracy of Calculated Ratios

et al. 2014

View full text Add to dashboard Cite

In relative protein abundance determination from peptide intensities recorded in full mass scans, a major complication that affects quantitation accuracy is signal interference from coeluting ions of similar m/z values. Here, we present pQuant, a quantitation software tool that solves this problem. pQuant detects interference signals, identifies for each peptide a pair of least interfered isotopic chromatograms: one for the light and one for the heavy isotope-labeled peptide. On the basis of these isotopic pairs, pQuant calculates the relative heavy/light peptide ratios along with their 99.75% confidence intervals (CIs). From the peptides ratios and their CIs, pQuant estimates the protein ratios and associated CIs by kernel density estimation. We tested pQuant, Census and MaxQuant on data sets obtained from mixtures (at varying mixing ratios from 10:1 to 1:10) of light-and heavy-SILAC labeled HeLa cells or 14 N-and 15 N-labeled Escherichia coli cells. pQuant quantitated more peptides with better accuracy than Census and MaxQuant in all 14 data sets. On the SILAC data sets, the nonquantified "NaN" (not a number) ratios generated by Census, MaxQuant, and pQuant accounted for 2.5−10.7%, 1.8−2.7%, and 0.01−0.5% of all ratios, respectively. On the 14 N/ 15 N data sets, which cannot be quantified by MaxQuant, Census and pQuant produced 0.9−10.0% and 0.3−2.9% NaN ratios, respectively. Excluding these NaN results, the standard deviations of the numerical ratios calculated by Census or MaxQuant are 30−100% larger than those by pQuant. These results show that pQuant outperforms Census and MaxQuant in SILAC and 15 N-based quantitation.M uch progress has been made in mass spectrometry (MS)-based quantitative proteomics in recent years, as evidenced by numerous applications, such as biomarker discovery, 1 study of chromatin assembly and disassembly, 2 identification of insulin signaling targets, 3 and protein posttranslational modification (PTM). 4 Among the most commonly used quantitative strategies are full MS scan-based quantitation methods, such as SILAC (stable isotope labeling with amino acids in cell), 5 15 N-labeling, 6 and 18 O-labeling. 7 In these strategies, proteins are metabolically labeled with stable isotopes, digested into peptides, and then analyzed using liquid chromatography (LC)-MS/MS. Quantitation software tools are designed to extract the intensities of pairs of light (L, unlabeled) and heavy (H, labeled) peptides from full MS scans. The relative abundance ratio of a protein between two conditions is then calculated based on the ratios of its constituent peptides. 8 For high-complexity samples such as whole cell lysates, it is not uncommon that a peptide coelutes with another peptide or a nonpeptide contaminant of a similar m/z value. 9 The interference caused by coeluting ions of similar m/z values can seriously compromise the accuracy of quantitation. 10,11 We examined two leading quantitation software tools Census 12 and MaxQuant, 13 and found that a lot of the peptide quantitation results ...

show abstract

“…It can be implemented with multistage sampling designs, as the proposed estimators are based upon first-order inclusion probabilities and a regression estimator. Alternative estimators proposed by Chambers and Dunstan (1986) and Rao et al (1990) can be slightly more accurate than the proposed estimators. However, in order to compute these alternative estimators, it is necessary to know the auxiliary variable for the entire population.…”

Section: Discussionmentioning

confidence: 93%

“…An exhaustive review of estimators of the distribution function and quantiles can be found in Dorfman (2009 Chambers and Dunstan (1986) is based on the following heteroscedastic regression model…”

Section: Estimators Of Quantilesmentioning

confidence: 99%

On Estimating Quantiles Using Auxiliary Information

Berger

Velasco-Muñoz

2015

Journal of Official Statistics

View full text Add to dashboard Cite

We propose a transformation-based approach for estimating quantiles using auxiliary information. The proposed estimators can be easily implemented using a regression estimator. We show that the proposed estimators are consistent and asymptotically unbiased. The main advantage of the proposed estimators is their simplicity. Despite the fact the proposed estimators are not necessarily more efficient than their competitors, they offer a good compromise between accuracy and simplicity. They can be used under single and multistage sampling designs with unequal selection probabilities. A simulation study supports our finding and shows that the proposed estimators are robust and of an acceptable accuracy compared to alternative estimators, which can be more computationally intensive.

show abstract

Estimating distribution functions from survey data

Cited by 213 publications

References 10 publications

Small area estimation via M-quantile geographically weighted regression

Small area estimation via M-quantile geographically weighted regression

pQuant Improves Quantitation by Keeping out Interfering Signals and Evaluating the Accuracy of Calculated Ratios

On Estimating Quantiles Using Auxiliary Information

Contact Info

Product

Resources

About