Stack Exchange Network

Stack Exchange network consists of 175 Q&A communities including Stack Overflow, the largest, most trusted online community for developers to learn, share their knowledge, and build their careers.

Visit Stack Exchange

Questions tagged [observational-study]

An observational study involves purely observing the state of the world without manipulating it.

2
votes
2answers
17 views

Matching covariate selection- should we not match on binary features where overwhelming majority of subjects fall in one category?

I am trying to investigate if there is a relation between Occupational Therapy (OT) dosage for stroke patients and patient recovery. I have separated the patients into 2 groups by the amount of ...
1
vote
1answer
29 views

After performing Matching with replacement, should tests (t-test/ KS test) to evaluate balance between the matched groups include repeated subjects?

I am using Genetic Matching to infer causality from observational data. Because I am matching with replacement, the matched Control group has multiple instances of some of the same subjects. In this ...
3
votes
1answer
58 views

Interpretation of intercept only random effects models

I am estimating the global risk of infection risk in a population of patients, but these patients are clustered in hospitals and wards/departments. If I just take the crude prevalence (infected ...
0
votes
1answer
117 views

In the superpopulation framework of causal inference, what is the necessity of assuming the outcomes, treatment and covariates are jointly iid?

In the textbook "Causal Inference for Statistics" by Rubin and Imbens, the following argument is made on pg. 39: "In part of this text we view our sample of size N as a random sample from an ...
0
votes
1answer
21 views

R- Trouble understanding what loss function is being used by Genmatch (genetic matching) algorithm

I am having some trouble understanding what loss function is being minimized to ensure that we are converging towards the best set of weights in the Genmatch function in R. I was reading the paper on ...
0
votes
0answers
16 views

R- trouble understanding how setting estimand to “ATE” is affecting matching in “Matching” package

I am working on a project where I am using observational data from patients and trying to find a causal relationship on how Treatment dose affects Patient recovery. Since the data is observational, I ...
0
votes
0answers
18 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
0answers
10 views

Econometric Models in Economic Development Theory

I have been reading some Economic Development and Policy Research papers and I realise there is extensive employment of econometric tools and models. For example, one of the papers used an Oaxaca ...
4
votes
1answer
37 views

How to name a bias that is not quite the “immortality bias”

Strange question from me, but try to follow me. I do not remember or name correctly a type of bias in cohort study which is pretty clear in my mind. I try to explain: Let's assume that I want to test ...
1
vote
0answers
8 views

Estimating incidence on data with limited observation

I have a data of many individuals and wish to know whether a certain event occurred during a specific time frame with each one. The problem is that each individual was observed only a certain portion ...
0
votes
1answer
59 views

Conditional treatment effect and average treatment effect under no unmeasured confounders (ignorability)

The conditional treatment effect (CATE) is defined as: $$ \tau(x) = \mathbb{E} \left[ Y^1- Y^0 \mid X = x \right], $$ the average treatment effect (ATE) is defined as $$ \tau_{ATE} = \mathbb{E}\...
0
votes
0answers
46 views

Cohort Study Sample Size and Multiple Comparisons

I'm designing an epidemiological retrospective cohort study with a large number of exposures and outcomes, and I'm trying to figure out how many subjects I'll need in order to run all my analyses. The ...
0
votes
0answers
85 views

Inference from regression in presence of multicolinearity

I would like to estimate the effect of one independent variable on the predicted variable in the purely observational study. On the other hand I know that there exists another independent variable, ...
1
vote
1answer
19 views

Evaluating propensity score matches- what to do when ratio of variances or standardized means of difference go to infinity?

I am working on a project where I am comparing the effects of a particular treatment on patients with other patients who didn't receive the treatment. As I am trying to replicate a randomized ...
0
votes
0answers
28 views

Double Mendelian Randomization: Reasonableness & False Positive Concerns

I've been interested in mendelian randomizations (a form of instrument variable analyses) as a method for gaining insight into causal relationships between risk factors and outcomes. An example i ...
0
votes
1answer
20 views

How can I determine how often an event occurs based on collected data how long one has to wait for an occurence

This is an experiment I can only observe, not design/change. I make the following observations: A police officer frequently monitors the same traffic location in the same manner. I see the officer ...
0
votes
0answers
27 views

Evaluating Impact of Unobserved Confounders - Is the E-Value applicable for Non-Significant Group Differences?

