Science method

Case-Control Studies - Science method

Studies which start with the identification of persons with a disease of interest and a control (comparison, referent) group without the disease. The relationship of an attribute to the disease is examined by comparing diseased and non-diseased persons with regard to the frequency or levels of the attribute in each group.
Questions related to Case-Control Studies
  • asked a question related to Case-Control Studies
Question
4 answers
It is known that selecting control is the most critical and difficult part while conducting a case control study design. For getting true association , it is imperative that controls should reflect the exposure pattern of the source population that give rise to cases. What are the ways of selecting controls to be closure to true association?
Relevant answer
Answer
The comparison group ("controls") should be representative of the source population that produced the cases. The "controls" must be sampled in a way that is independent of the exposure, meaning that their selection should not be more (or less) likely if they have the exposure of interest.
  • asked a question related to Case-Control Studies
Question
1 answer
justify it scientifically
Relevant answer
Answer
Hopefully the screenshot search will.be of some help. Best wishes David Booth
  • asked a question related to Case-Control Studies
Question
2 answers
Hello I have a manuscript revision with one of the reviewers is concerning about the power of study
Its a case control study with case group having 34 and control group having 71 patients
The primary outcome variable is a continuous variable with a mean 41 and standard deviation of 26 , and not -normally distributed, and our cohort is the largest cohort ever will be published
But there is no prior report on this issue, so how can i do a power analysis
Thanks for helping
Relevant answer
Answer
Thanks Dr. Petersen, I appreciated your taking time and reply
  • asked a question related to Case-Control Studies
Question
3 answers
I have two former cohorts from a case control study where children of different ages <18 months of life were recruited (healthy vs. disease condition) in order to compare their intestinal microbiota composition. Now I have a third cohort of other disease condition that I would like to compare to the other ones. The problem is that this third cohort was supposed to be followed for longitudinal studies, and so, I have repeated measures over time of few subjects.
My question is: would it be admissible to gather together all measures from the third cohort and compare them to the former cohorts? Is there a way to account for the fact that this third cohort has more than one measure from each subject? or otherwise, do I have to randomly subsample my third cohort so that every subject provides for a single measure?
Relevant answer
Answer
Both of the above responses are very subjective IMO. IF I was the reviewer on the paper I would conclude that this is not a good experimental design. You are just arbitrarily combining pretty unrelated observations. Best wishes, David Booth
  • asked a question related to Case-Control Studies
Question
3 answers
I understand meta-analysis of RCTs has a level I evidence and case control studies have a level III. But what is the level of evidence from meta-analysis of well-conducted case-control studies; is it I or III or otherwise? Many thanks
Relevant answer
Answer
Thanks Suraj Kapoor. I do not see this on the table. If individual case-control studies are level VI, ot would not make sense for systematic review and meta-analysis of a group of these to be level V
  • asked a question related to Case-Control Studies
Question
2 answers
i. real data of a particular year after base year,
ii. Hypothetical scenario taking certain data for a particular year,
iii. Case base study of a particular factor, or
iv. other options?
I will be thankful and appreciated the comments and suggestions from the dignified academicians.
Relevant answer
Answer
  • asked a question related to Case-Control Studies
Question
4 answers
I have a case-control study with 200 cases and 200 controls (d == 0 for controls and d == 1 for cases). Two tests y1 and y2 are applied to each case and control and the results are coded 1 for a positive test result and 0 for a negative test result. The estimated prevalence of the disease in the population, p = 0.15.
I want to calculate the PPV and NPV of these tests, the 95% CI of the predictive values, and compare the PPV and NPV of tests y1 and y2.
Can someone please help me with some Stata code for the same?
I am attaching the data file for the exercise. This is hypothetical data generated for an academic exercise only.
Relevant answer
Answer
Use a program spss to access the appropriate analysis
  • asked a question related to Case-Control Studies
Question
3 answers
I have taken 2 cases for 1 control in my study..is it ok to take it in this ratio where cases are more than controls.What explaination can i give for it
Relevant answer
Answer
Welcome you, Khaled Almaz
Kalra, Aakshi. "The odds ratio: Principles and applications." Journal of the Practice of Cardiovascular Sciences 2, no. 1 (2016): 49-49.
Hope this will work. Thanks.
  • asked a question related to Case-Control Studies
Question
3 answers
A case-control study has been used to construct a prediction model and there is no cohort study to calibrate it.
What solution do you suggest for calibration?
Relevant answer
Answer
Have you used the regression model? For example, logistic regression model?
  • asked a question related to Case-Control Studies
Question
3 answers
How can I improve the detection bias in these studies?
Relevant answer
Answer
How can I use NOS for assessing a nested case-control study? Should I assess all the primary cohort studies?
  • asked a question related to Case-Control Studies
Question
3 answers
In the case of a case-control study, I can adjust the odds ratio for age, sex, BMI, clinicopathological data, etc., in determining the odds ratio for genotype data with logistic regression/multinomial logistic regression in SPSS. However, in the case of allele data, as an individual can carry two same (wild/variant) or two different alleles (heterozygote), how can I adjust the odds ratio with covariates (age, sex, BMI, clinicopathological data, etc.)?
Relevant answer
  • asked a question related to Case-Control Studies
Question
3 answers
Hi unfortunetly in my study there are only 2 RCTs published to demonstrate any reliable effect with a surgical procedure on a pathology (osteoarthritis).
The remaining are case series, which measure patient's MEAN outcome scores at 1year, 1-5 years , >5 years. Some don't publish SD. Others publish just median scores. The series all have the same pathology (osteoarthritis), but do not necessarily have the same patient characteristics - typical of case series and units wanting to present their results.
Can I pool these Mean patient outcome scores together at 1 year / 1-5 years / >5 years and calculate the total mean and present them in a forest plot?
Does it statistically make sense or am I comparing apples and oranges? Do I just calculate the average or are there any tests you would recommend?
I understand that is the limitation that this is poor literature and hard to come to a conculsion, but that is the point I am trying to highlight that we can't keep publishing small case series but need large registry data which I will be working on.
