Questions tagged [survey-weights]

survey weights are used when data are collected according to a probability sampling design with unequal probabilities of selection and/or response

69 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
6
votes
0answers
5k views

When to use longitudinal (panel) weights vs cross-section weights in complex surveys

I'm currently working with a longitudinal dataset, the Kauffman Firm Survey. The survey tracks about 5000 firms starting from 2004 - 2009. Firms die out over the years. It has both cross-sectional ...
3
votes
0answers
26 views

Defining quantiles for complex survey samples

I am looking to accumulate a comprehensive list of definitions for quantiles under complex sampling that have been published or implemented in software. I'm not worrying about the separate problem of ...
3
votes
1answer
518 views

Replicate weights and the Current Population Survey

The Current Population Survey’s Annual Social and Economic Supplement (abbreviated, oddly, as ASEC) is the USA’s longest running and most detailed annual survey of income and employment. Along with ...
3
votes
0answers
145 views

multilevel longitutudinal model with missing data and survey weights

I'm estimating a multilevel longitudinal model in lme4, using publicly available survey data. The data include sampling weights, and there is substantial missing data (over 27%). I understand multiple ...
3
votes
1answer
102 views

How do you use Bayesian methods to analyze the American Community Survey Public Use Microdata Sample?

The American Community Survey (ACS) Public Use Microdata Sample (PUMS) comes with weights generated with the replication weight method. There are software packages such as the ...
2
votes
1answer
69 views

Matching biometrics with NHANES

Good morning everyone, I'm trying to figure out how to do some matching with NHANES datasets. Basically, I have a separate population of participants in a weight loss program, for which we do not ...
2
votes
0answers
30 views

Modeling rates with complex survey data

I have data derived from a stratified, cluster random sample with post-stratification weights (corresponding to the inverse probability of response). These are person-level data. Let's say I want to ...
2
votes
0answers
37 views

What do I do about unequal sampling probabilities for second-stage sampling units in a PPS sample?

Say that I am drawing a two-stage simple random sample. The first stage selectes a unit that is a cluster, the second stage selects units within the cluster. There are two different types of units ...
2
votes
0answers
304 views

Equivalence of svyglm and glm for simple random surveys

I have been exploring the use of the svyglm function in R's survey package to analyse surveys with both equal and unequal sampling probabilites. For an unequal ...
2
votes
0answers
445 views

Test difference of population proportion and weighted sample proportion

I want to test for differences of the known proportion of the population vs. the proportion of a sample. The sample is weighted by sampling weights. The sum of weights is equal to the size of the ...
2
votes
0answers
44 views

Should Mixed effects models with repeated cases have the same results as Weighted Mixed effects model?

I have a conceptual question that might also be a question about STATA and GLLAMM. Conceptually: Should duplicating some groups in a mixed effects model have the same effect as giving those groups a ...
2
votes
0answers
24 views

Problem computing population quantiles with survey micro data

All the major federal surveys come (American Community Survey, Current Population Survey, others) come with survey weights, such that the individual household observations times the population weights ...
2
votes
0answers
297 views

How to include 'Survey Weights' in a Proportional-Odds (Cumulative Logit) model

I am looking to design a Bayesian multilevel Proportional Odds model, which incorporates the use of survey weights in JAGS. The inclusion of weights for linear and Poisson models appears ...
2
votes
1answer
312 views

Reduce 'oversampling' when using bootstrapping

I'm wanting to use bootstrapping to estimate the sampling distribution of values over a geographical area. However, the samples I'm using are more heavily sampled in some areas that in others, for ...
2
votes
0answers
639 views

How meaningful is to pool data from different surveys on the same target population?

Apologies for cross posting This is a very theoretical question for me but I would like to find an answer as I might want to use this in the (near) future. In many cases same questions are used in ...
2
votes
1answer
836 views

Post stratification weights and the survey package in R

I have survey data that needs to be weighted, and to help me with this task, I have access to the full joint distributions of the variables I want to use. As I understand it, I should use the ...
1
vote
0answers
5 views

Impact of recoding variables on sampling weights

I'm working on a dataset with longitudinal survey data that includes final post-stratification weights. I want to recode some of the demographic variables, such as race and income, to combine several ...
1
vote
0answers
18 views

Are probability weights “relative”, i.e. can they be rescaled and work in the same way?

