Podcast
Questions and Answers
In a case-control study, what are the subjects referred to as when they have the outcome of interest?
In a case-control study, what are the subjects referred to as when they have the outcome of interest?
What does absolute risk measure?
What does absolute risk measure?
Which of the following statements about relative risk is correct?
Which of the following statements about relative risk is correct?
How is the risk calculated in a population?
How is the risk calculated in a population?
Signup and view all the answers
What is the primary difference between risk and odds?
What is the primary difference between risk and odds?
Signup and view all the answers
If the population prevalence of FeLV in cats is 10%, what are the pre-test odds?
If the population prevalence of FeLV in cats is 10%, what are the pre-test odds?
Signup and view all the answers
What does a higher likelihood ratio indicate in terms of post-test probability?
What does a higher likelihood ratio indicate in terms of post-test probability?
Signup and view all the answers
In terms of exposure groups, what does the term 'unexposed' refer to?
In terms of exposure groups, what does the term 'unexposed' refer to?
Signup and view all the answers
When comparing odds in a study, which formula correctly represents odds?
When comparing odds in a study, which formula correctly represents odds?
Signup and view all the answers
In aetiology, what are 'risk factors' categorized as?
In aetiology, what are 'risk factors' categorized as?
Signup and view all the answers
What are relative measures estimated to assess?
What are relative measures estimated to assess?
Signup and view all the answers
Which of the following is NOT a component of aetiological studies?
Which of the following is NOT a component of aetiological studies?
Signup and view all the answers
What is the interpretation of post-test odds roughly equal to 5.3?
What is the interpretation of post-test odds roughly equal to 5.3?
Signup and view all the answers
What is defined as the 'cause or set of causes' of a disease?
What is defined as the 'cause or set of causes' of a disease?
Signup and view all the answers
Which statement best describes the relationship between prevalence and post-test probability?
Which statement best describes the relationship between prevalence and post-test probability?
Signup and view all the answers
What does NNT stand for in the context of statistics?
What does NNT stand for in the context of statistics?
Signup and view all the answers
Which term refers to the probability of false positives in diagnostic tests?
Which term refers to the probability of false positives in diagnostic tests?
Signup and view all the answers
In which context is absolute risk typically analyzed?
In which context is absolute risk typically analyzed?
Signup and view all the answers
What is a common use of contingency tables?
What is a common use of contingency tables?
Signup and view all the answers
What do sensitivity and specificity most directly measure?
What do sensitivity and specificity most directly measure?
Signup and view all the answers
Which of the following is a use of likelihood ratios?
Which of the following is a use of likelihood ratios?
Signup and view all the answers
What does the acronym CER represent in clinical research?
What does the acronym CER represent in clinical research?
Signup and view all the answers
Which term describes the ratio of the probability of an event occurring to that of it not occurring?
Which term describes the ratio of the probability of an event occurring to that of it not occurring?
Signup and view all the answers
What does an odds ratio (OR) value of 1 indicate regarding exposure?
What does an odds ratio (OR) value of 1 indicate regarding exposure?
Signup and view all the answers
If an odds ratio (OR) is greater than 1, what does this imply?
If an odds ratio (OR) is greater than 1, what does this imply?
Signup and view all the answers
In the given example, what is the odds ratio (OR) calculated?
In the given example, what is the odds ratio (OR) calculated?
Signup and view all the answers
What describes the odds in the unexposed group based on the provided data?
What describes the odds in the unexposed group based on the provided data?
Signup and view all the answers
Which of the following statements correctly interprets the odds ratio of 36?
Which of the following statements correctly interprets the odds ratio of 36?
Signup and view all the answers
What is the formula for calculating the odds ratio (OR)?
What is the formula for calculating the odds ratio (OR)?
Signup and view all the answers
What effect does an odds ratio (OR) value less than 1 indicate?
What effect does an odds ratio (OR) value less than 1 indicate?
Signup and view all the answers
How are odds calculated for the exposed group based on given numbers?
How are odds calculated for the exposed group based on given numbers?
Signup and view all the answers
What does the aetiological strength indicate?
What does the aetiological strength indicate?
Signup and view all the answers
What is the formula for calculating Relative Risk (RR)?
What is the formula for calculating Relative Risk (RR)?
Signup and view all the answers
If the risk in the exposed group is 0.9 and the risk in the unexposed group is 0.2, what is the Relative Risk (RR)?
If the risk in the exposed group is 0.9 and the risk in the unexposed group is 0.2, what is the Relative Risk (RR)?
Signup and view all the answers
What type of outcome does the odds ratio (OR) measure?
What type of outcome does the odds ratio (OR) measure?
Signup and view all the answers
In the example provided, how many individuals were at risk in the exposed group?
In the example provided, how many individuals were at risk in the exposed group?
Signup and view all the answers
What can be inferred if a Relative Risk (RR) value of 1 is obtained?
What can be inferred if a Relative Risk (RR) value of 1 is obtained?
Signup and view all the answers
Which option correctly describes the relationship between odds and risk?
Which option correctly describes the relationship between odds and risk?
Signup and view all the answers
What is the likely implication of a high Relative Risk (e.g., 4.5)?
What is the likely implication of a high Relative Risk (e.g., 4.5)?
Signup and view all the answers
What does absolute risk reduction (ARR) represent?
What does absolute risk reduction (ARR) represent?
Signup and view all the answers
If the control event rate (CER) is 95% and the experimental event rate (EER) is 10%, what is the relative risk reduction (RRR)?
If the control event rate (CER) is 95% and the experimental event rate (EER) is 10%, what is the relative risk reduction (RRR)?
Signup and view all the answers
Which of the following statements about risk reduction is true?
