Biostatistics Flashcards
A study is being conducted, which aims to analyse the effect of a new drug on chronic back pain. Fifty patients were recruited and asked to self-rate their level of pain using a Numerical Rating Scale (NRS). They were then given the new drug and, after 2 hours, asked to again rate their pain using the same NRS.
Wilcoxon signed-rank test - compares two sets of observations on a single sample, e.g. a ‘before’ and ‘after’ test on the same population following an intervention
Not paired T test, bcz it is for parametric data. (Data that can be measured)
Standard error of the mean?
Standard error of the mean = standard deviation / square root (number of patients)
Odds VS probability?
Eg.
the probability of rolling a six is 1/6 or 0.166666
the odds of rolling a six is 1/5 or 0.2
Odds ratio?
The odds of achieving significant pain relief with paracetamol = 40 / 20 = 2
The odds of achieving significant pain relief with placebo = 30 / 60 = 0.5
Therefore the odds ratio = 2 / 0.5 = 4
A study is designed to look at the link between drinking alcohol and liver cirrhosis. One hundred patients with liver cirrhosis were questioned and it was found that 80 of them drank excessive alcohol. As a control, one hundred patients without liver cirrhosis were questioned and only 20 of these patients drank excessively. What is the odds ratio of developing liver cirrhosis for people who drink excessively compared to those who do not?
The odds of a patient with liver cirrhosis having a history of excessive drinking is 80/20 = 4.
The odds of a patient without liver cirrhosis having a history of excessive drinking is 20/80 = 0.25.
Therefore the odds ratio = 4 / 0.25 = 16
What is the odds ratio of developing hypertension if you work more than 40 hours/week compared to people who work less than 40 hours/week?
The odds of developing hypertension if you work < 40 hours/week is 50 / 1000 = 1 / 20 or 0.05
The odds of developing hypertension if you work > 40 hours/week is 60 / 600 = 1 / 10 or 0.1
The odds ratio is therefore = (odds of developing hypertension if you work > 40 hours/week) / (odds of developing hypertension if you work < 40 hours/week) = 0.1/0.05 = 2
Wilcoxon signed-rank test??
Compares two sets of observations on a single sample, e.g. a ‘before’ and ‘after’ test on the same population following an intervention
What are Parametric tests?
1)Student’s t-test - paired or unpaired
2)Pearson’s product-moment coefficient - correlation
What are the Non-Parametric tests?
1) Mann-Whitney U test:
Compares ordinal, interval, or ratio scales of unpaired data
2) Wilcoxon signed-rank test:
Compares two sets of observations on a single sample, e.g. a ‘before’ and ‘after’ test on the same population following an intervention
3) chi-squared test:
Used to compare proportions or percentages e.g. compares the percentage of patients who improved following two different interventions
4) Spearman, Kendall rank - correlation
