Questions tagged [selection-bias]
Bias introduced by non-random selection of observations, such that the sample is not representative of the underlying population.
52
questions
0
votes
0answers
15 views
How to handle retraining after model introduces bias
Here is my problem.
I am retraining a machine learning model to detect fraudulent purchases.
The training data is based on purchases and the target is whether or not they the purchase was considered ...
1
vote
0answers
33 views
Causal Inference: Selection Bias and Endogeneity [closed]
I've encountered lots of causal inference terms and jargons (under the Neyman-Rubin potential outcome framework), and I had questions regarding their relationships:
I know that exogeneity E(e|X) = 0 ...
1
vote
0answers
18 views
When we up-sample the training set, don't we introduce selection bias?
When doing supervised machine learning in the health or medical domains, we often have a target class that is relatively rare (e.g., prevalence 1-10% of cases). There are a few techniques we can do to ...
0
votes
2answers
47 views
Regression with endogenous dummy variables
Suppose I have 1,000 observations on variable Y, and I regress Y on just a dummy variable (d), in two different regressions. In the first regression, I set d equal to 0 for the first 500 observations, ...
2
votes
0answers
26 views
Which DAG would explain the lack of correlation between height and performance in NBA players?
A classic example of "selection bias" involves looking at the performance of professional basketball players. The example goes, among NBA players there is no correlation between height and ...
0
votes
0answers
19 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 ...
1
vote
0answers
27 views
Logistic regression for case-control studies
If I have designed a study where participants from 3 disease groups of fixed size were being sampled and suppose the three groups A, B and C are of sizes n_A=50, n_B=50 and n_C=100. Group A is a ...
0
votes
0answers
16 views
Adjusting for selection bias
I need to estimate the total financial impact of fraudulent cases in our business sphere. I have a dataset of audited cases where the selection process is guided by risk assessment and another very ...
1
vote
0answers
35 views
Intended selection bias
Sampling or selection bias is often presented as something that has to be overcome, avoided, or at least appropriately considered because it's a problem otherwise. I wonder how often situations arise (...
2
votes
1answer
22 views
Implicit Selection Effects in Mixed Models
I'm struggling with a question that I haven't seen talked about anywhere. Potentially it just illustrates some ignorance I have about how effects are estimated in mixed models.
Let's set up the ...
0
votes
0answers
19 views
Dealing with Heckman correction and sampling bias in an experiment without instruments
Imagine a randomised experiment where workers are offered a job for \$x, and they can choose to reject the offer, accept $x or propose some counteroffer x' > x. An equal number of workers are ...
2
votes
1answer
58 views
Is self-selection for a treatment a problem after all?
I have devised the following R code.
In this simulated dataset, we know that a certain treatment (e.g. a degree, an education) increases income by $ 1,000. Income is also caused by age.
In the first ...
1
vote
1answer
59 views
Is it useful to implement clustered SE in the probit-type models?
For my research, I am implementing a two-stage Heckman procedure. I am working with panel data, so I was wondering if it is common and actually needed to use clustered standard errors for the first ...
0
votes
0answers
9 views
Testing a sequence of random variables for hypothesis that distribution changes at single discrete point
Suppose we have an ordered sequence of independent random variables, $X_1, \ldots X_m, X_{m+1}, \ldots, X_n$,
where under the null hypothesis,
$X_{1..n}$ are identically distributed with
$$\mathbb{E}[...
0
votes
0answers
15 views
Lagged dependent variables: Is it safe to ignore bias over a long time horizon?
Suppose I have a Poisson model which investigates the effect of a county level policy on robbery counts. Here is the basic specification:
$$
\text{log}(y_{it}) = \theta y_{i,t-1} + \sum_i\text{County}...
4
votes
2answers
69 views
How would a statistician describe the problem with the figure in this publication? the solution?
I pointed out a problem with averaging values over time here https://www.researchgate.net/publication/344137839_SARS-CoV-2_binds_platelet_ACE2_to_enhance_thrombosis_in_COVID-19/comments in the ...
