Professional Documents
Culture Documents
Clinical Librarian
Is it relevant – PICO
Is it valid – chance
Is it valid – bias/confounding
Is it useful – effect size
BIAS RAMMBO
Treatment a b
Control
c d
Risk: the number of participants having the event in a group divided by the total number of
participants
Odds: the number of participants having the event divided by the number of participants not
having the event
Risk ratio (relative risk): the risk of the event in the intervention group divided by the risk of
the event in the control group
Odds ratio: the odds of the event in the intervention group divided by the odds of the event in
the control group Treatment
Control
Risk difference: the absolute change in risk that is attributable to the experimental
intervention
Number needed to treat (NNT): the number of people you would have to treat with the
experimental intervention (compared with the control) to prevent one event (in a specific time
period).
EER = Experimental Event Rate, CER = Control Event Rate
Outcome
YES NO
Treatment a b
Control
c d
Treatment a b
Control
c d
ODDS
Q2: For these 133 women, what is the odds of having the event (still infected)?
RR = no. with event in treatment group / no. with event in control group
no. in treatment group no. in control group
= (14/133) / (128/148)
= 0.1 / 0.86
= 0.12
OR = no. with event in treatment group / no. with event in control group
no. without event in treatment group no. without event in control group
= (14/119) / (128/20)
= 0.118 / 6.40
= 0.018
Treatment a b
Control
c d
Treatment a b
Control
c d
SAFE Study
http://www.nejm.org/doi/pdf/10.1056/NEJMoa040232
NEJM Correspondence
http://www.nejm.org/doi/full/10.1056/NEJM200410283511818
Journal Club Commentaries
http://www.biomedcentral.com/content/pdf/cc3006.pdf
http://www.biomedcentral.com/content/pdf/cc8940.pdf
Outcome
YES NO
Treatment a b
Control
c d
Type of outcome
Rao, S.C., Athalye-Jape, G.K., Deshpande, G.C., Simmer, K.N. and Patole, S.K., 2016. Probiotic supplementation and late-
onset sepsis in preterm infants: a meta-analysis. Pediatrics, 137(3), p.e20153684.
Use of weaning protocols for reducing duration of
mechanical ventilation in critically ill adult
patients:Cochrane systematic review and meta-
analysis
BMJ 2011;342:c7237
Heterogeneity primarily denotes that the range of
results varies among included trials. Although
heterogeneity may be due to chance alone, it can also be
caused by clinical or methodologic differences among
trials and might thereby result in systematic errors.
Occurs where the results of different studies vary from each other more
than might be expected by chance. Visually, on a Forest Plot, where the CI
lines do NOT overlap. Significant heterogeneity would rule out meta-
analysis, alternatives would include sub-group or sensitivity analysis.
When a distribution is negatively skewed, the mean will be
higher/lower/the same as the median?
A.Higher
B.Lower
C.Same
Book prices in UK: a "Recommended retail price" is generally the
modal price, and virtually nowhere would you have to pay more. But
some shops will discount, and a few will discount heavily.
Age at retirement: most people retire at 65-68 which is when the state
pension kicks in, very few people work longer, but some people retire
in their 50s and quite a lot in their early 60s.
For a normal distribution, 68% of the observations are within +/- one
standard deviation of the mean, 95% arewithin +/- two standard
deviations, and 99.7% are within +- three standard deviations
1. Normal distributions are
symmetric around their mean.
2. The mean, median, & mode of a
normal distribution are equal.
3. The area under the normal curve
is equal to 1.0.
4. Normal distributions are denser
in center, less dense in tails.
5. Normal distributions defined by
two parameters, the mean (μ)
and the standard deviation (σ).
6. 68% of the area of a normal
distribution is within one standard
deviation of the mean.
7. Approx 95% of the area of a
normal distribution is within two
standard deviations of the mean.
The standard deviation summarises the amount by which every value
in a dataset varies from the mean. It indicates how tightly the values
are bunched around the mean. It is the most robust and widely used
measure of dispersion since, unlike the range and inter-quartile range,
it takes into account every variable in the dataset.
100 subjects’ ages are normally distributed with a mean of 41 years and
a standard deviation of 4 years. Select the true statement
A.At least 5 subjects will be older than 49
B.16 subjects will be below 37 years of age
C.75 members of the study will be aged 37 and 45
D.50 of the subjects will be between 39 and 43 years of age
E.50% of the cohort will be between the age 37 and 45
Age of dementia diagnosis length of hospital stay
A positive skew distribution is one in which there are many values of a low magnitude
and a few values of extremely high magnitude, while a negative skew distribution is one
in which there are many values of a high magnitude with a few values of very low
magnitude.
Kurtosis is all about the tails of the distribution — not the peakedness or flatness. It is used to describe the extreme values in one
versus the other tail. It is actually the measure of outliers present in the distribution.
High kurtosis indicates that data has heavy tails or outliers. If a high kurtosis, we need to investigate why so many outliers. It
indicates a lot of things, maybe wrong data entry or other things. Investigate!
Low kurtosis indicates data has light tails or a lack of outliers. Low kurtosis (=too good to be true), then we need to investigate
and trim the dataset of unwanted results.
Mesokurtic: similar to the normal distribution. Extreme values of the distribution are similar to that of a normal distribution
characteristic. In this definition the standard normal distribution has a kurtosis of 3.
Leptokurtic (Kurtosis > 3): Distribution is longer, tails are fatter. Peak is higher and sharper than Mesokurtic, data are heavy-
tailed or a profusion of outliers. Outliers stretch the horizontal axis of the histogram graph, so the bulk of the data appear in a
narrow (“skinny”) vertical range, thereby giving the “skinniness” of a leptokurtic distribution.
Platykurtic: (Kurtosis < 3): Distribution is shorter, tails are thinner than the normal distribution. The peak is lower and broader
than Mesokurtic, which means that data are light-tailed or lack of outliers.
The reason for this is because the extreme values are less than that of the normal distribution.
Parametric tests assume data is drawn from a population with
a normal distribution.
MEDIAN
- Middle score in an ascending set of data, good for odd numbers of scores, need to
average the middle two if even number; less affected by outliers and skew
MODE
- most frequent value; highest bar in a histogram or bar chart; ‘most popular’ score
- but not unique, there may be two modes, may not identify central tendency
Mean (Average) – Median (Middle) – Mode (Typical)
The more skewed the distribution, the greater the difference between the median and mean,
and the greater emphasis should be placed on using the median as opposed to the mean
If dealing with a normal distribution, and tests of normality show that the data is non-normal, it
is customary to use the median instead of the mean.
However, this is more a rule of thumb than a strict guideline. Sometimes, researchers wish to
report the mean of a skewed distribution if the median and mean are not appreciably different
(a subjective assessment), and if it allows easier comparisons to previous research to be made.
Standard Deviation - a number representing how far from the average each score is
The square root of the variance
Range – IQR – Variance – Standard Deviation
Variance: Would the variance of 10, 12, 17, 20, 25, 27, 42, and 45 be larger if
the numbers represented a population or a sample?
Variance, if these numbers represent a sample you divide by N-1 (instead of N).