Week 5- Introduction to Evidence Flashcards
What is a null and alternative hypothesises?
Null: hypothesis or no difference
Alternative: research hypothesis
What is the decisions that researchers should come to after their research?
Reject or fail to reject the null hypothesis
What is a type I error?
- Incorrectly reject the null when it is true
- State a change/difference/effect when there isn’t one
What is a type II error?
- Incorrectly accept or fail to reject null hypothesis
- State there is no change/difference/effect when there is one
Describe the process of hypothesis testing?
1) State the research question
2) Specify null and alternative hypothesis
3) Decide on significance level
4) Decide whether to reject or fail to reject the null hypothesis (use of p value)
5) State the conclusion
What is a confidence interval?
- Gives an estimated range of values which likely to include an unknown population parameter
- Estimated range being calculated from a given set of sample data
- We estimate this with various degrees of confidence
- Use information from sample population/statistic to make inference about population parameter
- Wide interval indicates less precise in our estimates and indicates more data should be collected before anything very definite can be said about parameter
What are the purposes of confidence intervals for health care?
- Use results from sample so we can make inference for the population
- For treatment studies, CI shows the range with which the true treatment effect is likely to lie
- CIs tell us range of possible effect size
What are p-values and what is its purpose in health care?
- There is always an element of chance influencing outcomes
- As clinicians/researchers we need to decide how much chance we are allowing to influence our results
- If results show p-value less than 5% then we can reject null hypothesis and accept alternative
