Questions tagged [observational-study]

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

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

Multi-centre survival analysis

I have question regarding survival analysis. I am looking at observational studies comparing patient survival who received treatments A or B at different centres (>10), for the same condition and ...
user avatar
  • 35
1 vote
1 answer
14 views

Kaplan-Meier curves for retrospective studies

While doing a review i noticed that Kaplan-Meier curves are often used for retrospective studies in the medical field. However, is it correct to do so even if the registry of data is not prospective? ...
user avatar
1 vote
0 answers
13 views

Is this a repeated cross-secitonal analyses?

I am using a dataset that has three waves divided by months (e.g., Wave 1 April to June 2021, Wave 2 July to September 2021, Wave 3 October to December 2021). Some of the participants have ...
user avatar
2 votes
2 answers
54 views

How to conduct my first data-analysis study?

I'm trying to improve my understanding of a few basic concepts in statistics (like statistical significance, the p-value, etc.) and to achieve that I decided to do a study myself (trying to learn ...
user avatar
2 votes
1 answer
41 views

How do I determine whether there is a significant difference between two sets of price data?

I am conducting a study where I am collecting prices from two groups of funeral homes in a particular state: in the first group, the homes I collected prices from are owned by families, and in the ...
user avatar
  • 21
1 vote
1 answer
35 views

Multiple Sclerosis: study design to beta test a software

I am a beta-tester of a software that is intended to help the radiologist to interpret MRI reading of Multiple Sclerosis (MS). MS is a disease that, over time, could lead to new lesions, expanding ...
user avatar
  • 143
2 votes
1 answer
57 views

Is there a difference between ignorability and strong ignorability?

The whole idea around ignorability is still leaving me a bit confused. I did read this post from the site: Strong ignorability: confusion on the relationship between outcomes and treatment. It had ...
user avatar
0 votes
0 answers
45 views

Valid statistical test for difference in age between two time points (for a cohort with additional membership)

The question at hand is whether the membership for an organisation has 'aged' from 2016 to 2021. 2021 membership is made up of 2016 members who continued to 2021 and new members from 2016 and 2021. ...
user avatar
2 votes
2 answers
110 views

Analysis of ordinal patient data across 3 time points (ordinal regression vs. Wilcoxin rank sum)?

I am conducting a study of a number of patients with a disease, and using an ordinal scale assessment of functional status at 3 different time points. In this example we can say that I have 100 ...
user avatar
  • 23
1 vote
0 answers
15 views

Unbalanced and missing data in generalized mixed effects model

I have a highly unbalanced dataset from observational data. I want to assess sources of variation on my dependent variable (Y, binomial distribution), controlling by the year of sampling. For that, I ...
user avatar
  • 11
3 votes
1 answer
71 views

When do we do sensitivity analysis in biostat and how do we do it?

I have two questions below. I have seen people doing sensitivity analysis in observational study papers for the model to check sensitivity to assumptions in bayesian context for selection of priors. I ...
user avatar
  • 911
1 vote
0 answers
24 views

simulations for observational studies [closed]

I am trying to get a better understanding of the paper "Causal inference using invariant prediction: identification and confidence intervals". Part of it is trying to replicate their ...
user avatar
  • 1,045
11 votes
2 answers
2k views

Is Propensity Score Matching a "MUST" for Scientific Studies?

Recently, I have been reading about Propensity Score Matching : If I have understood this correctly, Propensity Score Matching is used to construct control/treatment groups in scientific studies, in ...
user avatar
  • 5,884
0 votes
0 answers
12 views

How to calculate number needed to treat for case-crossover study design?

I'm relatively new to epidemiological methods. I'm trying to assess a program where I have access to administrative data that can be put into a case-crossover study design. I'm trying to assess the ...
user avatar
1 vote
1 answer
25 views

Set weight for different values

I'm quite new in the statistics world and the questions I will ask might be stupid. So, I have a study in which I did the following. I have set 7 questions (7Q) which had a possible answer of true/...
user avatar
1 vote
0 answers
20 views

Statistical design for failure analysis

I am designing a test plan to find factors that correlate with pavement failure. Failure is a rare occurrence. How would I go about designing the test? I have N factors, with various factor levels, ...
user avatar
  • 53
1 vote
0 answers
11 views

Quasi Experiment with Diff-in-diff but very uneven # of treatment and control sample

Let's say my app has 1M users and I launched a new feature in the app. As a result of this launch 10K users (1%) adopted this new feature. I want to understand the impact of this new feature on ...
user avatar
  • 11
0 votes
1 answer
44 views

How to choose the right variables for the logistic regression in an observational study?