Relevant answer
Answer
I assumed included studies met your predetermined inclusion/exclusion criteria based on protocol. If so, in this case , I would contact author requesting some missing information that I need for meta analyais.
  • asked a question related to Case-Control Studies
Question
3 answers
I have developed a case-control study, matched 1:7. I addressed the conditional logistic regression analysis with COXREG (SPSS).
By using univariate analysis (McNamer/Wilcoxon), I found that there is no statistically difference between case and control groups (checked for one of my dichotomous independent variable).
When I used COXREG (in order to create consitional log regression in SPSS) and analyse the same independent variable (analyzed alone in regression) - I realized there was differenet between case and control groups.
To sum up - I found a different statistically significant while using univariate and COXREG (conditional log regression) analysis (for the same variable).
What could be my mistake?
Relevant answer
Answer
People who do not use SPSS may be wondering why Daniel Gabbai is talking about the COXREG command when he is estimating a conditional logit model. The reason is that SPSS still does not have a conditional logistic regression command (believe it or not). For years, the recommendation has been to cajole the COXREG command into estimating the model. Details can be found in these notes on the IBM website:
Daniel, bear in mind that there are other ways to account for the correlated nature of the data within match groups. You could use GENLIN with generalized estimating equations (GEE), for example; or you could use GENLINMIXED with patients clustered within match groups. Something to consider if you do not have to use conditional logistic regression. And FWIW, when I used GENLIN with GEE to reanalyze some data that I looked at with conditional logistic regression (using Stata's clogit command), I found that the results were very similar using the two approaches.
HTH.
  • asked a question related to Case-Control Studies
Question
7 answers
Need your expert opinion,
For my research I have 1 control ratio to 4 cases, is this ok?
Relevant answer
Answer
It depends on the availability of the controls and your research question. You can take Minimum 1:1 to maximum 1:4 controls.
  • asked a question related to Case-Control Studies
Question
4 answers
how to perform Cochran-Armitage (CA) trend test using spss?
can we perform it on 2*2 as well as 2*3 contingency table?
I am doing case control study and have to select one best fit genetic inheritance model for my study.
Relevant answer
Answer
Those links would be useful if the book cited in their example was available, alswere it is not possible to adapt their example to our context ...
I keep trying to solve this problem, any help is the most welcome.
  • asked a question related to Case-Control Studies
Question
3 answers
Identification of risk factors for cardiac malposition in children
Case control study
Need help for sample size estimation
Relevant answer
Answer
Good answer usually the control group should at least same case group and the ideal size is the double case group
  • asked a question related to Case-Control Studies
Question
6 answers
I am to calculate sample size for a case control study and I am not sure whether to use the crude odds ratio or the adjusted odds ratio of other studies to estimate my sample size
Relevant answer
Answer
  1. Kindu Yinges Define rates of participants for each group of outcome ,the minimum clinical significant difference , define the expected prevalence of exposure and define your significance level (usually p<0.05) and the power.
  • asked a question related to Case-Control Studies
Question
3 answers
It is identified in some pieces of text I have read that paired t test is used to compare between cases and matched controls with regard to a continuous variable. Is this correct and how is this justified?
Relevant answer
Answer
Not exactly. If participants were first placed into pairs based on a common variable and then one individual in the pair was randomly assigned to either the treatment or control condition (and the remaining individual to the other condition) - then a paired samples t-test would be appropriate.
In an independent samples t-test, which group an individual is assigned to (treatment or control) is independent of the assignment of all other participants. The paired samples t-test also goes by the name "dependent samples t-test". It is called this because individual assignment is not independent. For example, in a matched pair - if one individual in the pair is assigned to the treatment group, the other individual in the matched pair is assigned to the control group (and vice versa).
A paired samples t-test is "justified" in this situation because the assortment into matched pairs (supposedly) removes the variability associated with the variable of interest. For instance, if we grouped participants into pairs based on age prior to assignment. Any differences found between individuals in the treatment and control conditions is not likely due to age. The caveat is that individuals in the matched pair could differ in other ways that we didn't control for.
  • asked a question related to Case-Control Studies
Question
2 answers
in a case-control study, is it must for the population to be the same for control and cases?
i mean if we are going to study the impact of Female genital mutilation(FGM) on obstetric outcome in immigrant women
those who have FGM will be from some ethnic group, for control group if finding women without FGM is difficult from the same immigrant ethnic group, in these case can we take control from
other non-African or European women??
Relevant answer
Answer
Yes. In scientific research, you must include a control group equal to the treatment group in every way except that it will not receive the experimental treatment. Without a control group, exactly as same as the treatment group, you can't analyze whether the results were because of the treatment or due to another variable that caused the experiment's outcome.
  • asked a question related to Case-Control Studies
Question
2 answers
I'm conducting a meta-analysis of the prevalence and risk factors of pancreatic exocirne insufficieny (PEI) after pancreaticoduodenectomy.
All of the studies that I've included that report the prevalence of PEI are cohort studys. So, I've assessed their risk of bias using the Newcastle Ottawa scale.
Some of them, in the same study, perform a nested case-control study to analyse risk factors of PEI after pancreatoduodenectomy.
My question is, do I have to assess the risk of bias of the nested case-control study that is included in the original cohort study? This meaning, a unique article would have to different assessments of bias, as it includes two different types of study designs.
Or should I assess the risk of bias of the global study? In this case, how do I do it, as it has two different designs?
Relevant answer
Answer
Best to use a tool for prevalence studies as you are extracting prevalence information and the design is not really relevant
A tool of interest would be
  • asked a question related to Case-Control Studies
Question
4 answers
Hello all
i am currently doing a systematic review and am planning on using NOS to do quality assessment. However, I am struggling to tell whether Some of my included studies are case-control or cross-sectional, which is hindering me doing the correct NOS analysis. Would really appreciate some help with how to tell which papers are which.
for example, this paper ( ) has been referred to in a systematic review as cross-sectional rather than case-control, even though it compares a group of people with alopécia to a group if controls without alopécia. What is it that makes this paper cross-sectional?
All of my included papers are comparing the prevalence and mean scores of depression in patients with X disorder versus patients without X disorder.
i would really appreciate any help with this!
