Statistics + definitions Flashcards
What shape is normal distribution on a graph?
Symmetrical bell-shaped curve
Describe mean, median and mode in normal distribution.
Mean = median = mode
Which way is the graph shifted in a positive skew?
To the left (tail to the right)
Describe mean, median and mode in a positive skew.
Mean > median > mode
Which way is the graph shifted in a negative skew?
To right right (tail to the left)
Describe the mean, median and mode in a negative skew.
Mode > median > mean
What is epidemiology?
The study of the distribution and determinants of health-related states and events, including disease, and the application of this study to the control of disease.
Define prevalence.
The proportion of individuals within a population that have a disease at a given point in time.
Define incidence.
The number of new cases of disease that occur in a set period of time.
How is prevalence normally expressed?
As a percentage or fraction of the population.
What is the main study used to asses prevalence?
Case-control study
What study type is used to assess incidence?
Cohort study
How is incidence usually expressed?
As a fraction of the population.
How is prevalence calculated?
Number of people with disease/ total number of people
How is incidence calculated?
Number of new cases of disease / population
Define variance.
A measure fo the spread of observations around the mean.
What is standard deviation?
A measure of how spread out a set of data is.
What is standard error of the mean?
The standard deviation of the sample distribution.
Describe the relationship between standard error of the mean and standard deviation.
Directly proportional
Describe the relationship between standard error of the mean and sample size.
Indirectly proportional
What does a confidence interval show?
The precision of a result with reference to the whole population.
What is a 95% confidence interval?
Says that there is a 95% probability that the true value lies within the date set.
In normal distribution, what percentage of observations lie within 1 SD of the mean?
68%
In normal distribution, what percentage of observations lie within 2 SDs of the mean?
95%
In normal distribution, what percentage of observations lie within 3 SDs of the mean?
99%
Within what exact SD do 95% of results lie within?
1.96
What is the range of a data set?
The difference between the highest and lowest values in a data set.
What is interquartile range a measure of?
Statistical dispersion
What is interquartile range?
The data that lies between the 25th and 75th gentiles.
What does the null hypothesis state?
That there is no statistical significance between the populations.
What is the p-value?
The probability of rejecting the null hypothesis when the null hypothesis is true.
What is the relationship between sample size and p-value?
The larger the sample size, the smaller the p-value.
What happens if the p-value is less than a pre-determined significance level?
The null hypothesis can be rejected (result is likely to be statistically significant).
What is a type I error?
Rejecting the null hypothesis when it is true.
What is a type II error?
Accepting the null hypothesis when it is false.
What is power?
The power of a test measures the test’s ability to make a correct decision.
What does the power of a study define?
The study’s ability to demonstrate an association between 2 variables if one actually exists.
What does a z-score indicate?
How many standard deviations a result is from the mean.
What does it mean if a z-score is 0?
That the result is equal to the mean.
If the z-score is greater than 2.2 what does this mean?
That the null hypothesis can be rejected.
In which studies are odds and odds ratios used?
Case-control studies (because risk cannot be calculated)
Define relative risk.
The ratio of the probability of an event occurring in the exposed group versus the non-exposed group OR the probability of an event occurring in a treatment group versus in a placebo group.
What is EER?
The rate at which an event occurs in the experimental group.
What is CER?
The rate at which an event occurs in the control group.
How do you calculate relative risk (risk ratio)?
Risk in exposed group / risk in unexposed group.
**EER/CER
How do you calculate EER?
B/A
How do you calculate CER?
D/C
What does it mean if risk ratio is >1?
The rate of an event is increased compared to controls.
What does it mean if risk ratio is <1?
The rate of an event is decreased compared to controls.
How do you calculate relative risk?
(number with disease in exposed group / total exposed) DIVIDED BY (number with disease in unexposed group / total unexposed).
**(a/a+b)/(c/c+d)
How do you calculate relative risk reduction?
(EER-CER)/CER
Define number needed to treat.
The number of people you need to treat with a drug in order to prevent one bad thing happening.
How do you calculate number needed to treat?
1 / absolute risk reduction.
How do you calculate absolute risk reduction?
Event rate in control group - event rate in treatment group.
**a/(a+b) - c/(c+d)
What is absolute risk reduction?
The difference in event rate between control group and treatment group.
What does a p-value show?
The p-value shows the probability that a null hypothesis is true.
What does it mean to have a 95% confidence interval?
That you are 95% certain that the true value for a population lies within this range.
What happens as a p-value becomes smaller?
There is an increased likelihood that the null hypothesis will be disproven.
What does it mean if a p-value is <0.05?
his means that it IS statistically significant.
**Indicates strong evidence against the null as there is a less than 5% chance that the null is correct.
**Means that the null can be rejected.
What does it mean if a p-value is >0.05?
This means that it IS NOT statistically significant.
Define risk.
The probability that an event will occur during a specified time.
**number who get the thing or event/ total number of people
How do you calculate odds?
probability that ‘x’ happens / probability that ‘x’ does not happen.
** (p x ‘x’) / 1 - (p x ‘x’)
How do you calculate odds ratio?
Odds in exposed group / odds in unexposed group.
Define sensitivity.
The ability of a test to correctly identify disease.
How do you calculate sensitivity?
Number of true positives / all those with disease.
Define specificity.
The ability of a test to correctly exclude a disease
How do you calculate specificity?
Number of true negatives / all those without disease.
Define positive predictive value.
Chance of having the disease if your test is positive.
Define negative predictive value.
Chance of not having the disease if your test is negative.
How do you calculate positive predictive value?
True positives/ all those who tested positive
How do you calculate negative predictive value?
True negatives/ all those who tested negative
How do you calculate the likelihood ratio for a positive result?
The chance that a test is positive if a patient has the disease/ the chance that the test is positive if the patient is well.
Sensitivity/ (1-specificity)
How do you calculate the likelihood ratio for a negative result?
The chance that a test is negative if a patient has the disease/ the chance that the test is negative if the patient is well.
(1-sensitivity) / specificity
The larger the positive likelihood ratio….
… the greater the chance that you have the disease is your test is positive.
The smaller the negative likelihood ratio…
… the lesser the chance that you have the disease if your result is negative.
What does it mean if a likelihood ratio is >1?
The information increases the likelihood of a suspected diagnosis.
What does it mean if a likelihood ratio is <1?
The information decreases the likelihood of a suspected diagnosis.
What are the disease criteria for an effective screening programme?
Condition should be an important health problem
Natural history of the condition should be well understood
There should be a detectable early stage
What are the test criteria for an effective screening programme?
Test should be acceptable
Intervals for repeating the test should be determined
What are the treatment criteria for an effective screening programme?
An effective treatment must be available
Treatment at an early stage should be of more benefit than at a later stage.
What are the health system criteria for an effective screening programme?
Adequate health service provision should be made for the extra clinical workload resulting from screening
The risks, both physical and psychological, should be less than the benefits
The costs should be balanced against the benefits