0
votes
0answers
9 views
Interaction term and selection
I am estimating a probit model, say :
$Pr(y = 1 \mid x_1, sex_.woman) = \Phi(\alpha + \beta_1 x_1 + \beta_2 sex.woman + \beta_3 x_1sex.woman)$
The independent variable of interest is $x_1$. I find ...
0
votes
0answers
6 views
Hidden Traits in Selection
Is there a name for an artefact of selection where you think you are selecting for a number of traits and you find, that in the set that is output, there is a hidden shared trait between everything in ...
0
votes
0answers
10 views
Bayesian Variable Selection Bias
Suppose that we have a design matrix $X$, $n\times p$, a vector $Y$, $n\times 1$ and our goal is to select between the following two linear regressions
$$Y_{i}=a+b_{1}X_{1}+\epsilon_{i}$$
$$Y_{i}=a+b_{...
2
votes
1answer
156 views
How does the support vector machine constraint imply that sample selection bias will not systematically affect the output of the optimisation?
I am currently studying the paper Learning and Evaluating Classifiers under Sample Selection Bias by Bianca Zadrozny. In section 3.4. Support vector machines, the author says the following:
3.4. ...
0
votes
1answer
28 views
What is meant by "the number of examples is reduced", and why is this the case?
I am currently studying the paper Learning and Evaluating Classifiers under Sample Selection Bias by Bianca Zadrozny. In section 3.2. Logistic Regression, the author says the following:
3.2. Logistic ...
4
votes
1answer
147 views
$\frac{P(x_1 \mid y, s = 1) \dots P(x_n \mid y, s = 1) P(y \mid s = 1)}{P(x \mid s = 1)}$ indicates that naive Bayes learners are global learners?
I am currently studying the paper Learning and Evaluating Classifiers under Sample Selection Bias by Bianca Zadrozny. In section 3. Learning under sample selection bias, the author says the following:
...
1
vote
1answer
18 views
How to estimate the impact of policy on labor supply if the policy causes death, too?
Suppose people can make only one of three choices A, B, C.
A = Death
B = Survive, Work
C = Survive, Not work
I want to study the impact of an exogenous policy on ...
1
vote
0answers
62 views
Is this referring to the true underlying distribution, or the distribution of our sample?
I am currently studying the paper Learning and Evaluating Classifiers under Sample Selection Bias by Bianca Zadrozny. In the introduction, the author says the following:
One of the most common ...
0
votes
1answer
66 views
Endogenous Sample Selection and Heckit Correction in relation to Research Question
I am researching the funding amounts of start-ups. I am calculating two models:
...
0
votes
0answers
13 views
Truncation based on two variables
I have some data, which has been constructed from multiple API pulls. Observations have an expiry date, $x_i$, which means that observations which expire before the API pull is done do not appear in ...
11
votes
3answers
394 views
Abraham Wald survivorship bias intuition
During World War II, the statistician Abraham Wald took survivorship bias into his calculations when considering how to minimize bomber losses to enemy fire. Wald noted that the study only considered ...
0
votes
1answer
133 views
Heckman Selection (Selection vs. Outcome equation)
A common example of the Heckman selection model involves wages, which are only observed if an individual chooses to participate in the labor force. The first stage probit model dependent variable is a ...
1
vote
2answers
49 views
How to solve selection bias in a survey?
Selection bias often happens in survey studies. For example, sending out a survey to 10,000 customers to ask whether they like one specific product or not. Only 10% of people respond and 80% of them ...
3
votes
1answer
380 views
Heckman with second step probit in R [closed]
The functions selection and heckit (package sampleSelection) support a binary dependent ...
1
vote
0answers
66 views
Selection bias in categorical independent variable in regression analysis
I have an issue with selection bias in my independent variable and I am uncertain of the best approach to correct for it.
I'm looking at soccer data and trying to make some forecasts on players from ...
0
votes
1answer
23 views
Alternatives to balance tables to examine selection bias
I was wondering if someone has ideas to statistically examine selection into programme participation? For example, would it make sense to present the results of a propensity score analysis?
Thank you
1
vote
0answers
17 views
Correcting for known imputation bias
I have a survey sample which includes income values by type of income for a significant number of high-income households. Some of the income data is measured, i.e. present in the responses of the ...