Relevant answer
Answer
This fits into cross sectional study
Case control study procedures are not followed in the study
It is a cross sectional study with analytical component
  • asked a question related to Case-Control Studies
Question
5 answers
I noticed from several articles saying that case-controlled study is more bias prone than cohort study (in the context of cancer early detection using molecular marker). I spent sometime to try to rationalize the idea (I guess it has something to do with case-controlled study having more risk of carrying confounder?) and could not find the logics. Can someone some comments on this?
Relevant answer
Answer
Cases and controls are often not matched for life status. In mortality studies controls tend to be live whole cases have died. Live controls have more information about past exposures than relatives of people who have died. For example if work with asbestos brakes is an exposure of interest, relative are far less likely to know about occ changes than are actual cases or controls.
  • asked a question related to Case-Control Studies
Question
2 answers
I'm doing a retrospective case-control study on the outcome of stroke patients were either A) Community Onset or B) In-hospital onset
We have an n of ~1400 patients over several years. We wanted to do a multivariate analysis comparing patient outcome of whether their outcome by discharge from hospital was either A) Functionally Independent or B)Death/Dependency (no longer able to care for themselves)
We wanted to look a the following variables which we've tracked to see if there is a difference between community and hospital-onset stroke
1) Pre-hospital independence (YES/NO) *Defined as an OHS of <3
2) Patient Age
3) If they had atrial fibrillation (YES/NO)
4) If they received Thrombolytic Therapy (YES/NO)
5) If they received endovascular thrombectomy (YES/NO)
6) Sex (MALE/FEMALE)
For the inpatients, we're curious to know if there is a difference between those who had a procedure and those who did not but I think that has to go in a within-group analysis later on.
Most of my stats background comes from behavioural sciences where I worked with continuous data, not discrete data. I don't know/think a multiple-ANOVA would be the right approach here.
I thought about doing a Logistic-regression or a binomial - regression but I'm not if that fits especially with the patient age being a factor.
I thought of taking OUT patient age and doing a 2x7 Chi-square but then the sample size may contribute to a type 1 error.
Could anyone offer advice on the best to analyse this data or is the question setup flawed?
Relevant answer
Answer
I think you have two possibility:
1) I think that you have to do a "survival analysis" with kaplan-meyer curves. I made a similar analysis last year (https://www.nature.com/articles/s41598-020-60180-6) comparing stroke patients with and without a diagnosis of atrial fibrillation during a period of about 2 years. You may do a similar analysis calculating a kaplan curve for each factor (A) Functionally Independent or (B)Death/Dependency while caring about. You will have an Odd ratio for each "risk factor" (1-6);
2) you may simply calculate Mann-Whitney U test and Chi Square depending on the type of variables comparing the two population with (A) Functionally Independent or B)Death/Dependency (if the two population share similar demographics).
I hope you will find useful my answer. Good lack!
  • asked a question related to Case-Control Studies
Question
4 answers
If I understand correctly, retrospective cohort study collect data by recall, just as case-controlled study. Both of them suffer from recall bias. What is the pros of retrospective cohort study over case-controlled study?
Relevant answer
Answer
In short, retrospective cohort studies allow researchers to examine the risk associated with the exposures and express them as relative risk (RR), while case-control studies only allow researchers to express the association between exposures and outcomes using odds ratio (OR). Unlike RR, OR cannot be interpreted directly and thus yield lower quality to explain causations underlying the observed effects. I agree with Babak Saravi for the rest of the explanations.
  • asked a question related to Case-Control Studies
Question
4 answers
I am planning to conduct a research on oxidative stress of the pregnant mothers. There I am planning to compare oxidative stress between mothers with PIH and mothers without PIH. I would like to know what would be the best research design to conduct this study. Is case control study design ok for this? Or is there a better way?
Relevant answer
Answer
Hello
a well-designed case-control
  • asked a question related to Case-Control Studies
Question
5 answers
I am measuring sleep spindle activity in 3 groups: schizophrenia, bipolar disorder and healthy individuals.
I aim to compare their activities and the sleep study will only do once.
Do you think this is a cross-sectional study since I measure it at one-time point?
Or do you think it is a case-control study?
Relevant answer
Answer
In my understanding, both the terms are NOT mutually exclusive. So a case control study can be cross-sectional too and vice versa.
Please see here:
  • asked a question related to Case-Control Studies
Question
6 answers
I want to know if it is acceptable to combine cross-sectional studies (with the prevalence from the case group and control group) and case-control studies in a meta-analysis. I have seen several meta-analyses which combined the prevalence odds ratio from cross-sectional studies and odds ratio from case-control studies. I want to know if this is accepted in the field?
Relevant answer
Answer
It depends on two issues: conceptual and technical. You can combine those odds ratio if both studies consider the same outcome. See the attached article, particularly the "Combining different metrics" section.
  • asked a question related to Case-Control Studies
Question
7 answers
(1) Whether case studies are designed predicting a possible situation in the future based on the current facts, processes, and methods that are being followed? (OR)
(2) Whether the solutions that get articulated in terms of case studies narrating how problems have been overcome, and thus become an antecedent?
Relevant answer
Answer
Mangipudi, case studies are one of a range of qualitative research methods, which, when used rigorously, can highlight the intricacies, complexities and richness of a set of phenomena within a contextualised setting. It is in depicting the varieties and nuances of cases that qualitative researchers and other researchers who are sympathetic to its usage, that case studies can help us understand the implications and implicit meanings within them. Interesting.
  • asked a question related to Case-Control Studies
Question
3 answers
Conditional logistic regression is used to manage the presence of sparse data due to confounders using matching to improve the precision of estimation. Most statisticians and researchers recommend me to use statal.
1. Can I conduct conditional logistic regression using SPSS?. Why?
2. What is the advantage of STATA over SPSS in analyzing matched case-control study designs (1case:1control approach)?
Relevant answer
SPSS is good for logistic regression analysis.
  • asked a question related to Case-Control Studies
Question
5 answers
how the observational studies are useful in Ayurveda??
especially the case-control studies..
what is the use of case control studies and cross-sectional survey studies in Ayurveda?
