Critical Numbers Flashcards
What is confounding variable ?
Alternative explanation for an observed Association
What is the definition of a P value?
A P value tells you the probability that the results were due to chance
What is length time bias?
Screening happens at regular intervals, people may be missed out due to timing of screening
What is leadtime bias?
Difference between knowing about disease and making a difference. One patient knows for two years longer that they have the disease, but both die at the same point.
What is selection bias?
People who choose to participate in screening may differ from general population e.g. may be at higher risk
What is a negative predictive value?
Proportion of people with a negative result who do not have the disease
What is a positive predictive value?
Proportion of people who have a positive screening result who have the disease
What is the definition of specificity?
The proportion of people without the disease who are correctly excluded by the screening process.
What is the definition of sensitivity?
The proportion of people with the disease who are correctly identified by the screening process.
What is a false positive?
Someone who will be screened and shown to have the disease but on further testing do not appear to have disease
What does secondary prevention aim to do?
Detect and treat a disease in its early stages
What is the prevention the paradox?
A larger number of people at small risk of disease may contribute to more cases of the disease then a small number of people who individually at a greater risk
What is the definition of prevalence?
Number of existing cases in a defined population at a defined point in time, divided by the total number of people in the population at that time
What is the conclusion of a small P value?
Your sample results are unlikely when null hypothesis is true . Conclude there is a statistically significant effect
When is a p value statistically significant ?
P value < 0.05
What information do confidence intervals provide ?
Direction of the effect.
Strength of the effect.
Variability of the effect
What is the difference between statistically significant and clinically significant?
Clinically significant difference is one that is big enough to make it worthwhile difference. Statistical significance does not necessarily mean that the effect is clinically significant.
What is the process for hypothesis testing?
Set null hypothesis and alternative hypothesis. Carry out significance test. Obtain test statistic. Compare test statistic to hypothesised critical value. Obtain P value. Less than 0.05 reject null hypothesis
What is a cohort study?
What will happen? Specify factors associated with disease risk with exposure status determined.
What are the strengths of a cohort study?
Multiple diseases/outcomes can be studied. Multiple exposures can be studied. Demonstrates casual affects.
What are the weaknesses of a cohort study?
Need to deal with potential confounding affects. Not suitable for diseases with long latent periods
What is a randomised controlled trial?
What will happen? Randomises participants then applies intervention
What are the strengths of a randomised controlled trial?
Most convincing evidence of cause effect relationship. Insures treatment group similar at the start to prevent confounding.
What are the weaknesses of randomised controlled trial?
Complicated by non-compliance and loss in the follow-up. Not always ethical or feasible
What is a case control study?
What has happened? Retrospective direction of enquiry. Identify factors associated with the risk of disease
What are the strengths of the case control study?
Relatively quick and inexpensive. Multiple exposures can be studied. Suitable for long latency diseases.
What are the weaknesses of the case control study?
Only a single outcome can be studied. Exposure data must be available prior to study so limited potential to establish casual Effects
What is a cross-sectional study?
What is happening? Measures prevalence, established risk factors and symptoms
What are the strengths of a cross-sectional study?
Rapid feedback on current events. Quick and cheap
What are the weaknesses of cross sectional study?
Confounding problems, and difficult to establish disease aetiology.
Selection bias
What does standard error measure?
Measures variability of a sample estimate of the population parameter
What is standard deviation?
Describes variability of observations in sample. The higher the standard deviation the more difficult to get representative data.
How do you calculate a confidence interval?
To standard errors above and below sample mean
What do the widths of the confidence interval depend on?
Sample size. Variability of data. Level of confidence.
What are the two methods to compare risk?
Absolute risk.
Relative risk difference
What is the definition of number needed to treat?
Number of people you need to treat in order to prevent one outcome
What is the definition of number needed to harm?
Number of people you need to treat in order to cause one additional outcome.
In critical appraisal what does RAAMbo stand for?
Representative
Allocated or adjusted
Accounted for
Measurement blind or objective
What do you call the analysis of statistics and a systematic review?
Meta analysis
What does P.I.C.O stand for?
Population/patient
Intervention
Comparison
Outcome
Name five of the CASP checklist for randomised controlled trial?
Were all persons blind to study group?
What is their consistency between groups?
Were there enough participants?
Did the study ask a clearly focused question?
Was it an RCT?
What is an ecological study?
Observational study, uses routine data from population looks at prevalence trends and correlation
What is Association?
Existence of relationship between variables
What is causation?
Existence of casual relationships between variables, cause must proceed affect
What three things should you consider when doing a systematic review?
Validity
Reliability
Applicability
What is a systematic review?
A review of clearly formatted questions that uses systematic methods to critically appraise evidence and to collect and analyse data from studies included in the review
What is the Gini coefficient?
Statistical representation of Nations income distributed among residents.
What are the two types of numerical data?
Discrete data and continuous data
What is numerical data?
Data that has a measurement such as a persons height or weight
What is discrete data?
Discrete data represents items that can be counted,
What is continuous data?
Continuous data represents measurements, the possible values cannot be counted and can only be described using intervals on the real number line.
What is categorical data?
Categorical data represent characteristics such as persons gender, marital status
What is ordinal data?
Ordinal Data mixes numerical and categorical data. The data falls into categories but the numbers placed in the categories have meaning. For examples, rating a restaurant on a scale from 0 to 4
