Stats Flashcards
How is SEM calculated?
Standard Deviation /
square root of ‘n’
n = sample size
Calculate relative risk reduction
100 working women and 110 women who are house wives are followed up through pregnancy. 40 working women had LBW babies and 21 house wives had LBW babies.
Draw table
Top: Behaviour: working/housewife
Left side: Outcome: LBW Y/N
(40/100) / (21/110) = 2.1
2.1
CONTRAST odds ratio of LBW
(40/21) / (60/89) = 2.8
What non-parametric tests can be used to test the induction of labour interval between normal and pre eclamptic women? Name 3
Non parametric is for Names or Not normally distributed
Mann Whitney
Wilcox Rank
Spearman
How is the perinatal mortality rate defined?
The number of stillbirths and the number of neonatal deaths within 7 days of life, per 1000 births
ABO blood grouping is?
Parametric/nonparametric
nominal/ordinal
Non-parametric nominal
What is the risk of uterine rupture during a VBAC after 1 CS?
0.5%
or
1 in 200
The diamond shape Forest graph, lateral angles represents:
95% CI
What is the failure rate of vasectomy
0.5/1000
Null hypothesis is ACCEPTED if
i.e. say the variable is without effect
p > 0.05
Statistical analysis used for data with normal distribution. Name 3
Student t
Pearson (P for parametric)
ANOVA
What is the data type of
‘moderate / mild / severe’
Ordinal
What is an alpha or type 1 error
(with regards to the null hypothesis)
False positive
Incorrectly rejecting the null hypothesis
What gestation is defined as stillbirth rather than miscarriage?
24 weeks
Statistical heterogenicity means
Difference between studies
Calculate maternal mortality ratio
Total number of live births 250,000, early neonatal death 1500, Maternal death 750.
Maternal mortality ratio =
(Maternal deaths /live births) X 100,000
(750/250,000) X 100,000 =
0.003 X 100,000 = 300
Calculate SEM
For a group of 10,000
If the Mean 245 and SD 50.
SEM = SD/√n = 50/√10,000 = 50/100 = 0.5
Which study design would describe the relationship between shoulder dystocia and neonatal birth weight ?
retrospective case-controlled study
Calculation for negative predictive value
TN / TN + FN
What is the mode?
The most frequently occurring number (fashionable!)
Grade B recommendation of RCOG means
well controlled studies but non randomized
Incidence of “RARE” disease when translated into mathematics is?
1:1000 or rarer
Calculate BMI
150cm height and 90 kgs weight
BMI = weight / height in metres squared
90kg / 1.5 x 1.5
90/ 2.25 = 40
<18.5 underweight range.
<25, healthy weight range.
<30, overweight range.
Class 1 Obesity <35
Class 2 Obesity <40
*Class 3 Obesity 40 or higher