Relevant answer
Answer
The statistical test will depend on the type of study. Cross sectional study can be both observational type as well as analytical type whereas case control studies are analytical studies. Now if you want to perform an analytical study, you need to have a null hypothesis first. Next you have to determine the levels of alpha and beta errors for inference. Next, determine the best statistical test for the stated null hypothesis. Then you need to perform that test (you may calculate OR, AOR, PAF for case control studies). Finally, draw your conclusions based on the results. Best wishes.
  • asked a question related to Case-Control Studies
Question
4 answers
Hi,i'm working with case control studies for a meta analysis, however, controls are different amongst different studies. However, inclusion and exclusion criteria of cases are the same. What do you suggest please?
Relevant answer
Answer
Hi Maria,
That is a very interesting question. The same issue when you have different measurement tools (for example).
When there is so heterogeneity, meta-analysis should be avoided for many methodologists. However, you can enlarge your inclusion criteria and find a definition of the control group (comparator) which englobes all the comparators in the included studies. If there are significant differences between the controls, you should mention this in the limitation section.
Good luck.
  • asked a question related to Case-Control Studies
Question
4 answers
Is it enough to compare people who needed to be hospitalized with people who did not? , or should the age and duration of the illness be considered?
Relevant answer
Answer
However the exact time of the disease onset in patients is not clear.is it matter? how can i compare two group whereas that the time of disease onset is not the same?
  • asked a question related to Case-Control Studies
Question
11 answers
I have seen from some review articles which used the EPHPP or the Newcastle Ottawa Scale (NOS), but I can imagine that these are mainly used for clinical studies (cohort studies, case-control studies, etc.). I did a check on the keys used for the assessment to confirm it.
My systematic review however is not related to clinical studies. I am working on a review in the field of environmental pollution, particularly PAH pollution (which reports on the analytical techniques and the PAH concentrations in the different media), and I need to assess the quality of the already selected list of papers (after using PRISMA guidelines or checklist).
Thank you!
Relevant answer
Answer
Dear Samuel,
Hello,
First of all, I would like to thank you for the sake of this interesting discussion!
Although many of important criteria have been addressed by the friends participated in this discussion, I would like to add that novelty of the idea, good review of the literature, accurate research method, clarity and presentation of the work, and usefulness of the article contribution can also taken into account.
All the best,
Ali
  • asked a question related to Case-Control Studies
Question
4 answers
If I need to find out a suitable sample size population to utilise in a chronic disease case control study, how do I use an allelic frequency derived from a previous study on a chronic disease prevalence to calculate this value.
Relevant answer
Answer
You can have a look into the following link for calculating sample size using allele frequency. I think this calculator considers all the aspects required to calculate sample size for genetic analysis.
Best of luck.
  • asked a question related to Case-Control Studies
Question
19 answers
I'm writing a review for my master's thesis and am trying to identify for each study which design is used. Differences between a cross-sectional design and a case-control study are not so clear to me. In some of the studies, it is not thoroughly described how they recruited their sample. What should I look for in an article to know which design is used?
Thank you :)
Relevant answer
Answer
In a case-control study you sample on the outcome. That way you can oversample rare events.
  • asked a question related to Case-Control Studies
Question
5 answers
I am working on a meta-analysis of case-control studies.
I used Newcastle-Ottawa scale (NOS) to assess the quality of the studies.
I couldn't find a good reference to interpret the results although some studies categorize the quality as high (≥7 stars), medium (4–6 stars), and low (≤3 stars).
Is NOS a good choice or another quality assessment scale is recommended more?
Relevant answer
Answer
Dear Jamil,
To my knowledge, the NOS have not been published in peer-reviewed journals so far (the only reference is the web-based link http://www.ohri.ca/programs/clinical_epidemiology/oxford.asp) which is something to consider about its validation. Despite of that, NOS is the most used tool to assess risk of bias in non-randomized studies according to Quigley et al. (J Eval Clin Pract. 2019;25:44–52).
Other important issue is that it has been criticized that the use of summary scores involve inherent weighting of component items including items that may not be related to the validity of the study findings. Thus I would no go for a cathegorization on high, medium and low quality, but I would rather show the assessment by domains if I would use NOS.
Best regards.
  • asked a question related to Case-Control Studies
Question
4 answers
I planned to conduct case control study and I find difficulties in calculating samples size. And according to my search I cannot find any way to calculate the sample size. Can anyone help?
Relevant answer
Answer
There are several ways to calculate the sample size for the case-control study.
The above-mentioned link is a reliable online platform to calculate sample size for different study designs.
However, the most commonly used formulas to calculate the sample size for the case-control studies are provided into this presentation-
  • asked a question related to Case-Control Studies
Question
7 answers
Gentaplax is said to be effective in treatment of ED, any case control study?
Relevant answer
Answer
There is no any concrete scientific evidence to prove that 'Gentaplex' is effective in treatment of erectile dysfunction.
  • asked a question related to Case-Control Studies
Question
5 answers
In this article, we have 2 groups, patients with clefts and patients without clefts. Our outcome is teeth with developmental defects "enamel defects". The authors report this as a "cross-sectional study".
In this article, we have 2 groups, patients with clefts and patients without clefts. Our outcome is teeth with developmental defects or dental anomalies. The authors report this as a "retrospective study" (case-control?)
In this article, we have 2 groups, patients with clefts and patients without clefts. Our outcome is teeth with dental anomalies or developmental defects. The authors report this as a "cohort study"
My question is why is the study design different, if in all cases we recruit patients and examine clinically / with radiography to assess the outcome.
Relevant answer
Answer
In the past (and sometimes still) clinical researchers sometimes used the term "case control study" to mean comparing outcome in an exposed group to that in a "control" (ie un exposed group) ,cross sectionally. That is why in modern epidemiology (ie since about 1985) the term case-referent study is now preferred .
  • asked a question related to Case-Control Studies
Question
3 answers
I am one of the co-authors of this article: Effect of Girth Supersizing on Patient Satisfaction After Semi-Rigid Penile Implant Insertion: A Prospective Case-Control Study. But in the research gate, my contribution is refered to another one who’s name is also Mohamed Shokr.
