Questions tagged [survey-sampling]

Creating samples from a well-specified population (human: all adults; registered voters; individuals with diabetes; students of a university; establishment: all firms; firms with employment of 200 or more in New York City; resource: all land of a country or a state/province) using a probabilistic method, with the purpose of inference to that specific population

Filter by
Sorted by
Tagged with
2
votes
1answer
382 views

Is a "trimmed" simple random sample still a simple random sample?

Suppose I have a population of size N (N is large, say a million), and I take a simple random sample of size 100. Denote the units in the sample as $u_1$, ... $u_{...
0
votes
1answer
24 views

How do you sample without a sampling frame?

I want to research the returns to education in my city as well as assess whether people who have studied abroad on average earn more than those who have studied within the country. The data required ...
0
votes
1answer
19 views

Estimating Population mean given a sample, and the population size

For my study, I have population size known (in order of millions), and a sample data (about 30 sample size). I can estimate population mean using 95% confidence interval by t distribution or normal ...
0
votes
0answers
17 views

How to weigh data points to match multiple dimensions?

I am trying to match the results of one survey to another. I would like sex and age to match, so first, I weigh each datapoint to match the distribution of male/female. However, when trying to weigh ...
0
votes
0answers
7 views

Detecting Hosting companies

I am conducting research where I have a list of "ranges" which may or may not host websites. If a range has many websites there is good chance that the overall company may be a hosting ...
0
votes
0answers
14 views

What is the effective sample size in conjoint experiments?

I am running a conjoint forced-choice survey experiment. The idea is to interview 500 respondents, that will perform 5 choice tasks choosing between 2 profiles. Profiles are fully randomized. My ...
0
votes
0answers
16 views

How to calculated weighted proportion for a binary variable

I have a dataset with 100 samples of a PPS survey, and the outcome (y) is a binary variable (Y/N). I've calculated the weights for each sample, and I'm wondering how to calculate (formula) the ...
1
vote
0answers
7 views

Nonresponse weight adjustments in multi-stage household surveys

I have a question about nonresponse weighting in complex sample surveys in multi-stage designs, like say, The US National Comorbidity Survey Replication (NCS-R), the Health and Retirement Study (HRS), ...
1
vote
0answers
17 views

Estimating the size of a population. Is the method employed valid?

Context: in North America there has been a Drug Overdose Epidemic for several years. In my own municipality, more people have died of overdose than of COVID during the pandemic. My workplace (a non ...
0
votes
0answers
5 views

Base weights/Relative weights when sampling strata change

I have survey responses from a survey where the sampling plan was stratification with sampling rates proportional to the square root of the number of households. The plan created 12 strata, and the ...
0
votes
0answers
21 views

Using chi square test to determine representativeness of sample drawn from known population

I am trying something out of my comfort zone and would appreciate any help provided! I have used census data to identify the frequency of age brackets in my town. I then sampled about a thousand ...
2
votes
1answer
87 views

How is the asymptotic justification of the "linearization by influence function method" for surveys established?

The survey R package recently adopted the "linearization by influence function" method of estimating covariances between domain estimates. The central ...
1
vote
0answers
18 views

Comparison between weighted and unweighted surveys

I was hoping to get your take on comparing the results of a weighted survey with an unweighted survey. I have the results of two different surveys conducted in my state. Survey A was a multi-stage, ...
0
votes
0answers
9 views

Survey sampling: are these 2 options the same?

I want to show the impact of a communication campaign on people's understanding of a specific topic. My question is about sampling. Let's assume we will measure the impact of the campaign by running a ...
0
votes
0answers
11 views

Comparability vs Representativeness: Comparing weighted & unweighted personnel surveys YOY when populations changed?