I have conducted an analysis of treatment effects based on observational data (via statistical matching). As suggested by VanderWeele and Ding (2017), I want to evaluate the sensitivity of my analysis ...
4
votes
2answers
385 views

In propensity score matching, should a variable used in exact matching also be used in the model?

In propensity score matching, we can match on variables exactly. For example, we can match males with other males only. Additionally, the variable can be specified in the model. Here's some SAS code ...
0
votes
0answers
26 views

Model mean/median change per observation time?

A Cox proportional hazards model makes it possible to investigate how an independent variable affects the risk of a dichotomous state occurring per observation time. Is it possible to model (A Cox ...
2
votes
1answer
70 views

Why fixed design analysis for observational data

Why do we use a fixed design analysis of regression coefficients, even for observational data, where the design is not fixed? For instance: $Var[\hat \beta]=(X'X)^{-1}\sigma^2$ is conditional on $X$. ...
1
vote
2answers
47 views

Selecting the control group in a before-after study

I am interested in analyzing the effect of a specific change in traffic conditions on the amount of road accidents in a city. I need to select a comparison group; my approach is to select from ...
0
votes
0answers
86 views

Prospective studies and variable updates

In a cohort study, I'm measuring the apparition of a disease over time and confronting it against a variable, which we'll call X. This is a very straight-forward analysis where I have the baseline ...
0
votes
0answers
15 views

convert case-control to cohort

We know that a cohort is "stronger" than a case Control study. So, if I have a case control study I start with the outcome (cancer) then go and look back to see if the subject was a smoker or not and ...
1
vote
0answers
21 views

Matching inflation

I have data on a few millions of patients, about 1000 of them are cases, that is, they were diagnosed having a certain disease at some timepoint in their life. I think I basically have two options: 1)...
2
votes
1answer
393 views

Cox Proportional and Pooled logistic regression in a observational cohort study - laymans terms

So my brain is just not understanding the difference between the two above. I am currently writing a literature review and have to explain the significance of what was found in the research. The ...
0
votes
1answer
10 views

Independence of time intervals in ANOVA?

I am not sure how the independence assumption in ANOVA applies in this scenario... We have observational data on the foraging depth of whales across the summer separated into time intervals. We want ...
1
vote
0answers
22 views

case-control study with cross-sectional data

I have a General Practitioner dataset for several thousand patients, taken at a single snapshot in time (let's call it time X). Patients that have died since the database was set up are therefore not ...
0
votes
0answers
13 views

What potential bias is there to conduct a full study based on the results of a pre-study?

Say, ultimately some researchers want to conduct a full study which is a comparative study of examining Drug A's effectiveness vs. other Drugs for disease Z. Effectiveness is measured by how many ...
2
votes
0answers
30 views

How to combine observational studies

I am trying to show the releationship between a drug and an outcome in a particular setting. Using a systematic review, I have found 18 studies addressing this topic. Among those, the highest quality ...
2
votes
2answers
51 views

Differences in potential explanations between observational and experimental studies

Imagine we have a categorical variable, A—for example, whether somebody owns a dog or not—and a quantitative variable, B—for example, how many days a person is sick in a given year. ...
1
vote
1answer
163 views

How to reason about causal effect in time series when the treatment group reacts even before treatment?

Context: I'm running into a strange phenomenon about treatment effect and causality that I'll try to recreate here. Let's say I'm doing an observational study: Do people spend more time online as a ...
1
vote
1answer
447 views

Difference between using propensity score matching and CausalImpact for causal inference?

I'm investigating causal effect in some financial data, and I'm using two different approaches: propensity score matching with stratification and the CausalImpact package for Bayesian structural time ...
2
votes
1answer
396 views

What's the standard terminology for variables in observational studies vs experiments?

My stats textbook (De Veaux et al., 2008) advises using the terms response variable and predictor/explanatory variable in observational studies vs response variable and factor in experiments. However, ...
0
votes
1answer
90 views

Less than half of medical procedures are based on adequate evidence. What percent of those should we expect to be wrong?