Relevant answer
Answer
Here is some hints which well explaining the issue Another researcher has claimed my publications:
  • asked a question related to Case-Control Studies
Question
3 answers
Gun violence against one's self or others may be a planned behavior. However, current theoretical models of suicide, specifically the "ideation to action" theories of Joiner, O'Connor, and Klonsky and May, posit suicide as most frequently a planned behavior involving a process of mounting risk acuity over some period. Homicides, particularly mass shootings, are also known to be planned. In the US, 20 states have enacted or passed Extreme Risk Protection Order (ERPO) legislation (AKA "red flag laws") authorizing a local court to temporarily remove access to personal firearms if an individual is deemed at near-term risk of homicide or suicide. Advocates of such policies cite their value as preventive measures, especially in regard to suicide. It is argued that separating the at-risk person from her/his guns is an effective deterrent. There are reports both supporting and challenging this premise. However, the research only looks at rates of gun violence in specific states before and after passage of ERPO laws. No attention is given to the generic sources and nature of risk for homicide and suicide. Gun access in the home is a known risk factor for both, but is suicide risk inherently more enduring (consider "acquired capability") than homicide risk? Do homicides more likely involve short-term factors (e.g., interpersonal conflict)? This question relates to a policy science rather than “gun politics” perspective, i.e., are ERPO laws more efficacious in regard to firearms homicides than firearms suicides based on what we know of the nature of suicide risk? ? Here is a source on the topic: https://www.researchgate.net/publication/10746077_Homicide_and_Suicide_Risks_Associated_with_Firearms_in_the_Home_A_National_Case-Control_Study.
Relevant answer
Answer
This hypothesis might be true in USA and latin america where gun licence laws are are liberal no state control present, but in India homicides with firearm are mostly planned.
  • asked a question related to Case-Control Studies
Question
4 answers
Our data consists 1000 cancer cases and 1050 controls (frequency matched by age group and sex, incidence density sampling). I want to estimate the causal effect of smoking on thyroid cancer risk using Inverse Probability Weighting Technique (IPWT).
I came to know from some source that applying the PS in case-control is less straightforward. I know that case-control is an outcome oriented design, but with PS we are estimating the probability of exposure (say smoking in my case). So, I am little confused why PS is not recommended in case-control design.
Any thought from my peers?
Relevant answer
Answer
Yes, it is recommended
  • asked a question related to Case-Control Studies
Question
2 answers
Hi!
I´m doing my Masterthesis on electromyographical studies of certain exercises. These are observational studies without any epidemiological background. I cannot find an assessment tool that fits to this type of study!
The New-Castle-Ottawa-Scale has too many items for case-control studies. The items of the STROBE-Statement seem to fit quite well, but I just read, that it´s actually no tool for assessing studies (even though I already read Reviews that used it like that).
Can anybody help me?
Eva
Relevant answer
Answer
Thank´s for your advice. I´ll have a look at the CASP-checklists!
  • asked a question related to Case-Control Studies
Question
3 answers
Also, if I want to get genes' expression, should I have to know the gene?
Relevant answer
Answer
Price is always relative to what your budget is and how many samples you are looking to analyse. As far as I'm concerned it costs around 180-200$ per sample byt this may differ from country to country.
  • asked a question related to Case-Control Studies
Question
4 answers
Is it commendable or possible to computing and describing the prevalence rate of an outcome interest (mainly the cases) in case control study? I hope the answer whould be yes. However, I am confusing that in a case control study the respondents were selected from the source population which we are targeting based on the case ness or non case-ness conditions. Already the cases were known and and no more computing prevalence in the course of the study. How eve,r I think, we can comput it by taking assumptions of howmony of cases are found from the tareget population and ready for sam,pling procedure. Meaning we can determine before the study was conducted.Thus, in such cases what is the need to compute or present the revalence since it was not assumed as key findings in the research process? If you your suggestion is yes how can estimate the prevalence? In which case can we compute it?
Thank you in advance for your quick response and genuen answers!
Relevant answer
Answer
Thank You so much!
  • asked a question related to Case-Control Studies
Question
7 answers
It is recommendable that computing the prevalence rate of an outcome interest in case control study? I hope the answer whould be yes. However, I am confusing that in a case control study the repondents were selected based on the case ness or non case ness condition. Meaning the case for the outcome interest was already known. Thus, in this case what the need to compute or present the revalences? If you your suggestion is yes how can estimate the prevalences? In which case can we compute it? Thank for you quick response and genuen answers in advance.
Relevant answer
Answer
Only a prevalence study will allow you to determine a prevalence rate.
  • asked a question related to Case-Control Studies
Question
4 answers
In a case- control study, I determined lead, manganese, and zinc levels. when I study the normality of distribution, manganese levels were normally distributed, but lead and zinc levels were not. I was wondering whether I could use T test to compare manganese levels and Mann-Whitney to compare Lead and zinc levels, or I should use Mann-Whitney for the three metals?
Thanks
Relevant answer
Answer
Dear Israa,
In my opinion, of course, you can use both approaches parametric and non-parametric according to the distribution that your data follow and mention to your project the reason why you had to make that decision.
  • asked a question related to Case-Control Studies
Question
7 answers
A Case Control study, in which hospital patients were selected as cases, should the control group be similar to the cases in all respects other than having the disease in question (hospital controls), or whether controls should be representative of all persons without the disease in the population.
(Two controls groups are not possible because of financial constraints)
Relevant answer
Answer
Well, what (types of) exposure are you thinking of? This would make questions of comparability much easier to discuss.
Remember also to look up "Berkson's fallacy" - one of the classical critical concerns with hospital-based controls.
(I assume your study is an incidence study ("classical case-c."). If not, we must have more details. What is the question you try to answer?)
Good luck! / JH
  • asked a question related to Case-Control Studies
Question
2 answers
It is a well- known result of population genetics that admixture, heterogeneity, or stratification in a population can make it impossible to draw valid conclusions from a conventional case-control study, since these conditions (”population structure”) can give rise to substantial association even for unlinked loci.
