Statistics - calculations Flashcards
Number needed to treat (NNT)
definition
How many patients need to be treated with an intervention to reduce the expected number of outcomes by one
Number needed to treat (NNT)
calculation
1/absolute risk reduction (ARR)
Round to the next highest number
Absolute risk reduction definition
Is the difference between the event rate in the treatment group (experimental event rate (EER) )and the event rate in the control group (control event rate CER)
Absolute risk reduction calculation
Outcome undesirable:
ARR=CER-EER
Outcome desirable:
ARR=EER-CER
Experimental event rate (EER) definition/caluation
Number who had particular outcome with the intervention / Total number who had the intervention
Control event rate (CER)
Number who had a particular outcome with the control/ Total number who had the control
Variance definition
A measure of the spread of scores away from the mean
Variance
calculation
Square root stand deviation
Standard deviation calculation
Square root of variance
Odds definition
A ratio of the number of people who incur a particular outcome to the number of people who do not incur the outcome
Odds definition calculation
Total no to benefit from new treatment/those who received treatment but didn’t benefit
Odds ratio definition
Defined as the ratio of the odds of a particular outcome with experimental treatment and that of control
Usual reported measure in case-control studies. It approximates to relative risk if the outcome of interest is rare
Odds ratio example
Odds of experiment arm outcome/odds of placebo outcome = ratio
Probability definition
The fraction of times you’d expect to see an event in many trials – when expressed as a single number probability is always 0 and 1
Incidence definition
A measure of the number of new cases
Incidence calculation
New cases/total group surveyed x requested volume in population
Prevalence definition
A snapshot of existing cases
Point prevalence
Point prevalence = no. of cases in a defined population/number of people in a defined population at the same time
Period prevalence
Period prevalence = no. of identified cases during a specified period of time/total number of people in that population
95% confidence interval definition
a range of values within which the true effect of intervention is likely to lie
IF a repeat sample of 100 observations are taken from the same group 95 of them would be expected to lie in that range
95% confidence interval calculation
Mean +/- 2 x SE
Relative risk
is the ratio of risk in the experimental group (experimental event rate, EER) to risk in the control group (control event rate, CER). The term relative risk ratio is sometimes used instead of relative risk.
Usual outcome measure in cohort studies
relative risk calculation
EER/CER
Relative risk reduction (RRR) or relative Risk increase (RRI)
Divde the absolute risk change by the control event rate
Relative risk reduction (RRR) or relative Risk increase (RRI) calculation
RRI = (EER-CER)/CER
Power of a study definition
Probability of correctly rejecting the null hypothesis (that there is no difference between treatment arm and placebo) when it is false (i.e. not making a type II error)
Power of a study
calculation
Power = 1 – the probability of a type II error
Sensitivity calculation
TP/(TP+FN)
Sensitivity definition
Proportion of patients with the condition who have a positive test result
Specificity definition
Proportion of patients without the condition who have a negative test results
Specificity calculation
TN/(TN+FP)
Positive predictive value definition
The chance that the patient has the condition if the diagnostic test is positive
Positive predictive value calculation
TP/(TP+FP)
Negative predictive value definition
The chance that the patient does not have the condition if the diagnostic test is negative
Negative predictive value calculation
TN/(TN+FN)
Likelihood ratio for a positive test result definition
How much the odds of the disease increase when a test is positive
Likelihood ratio for a positive test result calculation
Sensitivity/(1-specificity)
Likelihood ratio for a negative test result definition
How much the odds of the disease decrease when a test is negative
Likelihood ratio for a negative test result calculation
(1-sensitivity)/specificity
Standard error of the mean
definition
The standard error of the mean is a good measure to determine the accuracy of the mean value of a dataset. You divide the standard deviation by the square root of your sample size
Standard error of the mean
calculation
Standard deviation/square root (number of patients)
Standardised mortality ratio
Definition
is a tool used to compare mortality within different populations while taking into account the effect of confounding factors such as age and sex.
SMR Calculation and result indicates
It is the observed deaths divided by the expected deaths (sometimes multiplied by 100).
An SMR of 100 (or 1) indicates that the mortality in the group being studied is the same as the standard population. An SMR of greater than 100 indicates a higher than expected amount of mortality.
Incidence
is the number of new cases per population in a given time period.
New cases in population over a given time period/total population at risk during that time period 2a
Note: don’t forget that people currently with the disease, or those previously positive for it, are not considered at risk.
Prevalence definition
is the total number of cases per population at a particular point in time. It can be divided into two types:
point prevalence
period prevalence
prevalence calculation
incidence * duration of condition
Point prevalence calculation
number of cases in a defined population / number of people in a defined population at the same time
Period prevalence calculation
number of cases in a defined population / number of people in a defined population at the same time