I am using survey data from different countries, and I pool them together for part of the analysis. Now, weights puzzle me for two reasons: 1) some of them are below 0 (i.e. the probability of being ...
1
vote
0answers
33 views

Latent time-series with multiple observations per time point

I have a latent time-series $\psi_t$ where for each time point $t$ I have multiple observations $y_t$, generated from a distribution dependent on $\psi_t$. The number of observations $n_t$ some time ...
1
vote
0answers
41 views

Which model to use for analyzing complex expenditure survey data (Regression, ML …)

I have a sample of $15,000$ households (survey on households' expenditures) of which only 3% have zero consumption. I would like to explain electricity expenditures (Elec_exp_hh) by income (TAExp_hh) ...
1
vote
0answers
66 views

Do we use weighted or unweighted data when doing categorical data analysis?

Im quite confuse if I should use a weighted or unweighted survey data when doing categorical data analysis such as Chi-square, G2, concordant or discordant analysis, etc. Basically, these analyses ...
1
vote
0answers
16 views

How do I create survey weights without sampling design data?

Suppose I have a survey for which data was collected conveniently, but there aren't weights present. The data set does have features like demographic data (e.g. age, gender, urban/rural location, ...
1
vote
0answers
191 views

Utilizing ipfraking to apply post-stratification weights for a Community Based Survey in STATA

I am a community data analyst for a small non-profit in South Florida. We are cleaning and preparing a local community survey for analysis and need to apply post-stratification weights to the survey ...
1
vote
1answer
57 views

How does the TraMiner Package Calculate Standard Error Using Weighted Data?

The TraMiner Package includes an option to include sampling weights in the analysis. However, I haven't found any discussion in the package documentation (or associated user manual) of how standard ...
1
vote
0answers
49 views

How do I convert a survey scale [7-point, -3 to 3] to a 7-point scale [1-7]?

I am working with a survey scale that is from -3 to 3. I have a mean value of .94 and I want to identify if there are ceiling effects, but I need to change the entire scale to 1-7 in order to ...
1
vote
0answers
62 views

What is the impact of seed weights in raking (iterative proportional fitting)?

In survey weighting, I've seen that first a design weight adjustment is made (to reflect over- or under-sampling), and then a non-response adjustment is made (to reflect groups that are less likely to ...
1
vote
0answers
66 views

Benefit of scaling survey design weights

In the european social survey the design weights are scaled to the sample size (see quote and source): As with the design weights also the post-stratification weights are scaled to the sample size, ...
1
vote
0answers
57 views

The set of variables used for weighing-up changes the resulting estimates

When comparing the effects of the set of variables passed to the svyby function on the resulting estimates and standard errors, I discovered that weighing up a single variable and two variables yields ...
1
vote
0answers
26 views

ulti-cohort longitudinal panel data: how to apply weights to models that incorporate variables from different years?

I'm running Stata 15.1 on OSX. The dataset in question comes from The American Panel Survey in which three cohorts of participants filled out surveys each month (some of which measured the same items) ...
1
vote
0answers
26 views

How Much More Information (as bits) is Gained (if any) from a Ranking vs. Likert Scale Survey of 100 Questions's / 1-5 Scale?

All other sources of noise controlled, I, know that asking users to rank their preference on a collection of items from "best" (5) to "least" (1) in lieu of having them rate each one individually on a ...
1
vote
0answers
12 views

when is it ok not to weight a national database analysis

I am running an analysis using a national database that has weights available to produce national estimates. However, I am comparing 2 procedures that are very specific to research hospitals only. ...
1
vote
1answer
52 views

Testing change over time with different sampling frames

In 2017 a representative sample survey of 400 schools was conducted with a stratified two-stage sample design. The sampling frame was an earlier school census. In 2018, a second round of the survey ...
1
vote
0answers
742 views

Combining multiple survey datasets with design weights in a single model

The analysis of survey data with design weights is a difficult topic. In my case, I am working with two datasets: 1) NHANES data, which makes use of cluster sampling and stratification, and 2) Survey ...
1
vote
0answers
106 views

Accounting for complex survey design for structural equation modeling

I am using proc calis procedure in SAS to perform structural equation modeling (SEM). I have a nationally representative survey data with person-level weights, strata and cluster variables. However, I ...
1
vote
0answers
89 views

Applying robust regression to complex survey data

My team is conducting an analysis using a large dataset of health data from >150 demographic and health surveys with the aim of identifying optimal metrics to quantify early childhood growth at the ...
1
vote
0answers
91 views

Can analytic weights be converted into sampling weights?