Relevant answer
Answer
Thank you
  • asked a question related to Case-Control Studies
Question
3 answers
I have two case controlled groups - clinical and healthy. I am measuring several variables in each group which are continuous variables. I could use T test, but I have 2 confounding variables (categorical 0,1). so which test can I use to compare the two groups? Can I Use ANCOVA? In addition to ANCOVA, Can I use Binomial Logistic Regression to find the predictor variable among all other variables? Thank you in advance.
Relevant answer
Answer
If this is set up as a standard epidemiological case referent (case control) study) with cases and controls (non cases) appropriately sampled, then standard binomial regression would be suitable-- include as independent variables all your continuous variables plus the two categorically defined confounder variables .
then the exp (beta coefficient) gives the multiplicative increase in odds ratio (relative risk) for unit change in each continuous independent variable (risk factor) ,adjusted for confounding.
if you are just comparing some findings in a group of patients with "normal " controls. Then I would recommend separate t tests for each variable between cases and controls in each confounder category (eg city male, city female,
rural male, rural female) if you have enough data.
  • asked a question related to Case-Control Studies
Question
8 answers
I plan to conduct a study in which I will compare depression and quality of life among children with cancer to children with other chronic conditions (hematologic, kidney and respiratory chronic conditions). Is it appropriate to say that the cancer patients are case and other children are control. Or should I change the study design?
In case my case group are children with cancer, who should be the control group?
Thanks
Relevant answer
Answer
If your research question is "does cancer cause depression and loss of life quality" you should compare non cancer patients with cancer patients ie start with the "exposure = cancer" and compare the exposed group to a non exposed group otherwise similar, This is a cohort design, not a case-control design.
if on the other hand you have a group of patients with depression and poor life quality (the cases) you should select a group without depression or poor life quality (the controls) and compare the presence or absence of cancer in the in the two groups. This would be a case control study..
Ii would recommend the cohort approach.
  • asked a question related to Case-Control Studies
Question
4 answers
question about case control study
Relevant answer
Answer
yes , can
  • asked a question related to Case-Control Studies
Question
10 answers
Can case control studies be prospective? Some say case control studies are always retrospective. Please clarify
Relevant answer
Answer
Dear Dr. Melvin George,
According to J. Last's "A Dictionary of Epidemiology" (4th ed., p. 22), "cases and controls in a case control study may be accumulated "prospectively," that is, as each new case is diagnosed it is entered in the study. Nevertheless, such a study may still be called "retrospective" because it looks back from the outcome to its causes".
Best regards!
  • asked a question related to Case-Control Studies
Question
8 answers
Results obtained from T-ARMS PCR
on what basis we select a genotype to dominant or recessive
Relevant answer
Answer
Mushtaq Ahmad, one of [GG vs GA+ AA] or [AA vs GA+ GG] will be a recessive model (and the other dominant) - depending on which allele is dominant. You could also try other genetic models e.g. co-dominant and additive. However, this will all depend on whether you know the underlying mode of inheritance a priori. If you don't try the genetic-model free approach ( ) or standard pairwise approach.
  • asked a question related to Case-Control Studies
Question
6 answers
We are currently designing a nested case-control study based on retrospective registry healthcare data available over a 4-year period. We have identified all cases, and are now looking into the selection of controls.
We want to use incidence density or risk set sampling, so selected controls should still be eligible as controls for future cases, and can be selected twice or more.
How should we select controls exactly when selecting from a retrospective registry dataset? We believe that if we select a control for a case occurring at time x, we should add all registry data we have available for this control up to time x, and delete all registry data available for this control after x. However, this control should still be available as a control for a case occurring at time x+y. If we select this control again for another case at time x+y, should we just add all available registry between x and y data to that control's data in the dataset? Or should we end up with two separate rows in our dataset by duplicating the control, and add data up to time x for the first duplicate, and up to time y for the second duplicate?
We believe the former makes more sense but do not find guidance on this in the literature.
Any advice in this would be greatly appreciated!
Philippe
Relevant answer
Answer
Hi Philipe,
I tend to agree with James, the first approach of selecting the controls with data up to a specific timepoint seems much easier.
Regards,
  • asked a question related to Case-Control Studies
Question
4 answers
I submitted one article/a 1:2 matched case control study by age and sex of participants/ in a peer reviewed journal and one of the reviewers commented that " He would suggest including the matching factor in the adjusted analysis because matching does not always remove the confounding of the matched factors. In addition, matching process in a case-control study can introduce bias by changing the association between the matching factor and the outcome and can create an association even if there were none before the matching was conducted". How I do that?
Relevant answer
Answer
Following with great interest...
  • asked a question related to Case-Control Studies
Question
3 answers
My question is based on conducting a meta-analysis on the association of multiple variants in a single gene with a complex disorder using published case-control studies.
For my study, around 5 well-studied SNPs in a single gene have been widely reported to be associated with a disorder as single SNPs or as haplotypes (two up to five SNPs in LD varying between different studies).
If I wish to explore associations of a 3-SNP haplotype with the disorder between studies, can I extract data from studies that only report 5- or 4-SNP haplotypes (that include the 3 SNPs) in association with the disease?
Edit: Thank you for your answers.
Relevant answer
Answer
I have only a limited experience with that subject, but SNP alleles could be found associated in LD in such a way as to suppress the main phenotypic effects of only one of them (and YES, thay could be in HW equilibrium, at least in ancient populations). I would be very careful about extracting data of three out of five SNPs if no validation is possible by any experimental approach. Try estimating MAF for each of them could be of help.
  • asked a question related to Case-Control Studies
Question
7 answers
Hi,
For example: If I have 20 eligible studies (Both case-control studies and cross-sectional studies without any control group ) coming out of a systematic search.
Can I do meta-analysis with 10 of the studies (as those 10 studies have presented data of interest and case-control) and systematically review the rest of the 10 studies (without control group or not normally distributed data)?
Regards,
Asiful
Relevant answer
Answer
Yes you can and this is methodologically right.
Systematic review usually consists of narrative and statistical presentation of data. According to the available data you can do meta-analysis of even two studies out of twenty included studies due to abscence of data for analysis.
