I am NOT a statistician

1

• I am NOT a statistician
• I am not a number
• I am a free person / GP

2
Need to know-

• Need to be able to understand what some of the
  concepts are .
• Other people (including authors) dont understand
  statistics and may use this to mislead reader.

3
Interpretation of data

• Data can be
• Quantitative
• - Discreet e.g. number of children
• - Continuous e.g. serum cholesterol
• Qualitative
• - not a number e.g. sex, blood group
• NB this is not the same as qualitative
  research!

4

• Normal distribution
• particular shape of curve
•  
• Skewed Distribution
•  
• It is possible mathematically to transform a
  skewed to a normal distribution.

5

• Mean
• average
• Mode
• most frequent
• Median
• mid-point
• Standard deviation
• way of describing spread around the mean
• In a normal distribution,
• 95 of values lie within /- 2SD
• 66 of values lie within /- 1SD

6

• Significance test when comparing two groups
  e.g. intervention and non-intervention, you start
  from the assumption that there will be no
  difference
• null hypothesis.
• Experiment/trial being done to disprove this.
• The value of P
• probability that a particular outcome would
  have arisen by chance.

7

• Standard practice (arbitrary)
• P of less then 1 in 20 or lt 0.05 is said to be
  statistically significant.
• P of less than 1/100 or P lt 0.01 is statistically
  very significant.
• BUT 120 times ( 1 paper /journal), this will be
  a fluke.

8

• If P is lt 0.05
• This suggests there is a 95 chance that the null
  hypothesis can be rejected i.e. there is a
  difference between the two groups.
• It does not tell you whether the sample size is
  big enough to be sure.
• Difference between statistical significance and
  clinical significance is important..

9

• Confidence Intervals (CI)
• This allows for an estimation of whether the
  strength of evidence is strong or weak.
• 95 confidence intervals imply that there is a
  95 chance that the real difference lies
  between the two limits given.
• The narrower this range the better.
• If 0 is included the test is not significant i.e.
  P gt 0.05.

10
Confidence intervals (cont).

• If the same trial was done 100 times, in 95 of
  them the TRUE result would lie between these
  limits.
• We do not have to calculate CIs but statisticians
  can do it on all sorts of data.

11
Clinical Significance

• A way to assess if a trial is big enough to give
  a definitive result is to look at the top end.
  2.5 of true results lie above the top number.
• If this range is NOT clinically significant the
  trial can be regarded as DEFINITIVE.

12

• Paired tests
• If something is measured twice on each subject
  (e.g. lying and standing blood pressure) the
  measurement before is paired with the measurement
  after.
• Can apply to measurements taken in the same place
  e.g. bed occupancy of the same ward one week
  apart.

13

• Correlation
• Two independent variables.
• Single pair of measurement on each subject
• Are they correlated? r Pearsons Correlation
  Co-efficient
• Regression
• An equation that allows one variable to be
  predicted from another.

14
Definitions

• Single blind
• subjects dont know which treatment they are
  receiving.
• Double blind
• neither subjects nor investigators know who is
  receiving treatment.
• Cross over
• each subject received both the intervention and
  controlled treatment (randomly) often with wash
  out.
• Patients act as own control.
• Placebo controlled
• controls received inactive or sham treatment

15

• Incidence
• number of new cases per disease per year.
• Prevalence
• overall proportion of population who have
  disease.

16
Risk reduction

• Absolute risk reduction
• The absolute difference in event rates
• CER EER
• Relative risk reduction
• The proportional reduction in rates between
  experiment and control
• (CER-EER)/CER x 100
• Number needed to treat
• The number of patients who need to be treated to
  achieve one additional favourable outcome
• 1/(CER-EER)

17

• Odds Ratio
• Can be used to summarise a systematic review or
  an individual study of treatment.
• It describes the odds of a patient in an
  experimental group having an outcome event
  relative to a patient in a controlled group.
• If Odds Ratio 1, there is no difference between
  the two groups.
• Odds ratio is similar to but different from the
  relative risk.

18
Screening Tests
Validation study comparing the gold standard
with a new screening test.
19

• Sensitivity
• True positive rate a / (ac)
• How good is this test at picking up people who
  have this condition?
• Detects a high proportion of true cases.
• Specificity
• True negative rate d / (bd)
• How good is this test at correctly excluding
  people without the condition?
• A specific test has few false positives.

20

• Positive predictive value
• If a person tests positive, what is the
  probability he/she has the condition?
• a / (ab) i.e. the proportion of test positives
  who are truly positive.
• Negative predictive value
• If a person tests negative what is the
  probability that he/she does not have the
  condition?
• d / (cd) i.e. the proportion of test negatives
  who are truly negative.
• Accuracy
• What proportion of all tests have given the
  correct results
• i.e. true positive and true negatives as a
  proportion of all results.
• (ad) / (abcd)

21
(No Transcript)
22
Forest Plots

• Show the info from the individual studies that
  went into a meta-analysis visual representation
• Show the amount of variation between the studies
  and an estimate of the overall result
• Result of comparative studies shown as a square
  point estimate of result with CI as horizontal
  line
• Overall estimate from meta-analysis and CI at
  bottom diamond
• Area of square proportional to weight that
  individual study contributed to meta-analysis

23

• Now you have a go!