I am running a linear probability model, so I know I need to correct for heteroskedasticity. Since I know the variance of the error (from theory) to be $y(\pmb x)(1-y(\pmb x))$ where $y$ is the ...
1
vote
0answers
136 views

How to weigh samples (representative of population) when comparing group means

I want to clarify my understanding of using sample weights when comparing means of sub-groups of a sample. Here is an artificial case with data that can be replicated in r (see code below): Let’s ...
1
vote
0answers
88 views

sampling and weighting algorithms for political survey

I'd like to find a readable reference (code or algorithmic description) for the sampling (méthode des quotas) and weighting (redressement des résultats bruts) algorithms used in political surveys. In ...
1
vote
0answers
129 views

Does exists a routine to perform Sensitivity analysis after weighting by inverse probability of treatment weight?

I am employing a propensity score matching to get the treatment group and the control group balanced. I employ the inverse probability weights times some sampling weights (I am using a survey, hence I ...
1
vote
1answer
24 views

Harmonizing variables across countries

Say, I have run an experiment in 2 separate countries, the U.S. and Tchad. While the outcome was isomorphically measured in both settings, one key background variable was not. Specifically, income was ...
1
vote
0answers
150 views

Visualizing ACS PUMS data with weight / PWGTP

I am working with American Census PUMS microdata, a yearly sample that includes a total weight per record and 80 replicate weights. I'm unsure if it makes sense to do descriptive statistics such as ...
1
vote
0answers
39 views

Estimating variance of data with a non-response bias

I have a set of scores whose mean is shifted by a non-response bias and whose variance is reduced as a result of the same bias. I know how to improve the estimate of the mean using non-response ...
1
vote
0answers
28 views

Should I calculate poststratification weights on the entire dataset, or just the test set?

I'm currently working on a classification task where certain features were intentionally oversampled, so I calculated using the R survey package to adjust my model ...
1
vote
0answers
990 views

How to handle skip patterns with complex sample survey data?

I have a question about analyzing complex sample survey data. In most statistical books on the subject, there are sections that emphasize the need to deal with item missing data and unit missing ...
1
vote
0answers
120 views

How calculate Gini coefficient (unbiased) and Lorenz Curve with stratified sample?

I'm working with a stratified sample by minimum variance method with 3 levels that becomes at 1176 stratum. The sample comes from finite population of income taxes data. I'm looking for how calculate ...
1
vote
1answer
31 views

How to deal with disparate survey response rate from different regions?

Hi & thank you all in advance for your help! I sent out a survey [to examine teacher satisfaction] to 3 school districts in New York state. District A is large, district B is medium, & ...
1
vote
1answer
87 views

Sample weights interpretation

The sample followed a two-stage design. In the first stage the primary sampling units (enumarating areas, EA) were randomly selected. In the second stage, in each EA, 10 secondary sampling units (...
1
vote
0answers
62 views

Re-weighting a survey after resampling with replacement been already used

I'd love to hear some experts' advice on a survey I'm working on. Let's assume a survey being conducted on a sample of community organizations. A public database (the sample frame, but almost a ...
0
votes
0answers
9 views

Removing weights/strata from weighted data (NHANES)

I'm currently working with NHANES dataset, and I'm hoping to introduce the dataset to people without any statistics background for educational purposes. However, the dataset is weighted, and it might ...
0
votes
0answers
11 views

Take into account Sensitivity and Specificity when calculating Estimates/CI's

I'm trying to thing about how to calculate confidence intervals in the presence of known measurement error for some test protocol. Let's assume we're doing a sample survey in which we're performing ...