  • asked a question related to Case-Control Studies
Question
5 answers
I am working with birth defects data with case - control ratio 1:4. However, I would like to choose controls that are a better match with my cases and reduce the ratio to 1:1 or 1:2. I am planning to use propensity score approach to choose my controls from this database. Is this the best method to use?
Relevant answer
Answer
Thanks for the information. I have used the psmatch packaged in STATA to perform propensity score matching but I don´t known how can I get 5 controls for 1 case. Can anyone help me with syntax for STATA??
  • asked a question related to Case-Control Studies
Question
8 answers
For a Dicotomous IV, the OR against DV is lesser then 0.
Does it means a protective effect.
decrease in the IV will increase DV.
Relevant answer
Probably your results are being presented as coefficients, not odds ratio.
The coefficients can be negative, but when you apply the exponential function to convert to odds ration, the previous negative values will be between zero and one.
What software are you using? Some already present the results in odds ratio, like Stata and SPSS. But for other, like R regression packages, you need to manually apply the exponential function on the coefficients.
  • asked a question related to Case-Control Studies
Question
2 answers
I'm trying to solve problem of possible overmatching in case control study dataset. Maybe, you had similar problem and found solutions how to make appropriate analysis of overmatched case-control study data? Is there methods to eliminate overmatching?
Relevant answer
Answer
Hi Giedrius,
Overmatching by itself is not necessarily a big problem, this actually gets you closer to the 'counter-factual ideal' that is the gold-standard for any comparative study.
What are your specific concerns with the dataset? Are there specific matched variables that are of particular importance?
Regards,
  • asked a question related to Case-Control Studies
Question
1 answer
I knew that I have to use conditional logistic regression when I want to analysis of matched pair in matched cohort study or case-control study for getting the RRs or ORs. (Am I right?)
I wonder that if I want to get Hazard ratio (HR), what kind of analytic method can be used?
Is there any specific statistical method in cox proportional hazard analysis such as 'conditional logistic regression"?
Also, If I want to conduct conditional logistic regression, I have to change the data format such as making dummy variable, or give same ID for matched pairs, and these are different from the ordinary data format (which is not matched pair data).
Then do I have to change the dataset to get HR in matched cohort study like what I say above?
Relevant answer
you can use the helper of statistical software to find answer such as "SPSS" and another programmes.
  • asked a question related to Case-Control Studies
Question
4 answers
How do I compute sensitivity analysis for variables in logistic regression model of case-control study?
Relevant answer
Answer
Hey Nigus,
Please see the following link with the hope that it will help you:
Best of luck
  • asked a question related to Case-Control Studies
Question
9 answers
Indeed I have seen the use of OR in several studies that are not case-control studies in journals with high impact factor. What are your points of view?
Relevant answer
Answer
Thank you very much for this answer which further reinforces my understanding. My best wishes 2019
  • asked a question related to Case-Control Studies
Question
3 answers
Hi,
how to perform age- matching for a case control study? I have enrolled 26 healthy controls and 50 cases. Age has an influence on the outcome. Is it a good idea to manually match them?.
Relevant answer
Answer
yes, it should.
  • asked a question related to Case-Control Studies
Question
14 answers
What is the justification for 1:4 ratio in Case Control study?
What are epidemiological and Biostatistics reasons for considering 1: 4 ratio in a case control study? How can we choose four controls per one case?
Relevant answer
Answer
Case control study is a study design for rare diseases. So in order to get requisite number of study subjects we have to strive very hard. So increasing the number of controls is the solution. But it has been found that if we increase the controls beyond 1 : 4, there is no gain in statistical power of the study. So going beyond 4 is futile....
Please feel free to ask any further question
  • asked a question related to Case-Control Studies
Question
4 answers
I am a BSc student and I have a research to study an association between a SNP and a disease,, my study design is case control ..
I am planning to study 2 SNPs
SNP 1 ,, MAF is 27% in case
SNP 2 ,, MAF is 8.89 in case
And I am using OSSE , online sample size estimator which needs the minor allele frequency in controls … can it be 0?? as in controls it should be normal sequence
If not 0 ….How can I now the minor allele frequency in controls ?
· By putting this information’s Iam getting very small size of case as for 13 only in 200 of controls .. ! can I increase the size of cases ?? or can you advice me to the best solution
· If you know another sample size estimator other that OSSE ,,, that can be better in calculation , I would be happy to know
Thank you
soma
Relevant answer
Answer
Hi Soma,
in addiction to their good chocolates, swiss university have good calculation and genetics tools among this one (http://csg.sph.umich.edu/abecasis/cats/gas_power_calculator/) for power calculation.
fred
  • asked a question related to Case-Control Studies
Question
3 answers
What is the justification for 1:4 ratio in Case Control study?
What are epidemiological and statistical reasons for considering 1: 4 ratio in a case control study? How can we choose four controls per one case?
Relevant answer
Answer
Thank you so much Surendra Karki for your quick response & very valuable information.
  • asked a question related to Case-Control Studies
Question
2 answers
Dear colleagues,
I am currently considering the Newcastle-Ottawa Scale (NOS) to appraise risk of bias or methodological quality of non-randomized studies (e.g., cohort and case-control) for my systematic review. This tool is based on three broad perspectives: 1) the selection of study participants; 2) the comparability of the study groups; and 3) the identification of either the outcome of interest or exposure for cohort or case-control studies, respectively. However, I noticed that the original tool is grounded on population- or community-based evidence appraisal. Since my subjects are all hospital-based, the following ‘Selection’ subcategories (item number 2, Selection of Non-exposed Cohorts; item number 3, Selection of Controls) for cohort-type and case-control studies were modified:
Newcastle–Ottawa Quality Assessment Scale for Cohort Studies
Category: Selection
Item No.: 2, Selection of Non-Exposed Cohort.
Item Purpose: This item assesses whether the control series used in the study is derived from the same population as the cases and essentially would have been cases had the outcome been present.
