1 Flashcards
Why conduct medical research?
As you progress in the field of medicine you will realise that scientific research is relevant to clinical decision making at every level, from everyday practice to setting national guidelines (e.g. NICE).
What is a research question?
When conducting a piece of scientific research, we are inevitably attempting to answer a research question. The research question provides the frame for the entire research project. Everything read, experimented and discussed should relate back to it. Research questions may be quite broad and non-specific, Or they may be narrow and specific.
Does exercise prevent osteoporotic fractures? &
Can walking 4 miles a day prevent osteoporotic fractures in post-menopausal women over the age of 55?
Explain role of the hypothesis in regards to the research question, and explain what a hypothesis is
One method of evaluating the research question is via hypothesis testing, which is often done in combination with significance testing using statistics. A hypothesis is a statement that predicts a new finding before the answer is known. There are two types of hypothesis:
Null hypothesis
Alternative hypothesis (or several alternative hypotheses)
These predictions are stated at the outset of a piece of work, and once data have been collected, carefully chosen statistical tests are able to test the validity of the hypothesis.
Explain what a null hypothesis is .
The null hypothesis (sometimes referred to as H0) states that there is no dependent relationship between two variables. One trail of thought is that the null hypothesis is the most important hypothesis to test, as being able to reject it demonstrates the existence of a relationship. That said, the null hypothesis is not often referred to in scientific papers, probably because the authors and readers understand and appreciate its existence as tacit (i.e. doesn’t need to be specifically stated).
Explain what an alternative hypothesis is.
The alternative hypothesis predicts a specific and reproducible relationship between variables.
Staying up all night before an exam will affect exam performance.
Exercise prescriptions will prevent osteoporotic fractures in post-menopausal women.
Sometimes you may predict the direction of the finding, which is especially useful if the results of an experiment can only possibly go in one direction.
Staying up all night before an exam will reduce exam performance.
Exercise prescriptions will reduce the incidence osteoporotic fractures in post-menopausal women.
Although investigators might select a directional hypothesis, which predicts a change in only one direction, when it comes to analysing data it is good practice to check for changes in both directions, in case you miss an effect
Explain what the p-value is
Statistical tests usually include a p-value in their output. The ‘p’ stands for probability and refers to the likelihood that the observed difference (or something more extreme) was observed by chance.
The p-value returns a number between 0 and 1 that calculates the probability your observed results are real. That is to say a study based on a small group reflects what would be observed in the entire population. The p-value is interpreted – and used to reject or fail to reject the hypothesis – by comparing the calculated probability to the significance level, usually denoted as alpha (a).
Explain the relvance of the ‘a’ value
Alpha is the probability of rejecting a null hypothesis when it is true. For example, a significance level of 0.05 indicates a 5% risk of concluding that a difference exists when there is no actual difference. That is to say rejecting the hypothesis when it should not be rejected.
Most authors would consider a p-value to indicate a significant difference when the probability is less than a = 0.05 (less than one in a twenty chance of being wrong). A p-value is censored to show a highly significant difference when the probability is less than a = 0.001 (i.e. less than one in a thousand chance of being wrong).
We can summarise as follows
A very small p-value (typically p ≤ 0.001) indicates very strong evidence against the null hypothesis, so you reject the null hypothesis.
A small p-value (p ≤ 0.05) indicates strong evidence against the null hypothesis, so you reject the null hypothesis.
A large p-value (p > 0.05) indicates weak evidence against the null hypothesis, so you fail to reject the null hypothesis.
p-values very close to the cut-off (0.05) are considered to be marginal (could go either way). Always report the p-value so your readers can draw their own conclusions.
Although your experimental evidence may be strong enough to reject the null hypothesis, it is never strong enough to ‘prove’ it unequivocally.