"The proportion of medical procedures unsupported by evidence may be nearly half." If we assume that half of all procedures are based on observational data, what methods can we use to estimate how ...
1
vote
0answers
19 views

Selecting controls from a case-cohort study when location is important

I am looking at the causes of a disease in cows, both 'environmental' (ie ground-drainage, bedding type etc) and 'biological' (previous disease, sex, weight etc). Most environmental variables are the ...
6
votes
1answer
228 views

What are the problems with number needed to treat (or harm) in observational studies?

I have been asked to comment on the use of NNT (number needed to treat) and NNH (number needed to harm) in observational studies. My intuition doesn't give me any reasons these would be problematic ...
0
votes
1answer
70 views

Post-Match Analysis After Already Adjusting For Everything

Let's say I am conducting an observational study in which a group that received treatment (T+) is matched to another group (T-) using propensity score analysis where I use the "throw-the-kitchen-sink" ...
1
vote
1answer
640 views

Adjusting Sample with Propensity Score Weighting and ATT

I have a retrospective sample that contains a treatment and non-treatment group with >10 covariates comprised of both categorical and continuous variables. I used the chi-squared and Mann-Whitney U ...
1
vote
0answers
129 views

How to implement a Poisson Gamma model to predict study recruitment?

After researching there are a lot of papers that suggest study recruitment can be modeled after a Poisson Gamma distribution. (which might just be a negative binomial distribution?) They also have a ...
1
vote
1answer
24 views

Unmeasured covariate adjustment

A study was presented where the authors used multivariable logistic regression to assess association between a risk factor and an incident disease outcome. The association was statistically ...
3
votes
1answer
9k views

Why is Average Treatment Effect different from Average Treatment effect on the Treated?

In RCTs, randomisation balances unmeasured confounders and, I'm told, ATE and ATT would be the same. In observational studies, this is not possible and Propensity Scores are used in various ways to ...
0
votes
1answer
104 views

Meta analysis of one-armed observational studies with varying follow up (time)?

I am about to start a meta analysis investigating the retention of different dental fissure sealers. Data extracted from the studies are: (number of teeth completely sealed at the end of study) (...
1
vote
1answer
199 views

In causal inference in statistics, how do you interpret the consistency assumption in mathematical terms?

In causal inference, the consistency assumption states that there are no multiple versions of treatment. Specifically, for a potential outcome unit $Y_i$ and a binary treatment vector $\mathbf{Z}$, $...
2
votes
3answers
393 views

What assumptions are necessary to establish that a variable is confounding?

Suppose that an article claims that there is a cause-effect relationship between a certain explanatory variable A and a response variable B. If I were to test whether a confounding variable C exists ...
1
vote
1answer
90 views

Observational study design method vs hypothesis testing vs other?

I am trying to understand the following: do more customers purchase an item because it is discounted 'now' because they engaged with the product before (viewed it, added to a wishlist etc) vs just ...
0
votes
0answers
33 views

How to find probabilities at the end of observations period?

I am collecting stats results for 15 consecutive days for network lines and the outcome for a line could be: 1 No problem 2 Problem of type A 3 Problem of type B What is the best attack for this ...
1
vote
1answer
653 views

Experimental Study vs Observational Study

I intend for this to be a very brief question. I am currently engaged in a small debate as to whether the study in this article is an observational study, or an experimental study? Since initial ...
1
vote
1answer
79 views

Propensity Score Stratification: Design Clarifications

I have a pool of users and I am able to send them push notifications. I want to measure the effect of receiving a push notification on a usage metric, such as using a feature in the game within the ...
5
votes
3answers
218 views

Collider stratification bias or index event bias

This excellent paper covers a very interesting topic: collider stratificaiton bias. In short, lots of observational studies from medical literature have reported paradoxes such as obesity being ...
2
votes
2answers
429 views

Network Meta-Analysis: Single Arm vs Contrasts Strategy Pros and Cons

I am working on a Network Meta-analysis that is aimed at comparing different treatments (medical vs surgery vs percutaneous approach) on short as well as long-term outcomes (including cardiovascular ...