Original Criteria:
a. Drawn from the same community as the exposed cohort
b. Drawn from a different source
c. No description of the derivation of the non-exposed cohort
Modified Criteria:
a. Drawn from the sameICU/hospital as the exposed cohort (e.g. exposed and unexposed drawn from the same database or group of patients presenting at same points of care from same hospital over the same or different time frame)
b. Drawn from different source (e.g. exposed and unexposed drawn from the same database or group of patients presenting two different points of care from another hospital over a same or different time frame)
c. No description of the derivation of the non-exposed cohort
Newcastle–Ottawa Quality Assessment Scale for Case–Control Studies
Category: Selection
Item No.: 3, Selection of Controls
Item Purpose: This item assesses whether the control series used in the study is derived from the same population as the cases and essentially would have been cases had the outcome been present.
Original Criteria:
a. Community controls (e.g., same community as cases and would be cases if had outcome)
b. Hospital controls, within same community as cases (i.e. not another city) but derived from a hospitalized population
c. No description
Modified criteria:
a. ICU-based controls (e.g. same hospital/ICU as cases and would be cases if had outcome) 

b. Hospital controls, within same or similar ICU-type settings as cases (i.e. not another different ICU type) but derived from another hospital
c. No description
I would like to seek opinions from a randomly select group of international experts with extensive experience in using NOS to validate whether the modified items are appropriate for an hospital-based review. Hope to hear from you.
Thank you,
John
Note: bold and Italicized words/statements are modified items
Relevant answer
Answer
Hello Godfrey,
Thank you for your suggestions. I appreciate it. I will take note of this.
Regards,
John
  • asked a question related to Case-Control Studies
Question
3 answers
I am trying to observe epigenetic markers that may identify early stages of COPD or predict disease prognosis in patients with COPD, I'm not quite sure how to calculate the sample size I need as there will be no intervention, only observation. I already calculated based on COPD prevailence of 2% against general population and got a sample size of 385, is this correct? it does seem too large.
Relevant answer
Answer
  • asked a question related to Case-Control Studies
Question
7 answers
Dose-repose meta analysis is restricted to three types of studies: cohort studies with cumulative incidence rate, cohort study with person-year incidence rate, and case-control studies. But, is it possible to combine these three types of studies into one dose-response meta-analysis using STATA software? Waiting for answers, thanks a lot!
Relevant answer
Answer
Epidemiologically, cohort study and case-control study are different types of observational study. While you may be tempted to combine the outcome (because they were measured similarly), it's will be better to stratify your meta-analysis by study type i.e. separate meta-analysis for cohort and separate meta-analysis for case-control. In doing so you will still have the overall estimates which may probably the same as just combining both cohort and case-control together.
Cheers
  • asked a question related to Case-Control Studies
Question
4 answers
Hi all,
Has any one came across a quality assessment tool that is applicable to both observational studies (case control, cross sectional, cohort) and RCTs? i.e. a tool that is applicable to only a specific study design?
I have found Downs and Black that you can use for randomised and non-randomised studies, however wanting to know if there are any others?
Thanks in advance,
Relevant answer
Answer
Hi Godfrey and Mathieu,
I do tend to agree, perhaps using different tools would be ideal.
I appreciate your advice and reference of tools.
Thanks again,
Jordan
  • asked a question related to Case-Control Studies
Question
4 answers
Currently, I am doing a systematic review and I have few questions regarding that.
1. Can I combine results of cross-sectional and cohort studies if the outcome is given as Odds ratio for both of them? If yes then please give me some suggestions about that.
2. Can I combine the results of case-control studies results if some of them are in OR and some in HR?
I will be really thankful if someone can help me out.
Relevant answer
Answer
No OR and RR cannot be combined since they are different ratios.
Yes this is appropriate
  • asked a question related to Case-Control Studies
Question
5 answers
Dear all,
Recently I saw a paper where cases and controls differed at the sequencing depth. I wonder if this indicates a systematic bias, or it may be due to biological variation. I will be more than happy to hear your opinion.
Other question is how these differences can influence the results of alpha-, beta-diversity and relative proportion comparisons.
In my opinion the richness could be influenced, but not Shannon and Simpson index, since they control for differences at the sequencing depth. The relative proportions of reads assigned to certain taxa also should not be influenced, since their purpose is to take into account the differences in sequencing depth. Again it will be nice to hear your opinion :)
Best,
Joanna
Relevant answer
Answer
Hi Joanna,
deep sequencing need lot of preparation steps in which manipulation bias can occur. In addition, quality of the samples can also greatly influence depth.
fred
  • asked a question related to Case-Control Studies
Question
3 answers
I'm doing an analytical cross-sectional study, and i want to use a 2x2 table and find the OR, but i need the correct interpretation; i can only find the traditional one used in case-control studies. They are asking me to present a valid study or scientifc paper that supports my use of OR in a cross-sectional study.
Relevant answer
Answer
i did one cross sectional stidy and found similar problem but spss helped me out
Univariate and bivariate regression in SPSS will help you out in finding both adjusted Odds ratio and unadjusted Odds ratio
Regards
  • asked a question related to Case-Control Studies
Question
7 answers
what is the diffidence between case-control study and cross-sectional study?
Relevant answer
Answer
In cross sectional study exposure and outcome are present at one time no follow up is needed
and we can find out Only prevalence in cross sectional studies
while in case control study cases and control groups are assigned and they are followed up for the particular risk and outcome and we calculate odds ratio relative risk attributable risk and hazards ratio and find how much lethal is effect of risk of outcome
  • asked a question related to Case-Control Studies
Question
6 answers
My work is association based.
Relevant answer
Answer
You may reasonably deduce an association
  • asked a question related to Case-Control Studies
Question
5 answers
for early detection of MI showing highly specificity and sensitivity marker i want to do case control study of CAD patients i want to know the correct sample size
Relevant answer
Answer
See the link below for calculators and detailed answers to your questions:
Best wishes, David Booth
  • asked a question related to Case-Control Studies
Question
3 answers
Dear colleagues
We want to perform a case-control study with aged-matched manner. Could you present me a reference about blocks of 10 or 20 for sample collection?
Also, please present me an article that employed this method in its sample collection.
Thank you
Relevant answer
Answer