I am looking at designing a personnel survey and the aim this year is to apply weights to the survey to make sure that the results are representative of the population of all employees. The survey ...
0
votes
1answer
61 views

Sample Size determination at coutry level or states levels

A country is stratified into states. A researchers wants to carry out a survey with a main requirement of state level data representation. I wonder if sample size should be determine using country ...
2
votes
0answers
33 views

Using a sample of paid survey respondents to bias correct lower response rate among larger non-paid sample

I'm running a tracker survey on a website that has a low response rate of about 2%. The survey is not incentivized but the website traffic is large enough in volume I can always meet my sample target ...
0
votes
0answers
11 views

Book on probability proportional to size sampling

Can anyone please suggest a book to study probability proportional to size sampling with and without replacement and all its details ? Thank you
0
votes
0answers
28 views

Horwitz thompson estimates

Let U = (1, 2, 3, 4, 5, 6) be a finite population of size 6. Let $\ S_d $ = {($\ s_1 = (1, 2), \ s_2 = (3, 4, 5), \ s_3 = (1, 2, 6), \ s_4 $ =(3, 4, 6)} be the support of the design. Let P($\ s_i $) = ...
0
votes
0answers
28 views

Lahiri method of selection with replacement

Show that in lahiri method , the average number of draws to select one unit is $\frac{M}{\mu} $ bar where M is maximum of sizes for $\ x_i $ (i= 1,1,3....) and $\mu $ is $\frac {\sum_{i=0}^{N} \ x_i }...
3
votes
1answer
67 views

How to show that $\pi^*_i \pi^*_j - \pi^*_{ij} = \pi_i \pi_j - \pi_{ij}$ in a probability sample?

Let $\pi^*_i \quad i=1,2,\dotsc, N$ be the probability of not including the $i$th unit in the sample and let $\pi^*_{ij} \quad i, j = 1, 2,\dotsc, N$ be the probability of including neither the $i$...
1
vote
1answer
58 views

Survey sampling: How many participants per group (current, former, and potential users) should we recruit?

We are designing research in which we will explore the perception of users (C current, F former, and P potential) on a product. We apply the same questionnaire for each group adapting (verb tenses) ...
0
votes
1answer
55 views

Calculation of survey weights when some respondents are certain to be selected

I am helping with the design of a household survey which will use a four-stage sampling process, and I am unsure how to account for some elements of the population being selected with 100% probability....
1
vote
1answer
15 views

Do survey sample standard errors take into account/correct for anything else besides finite population?

Regular standard errors are biased when the data comes from a survey sampling design. The article "Wait Wait, Don't Tell Me... You're Using the Wrong Proc!" explains that the bias is due to ...
0
votes
1answer
27 views

Sample size of a vote transfer poll

A vote transfer poll asks the electorate about how they voted in the last election and how they would vote if the next election was now. With the result from both questions one could build a matrix of ...
1
vote
1answer
73 views

Specifying the survey design correctly in the R survey package

I have the results from a survey where a geographic area was stratified and power allocation (using the number of households in each stratum) was used to determine the number of surveys to send out to ...
0
votes
0answers
12 views

Need help on running sample data analysis -

Background: I have a survey data for a year 2019 where I received 50% response rate. I wanted to compare it with 2020 data which has 65% response rate. Question being asked in the survey is to rate ...
1
vote
1answer
35 views

Sample size for two-staged cluster sampling

I have a question about the R-package samplesize4surveys. I want to calculate sample size for tests of difference in proportions in a two-step clustered sampling ...
1
vote
1answer
49 views

Reconciling sample size calculations using Cochran's formula and Wald test

This is quite a basic question but I could not find a clear answer elsewhere. If we wish to draw a simple random sample to determine the estimated proportion of an attribute in the population, given a ...
0
votes
1answer
12 views

Why do you only need to identify the first cluster level in svydesign(), even if you have multi level clustering?

Going through the a course on Survey Weights and it says that even though a dataset may sample using 3 clusters (like Counties, City Blocks, and households), you only need to specify the first level ...
0
votes
1answer
31 views

Can I make conclusions with two independent samples?