Which of the following statements about risk reduction is true?
Signup and view all the answers
What does the equation RRR = (CER - EER) / CER indicate?
What does the equation RRR = (CER - EER) / CER indicate?
Signup and view all the answers
Given CER = 95% and EER = 10%, what is the absolute risk reduction (ARR)?
Given CER = 95% and EER = 10%, what is the absolute risk reduction (ARR)?
Signup and view all the answers
Why is it important to handle the letters (a, b, c, d) carefully in contingency table calculations?
Why is it important to handle the letters (a, b, c, d) carefully in contingency table calculations?
Signup and view all the answers
If the experimental event rate (EER) increases, what effect does this have on the absolute risk reduction?
If the experimental event rate (EER) increases, what effect does this have on the absolute risk reduction?
Signup and view all the answers
Which measure informs how much more likely an event is to occur in the control group compared to the experimental group?
Which measure informs how much more likely an event is to occur in the control group compared to the experimental group?
Signup and view all the answers
Study Notes
Applied Statistics 2
- This course builds on Applied Statistics 1, covering additional statistical measures and analyses used in research papers.
- Learning outcomes include calculating, interpreting, and explaining terms like risk reduction, absolute risk, relative risk, sensitivity, specificity, predictive values, likelihood ratios, odds, odds ratios, and probabilities (including pre- and post-test odds).
- Students will learn to use contingency tables and interpret survival curves.
- Some content is a review of previous material (VMS2008).
- Different types of research questions (Treatment, Prognosis, and Incidence, Aetiology and Risk, Diagnosis, Prevalence) and suitable study types are covered.
Types of Research Questions
- Treatment: Example - does a supplement reduce lameness in osteoarthritis in dogs?
- Prognosis and Incidence: Example - does sex affect average lifespan in flat-coated retrievers with lymphoma?
- Aetiology and Risk: Example - is general anaesthesia causing increased death risk in ferrets?
- Diagnosis: Example - does milk ELISA have better sensitivity/specificity for fascioliasis than serum ELISA in lactating cattle?
- Prevalence: Example - what is the prevalence of laryngeal neuropathy in adult racehorses during winter?
Contingency Tables
- Contingency tables display frequency distribution of two categorical variables.
- Commonly used to analyze the relationship between two categorical variables (2x2 tables - most frequent).
- A key method for this analysis is Chi-square test.
- Different analysis methods used depending on study specifics.
- Example scenarios covered include "Therapy (vaccination)," "Diagnostic tests (FeLV status)," & "Aetiology (exposure to an adverse outcome)."
Numeracy Reminders
- Conversion between decimals and percentages demonstrated.
- Importance of rounding values when further calculations will be based on them.
Statistics in Research Studies
- Learning Objectives: Calculate, interpret, and explain statistical terms relevant to research.
Risk
- Defined as a proportion—the probability that an event will occur.
- Calculated as (number of subjects/animals with the event of interest) / (total number of subjects/animals at risk).
- Commonly used to compare risk of an outcome between different study groups (e.g., exposure groups, treatment/therapy groups).
- Exposure groups: observational studies.
- Treatment/therapy groups: randomised control trials (ideally).
Risk Reduction
- Refers to the reduction in the likelihood of a bad outcome due to an intervention/treatment.
- Can be measured absolutely or relatively.
- Absolute Risk Reduction (ARR): The absolute difference between two groups (control and experimental/treatment).
- Relative Risk Reduction (RRR): The proportion of improvement in the treated (or experimental) group compared to the control group.
Number Needed to Treat (NNT)
- The number of subjects required to be treated to observe one successful outcome or prevent one additional bad outcome.
- Calculated as the inverse of the absolute risk reduction (ARR).
- A useful clinical measure of treatment benefit (ease of interpretation when compared to ARR).
Confidence Intervals (CIs)
- A range of values around an estimate of a population parameter that expresses an uncertainty.
- Provides an idea of precision around the estimate.
- Wider CIs indicate more uncertainty, usually due to a smaller sample size.
Diagnostic Tests
- Used to determine the presence or absence of a disease or condition.
- Validation studies compare results with a reference standard.
- Key variables: true status (disease or not), test result (+ve or -ve)
Sensitivity/Specificity
- Sensitivity: Proportion of true positives correctly identified.
- Specificity: Proportion of true negatives correctly identified.
Likelihood Ratios
- Another method for assessing diagnostic test quality.
- Positive Likelihood Ratio (LR+): How much more likely a positive test is in those with the disease compared to those without.
- Negative Likelihood Ratio (LR-): How much more likely a negative test is in those with the disease compared to those without.
Odds vs. Probability
- Both are related but distinct statistical concepts expressing likelihood.
- Probability ranges from 0 to 1 (impossible to certain).
- Odds are the ratio of the probability of success to the probability of failure.
Pre- and Post-test Odds and Probabilities
- Pre-test odds/probability refers to the likelihood of having a disease before a test.
- Post-test odds/probability refers to the likelihood after a test.
- Likelihood ratio (LR+) or LR- is used to determine this change.
Survival Curves/Analysis
- Used to measure survival time, typically in clinical studies.
- Data is usually censored.
- Kaplan-Meier method: handles censored data in survival analysis (common, useful estimation method).
- Interpretation of the shape of curves helps understand differences between groups (e.g., effect of different treatments or risk factors).
Studying That Suits You
Use AI to generate personalized quizzes and flashcards to suit your learning preferences.
Related Documents
Description
Test your knowledge on advanced topics in Applied Statistics 2, including concepts like risk reduction, predictive values, and survival curves. This quiz will challenge you to calculate, interpret, and explain essential statistical measures used in research. Ensure you've grasped the various types of research questions and suitable study types covered in the course.