| Course Description: Overview:
The course provides an understanding of basic statistical methodology to enable the attendee to design their study appropriately, choose the correct statistical analysis relevant to the aims of their research, analyse data using SPSS software, and interpret their own results as well as those in the literature.
Course Link: https://moodle.ucl.ac.uk/course/view.php?id=9868
This Session will cover:
- Summarising Data
- Hypothesis Tests for Numerical Data
- Procedures for Categorical Data
- Correlation and Regression
- Sample Size Estimation
- Assessing Agreement
- Diagnostic Tests
- Measuring Disease Frequency
Learning Outcomes:
- Explain the importance of design considerations underlying a study, with particular reference to clinical trials.
- Summarise data appropriately.
- List the steps involved in performing a hypothesis test: in particular, explain the meaning of the P-value.
- Decide on, perform and interpret the results of an appropriate statistical analysis for the comparison of 2 groups of independent or paired observations when the variable of interest is numerical or categorical.
- Use regression techniques to explain how to investigate the linear relationship between 2 variables, and to extend this concept to the situation in which there are more than 2 explanatory variables of interest(multiple regression) and/or in which the outcome is binary (logistic regression).
- Use power considerations to determine the optimal sample size of a study when the intention is to compare2 groups and the variable of interest is numerical or categorical.
- Assess the agreement between pairs of observations in a repeatability or reproducibility study when the variable of interest is either categorical or numerical.
- Determine the appropriate measures to assess the reliability of a diagnostic or screening test, choose an appropriate cut-off if the diagnostic test is based on a numerical outcome, compare 2 or more tests and evaluate how likely it is that a particular individual does or does not have the outcome (eg disease) of interest after the diagnostic test result is obtained.
- Calculate and interpret simple measures of disease frequency such as a count, risk, rate and odds, and explain how a risk and rate differ. Assess the association between a potential risk factor and a disease outcome by determining measures such as the odds ratio, relative risk and attributable risk.
- Critically appraise the design, statistical methodology, the reporting of the results and their interpretation in published research studies.
|