Suppose I have a sample (n°1) that is statistically representative of a country A population, that I randomly selected. I want to give a survey to that sample to infer some things about the true ...
0
votes
2answers
208 views

Sample size needed for a survey with multiple questions

I want to make a survey with several questions and conclude those results for the whole population. For example, I want to estimate the following questions for my 1 million population : "do you ...
1
vote
0answers
31 views

ICC for cluster within cluster (survey package R)

So I'm not quite sure about the terminology but what ever it's called the actual scenario is straight-forward. I'm dealing with a two-stage cluster sample. It's also stratified but let's set that to ...
0
votes
1answer
18 views

Matching a Subsample with Complex Survey Data

I am completing a study to analyze the effects of a policy treatment on a sub-population of adults (low-income adults, specifically) that are represented in a complex, nationally representative survey....
0
votes
1answer
50 views

How to operationalize stratified, cluster survey sample “standard of the mean” in Excel

I have a question on the analysis of complex survey design. Basically, I am trying to replicate the SAS Surveymeans procedure in Excel in order to understand how to operationalize the equations to ...
1
vote
1answer
27 views

Appropriate statistical test for paired survey data?

I'm somewhat new to statistics, so forgive me for a rather elementary question. I'm not looking for someone to do any sort of in-depth explanation, rather would just like to be pointed in the right ...
1
vote
0answers
9 views

Random sampling in quantitative studys [closed]

Many empirical studies are based on random samples which are used to draw conclusions about a corresponding population. In this context, the importance of a random sample is often pointed out. As to ...
3
votes
0answers
17 views

How can I infer the precision of my sample?

Let's say I have a survey about the quality of my product. But only 30% of my customers answered. If, for instance, the average rate for my product quality is 7, what can I infer from the real rate? I ...
0
votes
2answers
23 views

means and errors for election polls

I'm trying to assess how to compute the errors associated with a numbers of likely voter polls of the Warnock Georgia Senate race. I have estimates of the margin of victory from 9 surveys of varying ...
0
votes
1answer
300 views

What goes wrong with post-stratification if a combination of values does not exist in the sample? How to fix it?

This question is both about the "survey" package in R and about the mechanics behind it. I'm more interested in the mechanical reasons why this package fails to create weights when ...
1
vote
1answer
40 views

Why two different surveys will not give the exact same result?

I faced a challenge recently with our commercial team about our annual market survey result. As you can guess, our commercial team has no background in statistic or math etc. A brief introduction, ...
0
votes
0answers
191 views

How to calculate weighted average based on two variables: sample size and pollster grade?

Let's say I have a dataset with three columns with 5 rows and 3 columns. Each row represents a separate poll result of a single political party. The columns are poll prediction, sample size of the ...
0
votes
0answers
36 views

Expectation of sample mean for a population group using simple random sampling

As we know, in case of simple random sampling the sample mean, $\bar{x}$, is an unbiased estimator of the population mean, $\mu$ (for a prove, see, for example, here). I assume a similar case can be ...
1
vote
0answers
19 views

t-test for likert scales questionnaire [closed]

I am working on a research assessment where I intend to ask individuals to submit a questionnaire based on public perceptions of national security. Participants will answer statements based on a 5-...
2
votes
0answers
16 views

Raking weights - How can they possibly recover the joint distribution?

So I've recently encountered raking weights as a way to obtain weights for population level estimates: https://www.pewresearch.org/methods/2018/01/26/how-different-weighting-methods-work/. My question ...
1
vote
0answers
105 views

How to compute weights using logistic regression

I'm not interested in creating a logistic regression model which is weighted, I'm interested in using a logistic regression model to compute the weights of a survey. It seems that, given the weights ...
1
vote
0answers
24 views

How should one compute confidence intervals for means computed with inverse propensity weights (IPW)?

Inverse propensity weighing involves a machine learning model that takes features and outputs the predicted probability that this person is in the sample. Let $w_i$ be the inverse of the output for ...
1
vote
0answers
34 views

Testing differences between census and survey

I am trying to compare voter turnout for two consecutive elections, one in 2015 and one in 2019. I have turnout data for several geographic locations and age and gender groups. The goal is to see if ...
1
vote
0answers
48 views

Finding the "most representative" variables of a population

Most polls use the so-called quotas method to obtain their sample. They draw candidates upon a large panel of people and add one-by-one each responding candidate to the sample unless a certain quota ...
3
votes
0answers
53 views

Sampling from a skewed distribution

So I have a dataset with around 40,000 unique free text descriptions of purchased goods. I also know the spend on each of these unique descriptions, and the distribution of spend is long tailed. Some ...