critical numbers PT Flashcards
what is a case control study
find people with a disease, look back in time and see if they were exposed to risk factor in question
Retrospective
what are the positives of a case control study
works well for investigating rare outcomes
fast + cheap
few ethical considerations
what are the negatives of a case control study
cannot prove causation/eliminate cofounders
can be difficult to establish order of events
bias (recall)
can only investigate a single disease
what is a cross sectional study
take a sample, see who has the disease right then and there
what are the positives of a cross sectional study
fast/cheap
few ethical considerations
generates hypothesis
what are the negatives of a cross sectional study
cannot prove causation/eliminate bias
less suitable for rare diseases
difficult to get an understanding of order of events
sample bias
what is a cohort study
collect information from a sample, some with exposure, some do not (none with outcome)
follow up over time and see if there is a link between exposure and outcome
prospective
what are the positives of a cohort study
few ethical considerations
clarity on event sequence
what are the negatives of a cohort study
cannot prove causation/eliminate cofounders
not suitable for rare diseases or when disease takes a long time to develop
time consuming/expensive
difficulty following up
patients can change behaviours in the cohort
what is a randomised control trial
multiple groups (arms) , give each different exposures and compare outcomes can balance arms by matching, randomising, cross-over, placebos, binding
what are the positives of a RCT
gold standard - can prove causation by eliminating cofounders
random - less bias
what are the negatives of a RCT
not suitable for rare outcome or when outcome takes a long time to develop
time consuming + expensive
often unethical
issues with follow up/ compliance
what is an ecological study
massive sample, by looking at data previously collected to look at prevalence, trends and correlation (populations, not individuals)
what are the positives of an ecological study
fast/cheap
very large sample - small SE
easy
good to generate hypothesis
what are the negatives of ecological studies
variation/ bias/ inconsistency in data
cannot prove causation
what is ecological fallacy
where there is a correlation between predictor and outcome, but this does not mean causation
what is the target population
the population the sample represents
what is the sample population
the people whom data is collected
what is random sampling
random number generator, “draw a name out of a hat”. Usually preferred way of sampling.
what is systematic sampling
e.g. count of the list and every “k”th element is taken
what is convenience sampling
The first people who approach you are used. Easiest technique but likely the worst.
what is cluster sampling
Divide the population into groups, usually geographically
Each group is called a cluster, or block
Clusters are randomly selected, each element in the selected cluster used.
what is stratified sampling
Divide the population into groups/strata, based not on geography, but some characteristic, e.g. Males or Females.
A sample is taken from each of these strata using either random, systematic or convenience sampling
what is sampling bias
sample is not representative of the target population
what is recall bias
people fail to remember specifics innocently
what is social-desirability bias
incorrect information is given due to societal pressure
what is information bias
where data is consistently measured wrong
what is volunteer bias
volunteers aren’t representative
what is produced bias
subjects in different arms are treated differently
what is reliability
how consistent the results of the study are
what increases reliability
larger sample size
peer reviewed
what is validity
does the test measure what it is supposed to? - have confounders been addressed
what are the 2 types of numeric variable
continuous (any value within a range)
discrete (whole numbers)
what are the 2 types of categorical variables
ordinal (distinct ordering or hierarchy)
nominal (no distinct ordering)
what is risk
number of examined outcomes / total number of possible outcomes
what is the absolute risk difference?
difference between 2 risks
how do you calculate absolute risk difference (ARD)
work out the 2 individual risks for the subsets you’re measuring and then subtract them
how do you calculate number needed to treat (NNT) or harm (NNH)
NNT/H = 1/ARD
how do you calculate risk ratio/relative risk
divide one risk by another
what is odds
the ratio of the probability of the occurrence of the event to the probability of non-occurrence
odds equation
odds = probability / (1- probability)
how do you calculate odds ratio
divide one odd by the other
what is sensitivity
The sensitivity of a test is the proportion of people who test positive among all those who actually have the disease
= true positive/ true negative + false negative
what is specificity
The specificity of a test is the proportion of people who test negative among all those who actually do not have that disease.
= true neg/ true neg+ false pos
what is positive predictive value (PPV)
the probability that following a positive test result, that individual will truly have that specific disease.
= true pos / true pos + false pos
what is negative predictive value (NPV)
the probability that following a negative test result, that individual will truly not have that specific disease.
= true neg/true neg+ false neg
what is test accuracy
the proportion of true result that were revealed
= TP +TN/ TP +TN + FP +FN
what is prevalence
the proportion of people within the community with the disease
how do you calculate standard deviation
minus the mean from every data point, square it and sum all values together. Following this, divide by n-1 and then square root the entire result
what is standard error
the SD of all the sample means S/ square root of n
what does standard error assume
the data is normally distributed and there is a sufficient sample size
what is interquartile range , how do you calculate it and what is it useful for
Used in conjunction with the median to describe data. Calculated by subtracting the upper quartile (75%) from the lower quartile (25%)
Especially useful to use when the data is not normally distributed (i.e. skewed)
what are confidence intervals
give limits in which we are confident (in terms of probability) that the true population parameter lies
how do you calculate 95% confidence intervals
mean +/- 1.96 x standard error
what is the p-value
the probability of obtaining your results or results more extreme, if the null hypothesis is true
when do you reject the null hypothesis
if the p-value is less than 0.05
using Pearson’s correlation coefficient what does +1, -1, and 0 mean
+1 = perfect positive linear association
-1 = perfect negative linear association
0 = no linear relation at all
simple linear regression formula
y = mx + c y - dependent variable m- gradient x- independent variable c- intercept
what is multiple linear regression
expansion of simple linear regression to include multiple independent variables
what is logistic regression
used when your outcome variable (y) is a binary variable
what does PICO stand for
P - patient of population
I - intervention or indicator
C - comparison or control
O - outcome