0
votes
1answer
313 views
Sample Selection Bias in Logistic Regression [duplicate]
I'm working on a classification problem where I expect
$True\ Positive\ Rate =0.999$
$True\ Negative\ Rate = 0.001$
To model this data, I have created a training set with an equal proportion of ...
6
votes
2answers
105 views
Favored methods for overcoming selection bias (special attention to healthcare fields)?
I am frequently measuring the effect of behavioral health treatment interventions on outcomes of interest. However, comparing the relative efficacy of different types of treatment is tricky - more ...
0
votes
1answer
75 views
What is the correct notation for expressing a mixture of distributions?
In a normal classification context, the training instances are drawn from a distribution $D$ which is defined over $X \times Y$, where $X$ is the feature space and $Y$ is the label space. When ...
0
votes
1answer
63 views
Sample selection bias
In Learning and Evaluating Classifiers under Sample Selection Bias, we suppose that
examples $(x, y, s)$ are drawn
independently from a distribution $D$ with domain
$X × Y × S$ where $X$ is the ...
0
votes
0answers
227 views
How to perform inference on inverse Mills ratio in Heckit estimation?
I want to estimate log(wages). Most wage estimations suffer from sample selection bias.
So I used the two step heckit procedure to correct for it.
The problem is that I get an insignificant inverse ...
1
vote
0answers
121 views
Can selection bias be solved by including control variables?
Omitted variable bias can be solved by including covariates that are omitted. However, can selection bias also be solved by including covariates?
0
votes
0answers
22 views
Logistic regression when only TRUE values are observed, but a control sample exists
I'm involved with a creel survey. We have reason to believe that anglers are keeping the larger fish they catch, or at least that a relationship exists between the size of caught fish and the ...
0
votes
2answers
244 views
Correcting sample selection bias of binary classifiers
In fraud investigation the number of detected fraud cases can be very small when compared to the total number of cases. This would also apply to rare desease detected in a very small number of people ...
0
votes
1answer
597 views
IV-estimation vs. Heckman's selection model
I am trying to grasp the difference between IV-estimation and Heckman's selection model.
I do that by considering the following set-up. My outcome if interest is y ...
2
votes
1answer
1k views
Why does weighted bootstrap have awful coverage even in toy example?
I'm interested in using the weighted bootstrap to correct for selection bias with a known form. I simulated a very simple example where the underlying data, $X$, are $N(0,1)$ and we are calculating a ...
6
votes
2answers
289 views
Is this actually an example of selection bias?
In Lesson 3, Chapter 3 of Miguel Hernán's edX course on causal diagrams, he presents this DAG:
It represents a study on the effect of hormone therapy on lung cancer (whether hormone therapy causes ...
3
votes
2answers
314 views
Usage of Heckman estimation for a random sample
My colleague argues to use a Heckman Model in the following case (Agricultural economics):
I have a random sample of farmers (n) of the general population N. In n some observations apply a given ...
2
votes
1answer
182 views
In what instances do we need to worry about Heckman correction for selection bias?
I understand that Heckman selection models attempt to address selection bias by running two-part models. In the oft cited example of determinants of wage offers: 1) we have a group of people who work ...
1
vote
0answers
75 views
How to handle bias due to self-selection in one group
I want to compare two or three social groups across a set of dependent variables, using data from a longitudinal survey.
The problem is that membership in one of the groups leads to a self-selection ...
5
votes
0answers
237 views
Correcting Sample Selection Bias given actual Distribution
I have two datasets, both from the same population:
The samples from the first survey are quite representative of the underlying truth. However, the second survey comes with a change in distribution ...
5
votes
4answers
357 views
Bias induced from model selection
I am trying to understand the following sentence
Cross-validation and information criteria make a correction for using the data twice (in constructing the posterior and in model assessment) and ...
2
votes
0answers
77 views
Adjusting for selection bias in a structural topic model
I want to build a structural topic model that adjusts for selection bias into the sample of entities about whom documents are written. I wanted to use the stm R ...