I have read answers to the similar questions here and read other resources but I could not find a solid answer to this point. Sorry for my simple terminology. While analyzing the data from an ...
user avatar
0 votes
1 answer
91 views

Sample size and a study design: AI in shadow mode vs physicians

My research group has a group of patients where we are comparing the performance of a Random Forest classifier for acute respiratory tract infections. We are designing a study where we compare the ...
user avatar
  • 1
2 votes
1 answer
37 views

Current examples where randomized studies yield different results than observational studies

I have been reading the following paper by G. Smith (2002). I found it rather surprising. Some excerpts: Promising epidemiological and laboratory findings led to a paper published in 1981 in Nature ...
user avatar
  • 123
0 votes
0 answers
14 views

Contextual levels with 1:1 clustered observational units

Imagine a study that, from a design perspective, has both repeated measures and hierarchical structures. The ratio of observational units at level -3 to level-2 is 1:1(For example, "only one &...
user avatar
0 votes
0 answers
97 views

Use of null hypothesis significance testing in observational data

My question is about the use and interpretation of null hypothesis significance tests in cases where we do not have random samples or designed experiments, but rather have observational data from the ...
user avatar
  • 520
0 votes
2 answers
67 views

Retrospective cohort study and case control study

What study would best suit looking at the association between low birthweight and later academic performance? Note - 1000 low birth weight children and 3000 normal birthweight children were included ...
user avatar
  • 41
0 votes
0 answers
18 views

How to determine if some observers give the same answer

I wanted to know if I can statistically determine whether some observers give similar answers: let's imagine having 3 observers which have to evaluate 3 different pictures expressing how much of a ...
user avatar
1 vote
1 answer
546 views

How are weights computed in R matchit() function for full matching?

In the example I have, a small number of treated subjects are matched to a large number of untreated controls. I used ...
user avatar
  • 475
0 votes
1 answer
74 views

Prospective study and ascertainment of the exposure during the follow-up period

This question landed here after two migration requests from "Medical Sciences" and "Operations Research" I'm reading several prospective studies published in top journals where a ...
user avatar
  • 342
3 votes
1 answer
74 views

linear models for longitudinal observational study before - after surgery

I'd need an help from you for an analysis. I'm a physician with an interest in statistics. A colleague of mine asked me to analyse a dataset. He had the impression that symptoms get worse after ...
user avatar
  • 41
3 votes
1 answer
13 views

Inputs not proxying for variance, but nevertheless well-correlated

In a summary of this behavioral economics article, it says Our third finding is that cross-consumer heterogeneity in biases is poorly explained by even a “kitchen sink” of other consumer ...
user avatar
  • 371
1 vote
1 answer
35 views

What are the main methods for estimating the Average Treatment Effect in Observational Studies outside of matching?

I am wondering what the main methods for estimating the Average Treatment Effect in Observational Studies are outside of matching. In matching, there are weighting, stratification, propensity score ...
user avatar
  • 2,659
2 votes
1 answer
59 views

Including outcome only related covariates in propensity score estimation

When estimating the propensity score in an observational study, there seems to be a relative consensus on the fact that covariates related to the treatment and the outcome (i.e. cofounders) and ...
user avatar
0 votes
1 answer
37 views

Is different distribution of confounders across groups a problem for OLS as this researcher says, and if so which assumptions are violated?

I am watching this video where the presenter writes (the link will open at the correct time): Regression models Problems [...] confounders have different distributions across the intervention groups ...
user avatar
1 vote
1 answer
140 views

How to check baseline covariate balance after variable ratio matching?

In my case, each active subject is matched to a variable number of control subject. The way I can think of is to first average across the control subjects for the same active subject to make a 1: 1 ...
user avatar
  • 475
0 votes
1 answer
54 views

Is there a need to account for confounders if crude association is not significant?

