Corrections Flashcards
What test is used to compare proportions or percentages e.g. compares the percentage of patients who improved following two different interventions?
Chi-squared test
Prospective vs retrospective cohort study?
Prospective –> look at subjects before exposure to risk factors
Retrospective –> look back at individuals who have already been exposed to risk factors
Which clinical phase typically involves 100-1000’s of people, often as part of a RCT?
Phase 3
Clinical phase IIa vs IIb?
IIa - assess optimal dosing
IIb - assess efficacy
What is the Hawkthorne effect?
Describes a group changing it’s behaviour due to the knowledge that it is being studied
What test is used to assess correlation with parametric data?
Pearson’s coefficient
Parametric - Pearson’s
What test is used to assess correlation with non-parametric data?
Spearman’s coefficient
What is the likelihood ratio for a negative result?
Defined by how much the odds of the disease decrease when a test is negative.
Formula for the likelihood ratio for a negative result?
(1 - sensitivity) / specificity
What is the likelihood ratio for a positive test result?
How much the odds of the disease increase when a test is positive
Formula for the likelihood ratio for a positive test result?
Sensitivity / (1-specificity)
What is normal distribution?
A probability distribution that is symmetric about the mean, showing that data near the mean are more frequent in occurrence than data far from the mean.
What is the power of the study?
The probability of correctly rejecting the null hypothesis i.e. the chance of correctly identifying a statistically significant difference.
Power is increased by increasing the sample size.
Formula for power?
Power = 1 - the probability of making a type II error
Purpose of a significance test?
Uses the sample data to assess how likely the null hypothesis is to be correct.
What is a Spearman’s rank correlation coefficient and Kendall’s rank correlation coefficient used for?
Measures the strength and direction of the association between two variables.
Paired vs unpaired t test?
A paired t-test –> designed to compare the means of the same group or item under two separate scenarios.
An unpaired t-test –> compares the means of two independent or unrelated groups.
What is the chi-squared test used for?
Used to compare proportions or percentages e.g. compares the % of patients who improved following two DIFFERENT interventions.
What is a Wilcoxon signed rank test used for?
Compares 2 sets of observations on a single sample, e.g. a ‘before’ and ‘after’ test on the same population following an intervention.
Define selection bias
Term describing the non-random assignment of patients to a study group.
Selection bias refers to systematic differences in the baseline characteristics of the groups being compared.
How can selection bias be prevented?
Randomisation
What statistical test is used to compare proportions or percentages e.g. compares the percentage of patients who improved following two different interventions?
Chi-squared test
What is the relationship between standard deviation and variance?
Variance = square of standard deviation
SD = square root of variance
Define variance
A measure of the spread of the scores away from the mean
What is intention to treat analysis?
A method of analysis for randomised controlled trials in which ALL patients randomly assigned to one of the treatments are analysed together, regardless of whether or not they completed or received that treatment.
I.e. this analysis includes patients who have dropped out of the trial.
Purpose of intention to treat analysis?
This approach preserves the randomisation process and reflects real-world conditions, ensuring that the estimated treatment effect is not biased by non-compliance or attrition.
What does a power calculation help?
Helps researchers decide how many participants need to be recruited in a study to detect a meaningful difference between the two groups.
If the sample size is too small, there is a higher risk of a type II error. Increasing the sample size of a study increases the power and decreases type II error.
What is there higher risk of if the sample size is too small?
Higher risk of making a type II error
What does increasing the sample size decrease the risk of?
Decreases the risk of making a type II error
What does increasing the sample size increase?
Power
Binary data?
Where each individual’s outcome is one of only two possible categorical responses.
E.g. achieved BP control or not
What significance test compares two sets of observations on a single sample e.g. a ‘before’ and ‘after’ test on the same population following an intervention?
Wilcoxon signed-rank test
What bias occurs when: two tests for a disease are compared, the new test diagnoses the disease earlier, but there is no effect on the outcome of the disease?
Lead-time bias
Recall bias is a major problem in what studies?
Case control studies
Define a clinical audit
A quality improvement process that seeks to improve patient care and outcomes through systematic review of care against explicit criteria and the implementation of change.
What is expectation bias (Pygmalion effect)?
Observers may subconsciously measure or report data in a way that favours the expected study outcome.
What type of trials does expectation bias occur in?
Non-blinded trials
Role of Phase 3 of clinical trials?
- larger studies (e.g. 500-5,000 patients)
- examines efficacy, adverse effects
- may compare drug with existing treatments
- studies of special groups e.g. renal, elderly
Which phase of a clinical trial involves comparing the new drug against existing treatments?
Phase 3
What is odds?
A ratio of the number of people who incur a particular outcome to the number of people who do not incur the outcome.
It is NOT a ratio of the number of people who incur a particular outcome to the total number of people.
Properties of normal distribution: the mean +/- 2 standard deviations contain what % of the values?
95.4%
Properties of normal distribution: the mean +/- 3 standard deviations contain what % of the values?
99.7%
Properties of normal distribution: the mean +/- 1 standard deviations contain what % of the values?
68.3%
What is the 95% confidence interval?
The range of the mean - (1.96 *SD) to the mean + (1.96 * SD)
I.e. If a repeat sample of 100 observations are taken from the same group 95 of them would be expected to lie in that range
What does paired data involve?
2 sets of observations on the same population group e.g. before and after an intervention
What does unpaired data involve?
Comparing the effects of two different types of intervention on two different groups.
Which statistical test is used for paired data and which for unpaired data: Wilcoxon signed-rank test vs Mann-Whitney U test?
Wilcoxon signed-rank test: paired data
Mann-Whitney U test: unpaired data
Define power
The probability of detecting a stastically significant difference
Formula for standard deviation?
Square root (variance)
Formula for variance?
standard deviation squared
Define relative risk
The ratio of risk in the experimental group (EER) to risk in the control group (CER).
Define EER
Experimental event rate
The rate at which events occur in the experimental group
Define CER
Control event rate
The rate at which events occur in the control group
Formula for EER?
Number that event occurred in / total number in experimental group
Formula for CER?
Number that event occurred in / total number in control group
Formula for relative risk ratio?
EER / CER
What does the risk ratio of >1 indicate?
Then the rate of an event (in this case experiencing significant pain relief) is INCREASED comapred to controls.
The relative risk increase should be calculated if necessary.
What does a risk ratio of <1 indicate?
Then the rate of an event is DECREASED compared to controls.
The relative risk reduction should therefore be calculated.
How is the relative reduction (RRR) or relative risk increase (RRI) calculated?
By dividing the absolute risk change by the control event rate.
(EER - CER) / CER
What ratio is typically used when analysing survival over time?
Hazard ratio
What is the most appropriate statistical measure to compare survival time in a study?
Hazard ratio
Formula for standard error of the mean?
Standard error of the mean = SD / square root (number of patients)
What can linear regression be used to predict?
How much one variable changes when a second variable is changed.
What does the Kaplan-Meier survival plot display?
An estimate of decreasing survival with time after an event.
Formula for relative risk reduction?
(EER - CER) / CER
What does a higher p valve indicate?
The higher the chances that the null hypothesis is true and thus should not be rejected.
Lower p value = lower chance of making a type I error (rejecting the null hypothesis when it is true).