Background: Swallowing exercises are prescribed to head and neck cancer patients during radiotherapy to prevent swallowing impairment Aim: Determine impact of swallowing exercise compliance on ...
user avatar
7 votes
2 answers
4k views

What are the pros and cons of using mahalanobis distance instead of propensity scores in matching

I learned about this option of using mahalanobis distance instead of PS to do matching from the matchit() function in R. It seems a more nonparametric approach. Could you state its pros and cons and ...
user avatar
  • 475
2 votes
1 answer
78 views

How is the vaccine effect calculated?

I'm trying to understand this study about the vaccine effect for the COVID. In the results the authors state: We found that VEs increased over time until a peak at day 28-34 days post-vaccination for ...
user avatar
  • 123
1 vote
0 answers
33 views

How to combine observational and experimental data?

I’m trying to figure out the effects of system changes on user long-term revenue (over a 12-month period, say) for an online platform. I have a lot of observational data, so I fitted a model that ...
user avatar
3 votes
1 answer
195 views

Network-Meta Analysis of Observational Studies

Does anyone have experience on conducting a network-meta analysis based on observational studies? Although network meta-analysis were proposed as a method to produce indirect comparisons between two ...
user avatar
1 vote
1 answer
16 views

Can you determine if a correlation exists independent from outliers without conducting an experiment?

Let's say A correlates with B. But, A is correlated with C, D, E, and F which also correlate with B. Could you determine if A's correlation with B is solely due to the fact that C, D, E, and F ...
user avatar
0 votes
1 answer
82 views

Analyzing a counterfactual in observational studies?

In observational studies, when randomization is not an option (everyone is treated), it is necessary to estimate a counterfactual of what would have happened in the absence of treatment. Once you ...
user avatar
  • 87
3 votes
1 answer
103 views

Why is ANCOVA not appropriate for modelling post-intervention outcome, controlling for baseline

I was trying to understand the different use-cases for differences-in-differences models vs. ANCOVA (post-period = pre-period + experiment_group), for observational data. I came across the below ...
user avatar
1 vote
0 answers
24 views

Case-Control Study Design for Longitudinal Analysis

I am designing a study in which I want to examine the relationship between a disease - major depression - and five exposures of interest: healthy/unhealthy diet, daily exercise hours, general outlook ...
user avatar
3 votes
1 answer
78 views

Name of study design for 2 samples measured at different times

I am trying to figure out the name for a design study in the following scenario. Imagine a hospital where patients with a certain condition (say bacteria infection) are treated with a certain ...
user avatar
1 vote
0 answers
91 views

Regression or statistical test for change in counts after a treatment

I am seeking suggestions for suitable regression or statistical tests to measure the effect of a treatment in counts (or proportions), when a control group is not available. Let's say an event takes ...
user avatar
  • 103
2 votes
1 answer
138 views

Difference in difference with similar units over 2 periods of time

I have ESG (Environmental, Social & Governance) scores for 20 companies over a period of 10 years. In the fifth year a policy was introduced and I want to estimate the impact/effect of the policy ...
user avatar
  • 21
2 votes
0 answers
94 views

Does bayesians' critique to frequentists apply to themselves too?

I've been reading about bayesians versus frequentists, including articles in this forum (like this one). Key is of course the issue of "priors". The bayesian critique being that frequentists ...
user avatar
1 vote
1 answer
477 views

Multiple regression vs propensity score matching for covariates in observational study [duplicate]

I want to determine if smoking is related to this cancer in an observational study. I have data from 1000 subjects with following variables: ...
user avatar
  • 9,133
1 vote
0 answers
22 views

Is there a name for this kind of causal inference from observational data? Using a single model across multiple contexts

Suppose you have two variables A and B, such that A influences B with some coefficient b. What is the correlation between A and B? Well, it depends on the variances of b, so it's going to vary across ...
user avatar
0 votes
1 answer
26 views

For retrospective observational studies how to determine the baseline of control subjects

I understand that for the active treatment group you can consider the start of treatment as baseline. How about the control group? It is difficulty to do matching without resolving this problem.
user avatar
  • 475
2 votes
1 answer
38 views

How to do propensity score matching for a cohort study?

Suppose I want to look at the relationship between smoking and lung cancer, and want to use propensity score matching to select a similar group of people to study. Knowing that age, and gender are ...
user avatar
2 votes
1 answer
100 views

Effect of duration of treatment on time to event outcome (overall survival)

I am trying to understand how to design an analysis for the following situation. We have the following data collected retrospectively on a group of patients: Age, Sex, Race, and other variables ...
user avatar