1/35
Looks like no tags are added yet.
Name | Mastery | Learn | Test | Matching | Spaced |
---|
No study sessions yet.
Randomised Controlled Trial (RCT)
The most basic form of a randomised controlled trial (RCT) involves 2 steps:
Divide subjects into 2 Groups: Treatment and Control.
The Control is given a placebo.
Placebo
Fake treatment
Contemporaneous Control group
A contemporaneous Control group occurs at the same time as the Treatment Group.
Historical Control group
A historical Control group occurs at an earlier time than the Treatment Group.
The placebo effect
An effect which occurs from the subject thinking they have had the treatment.
Bias
Something which effects the ability of the data to accurately measure the treatment effect.
Consent Bias
When subjects choose whether or not they take part in the experiment.
Double-blind Trial
When the subjects and investigators are not aware of the identity of the 2 Groups
Observational Study
Research that gathers data in a real-world setting without intentionally manipulating any variable.
The investigator cannot use randomisation for allocation to groups.
4 Precautions of Observational Studies
1. Observational studies can't establish causation.
2. Observational Studies can have misleading hidden confounders.
3. Observational studies with a confounding variable can lead to Simpson's Paradox
4. Observational studies result from using an historical control
Confounding
When the Treatment Group and Control Group differ by some third variable (other than the treatment) which influences the response that is studied.
Hence the seeming effect of the treatment is also caused by other factors.
Survivor bias
when certain types of subjects finish the study
Adherer Bias
when certain types of subjects keep taking the treatment (or placebo), as opposed to the non-adherers.
Selection bias
when some subjects are more likely to be chosen to be in the study than others.
Simpson's Paradox
When relationships between percentages in subgroups are reversed when the subgroups are combined.
How many observations and how many variables in the mtcars set, given this output:
> dim(mtcars)
[1] 32 11
32 observations, 11 variables
Best chart for 1 qualitative variable?
Bar plot
Best chart for 2 qualitative variables?
Double bar plot
Best charts for 1 quantitative variable?
Histogram
Box plot
Best charts for 2 quantitative variables?
Scatter plot
Best chart for 1 quantitative and 1 qualitative variable?
Comparative box plot
What does the area of a box in a histogram represent?
Percentage
What does the height of a box in a histogram represent/
Crowding
What would you call it when an interval contains the left endpoint but excludes the right endpoint? What is the command for this in R?
Eg. an 18 year old would be counted in [18,21) not [0,18).
Left closed, right open
In R: right = F
How many columns/rows does the following output code for:
par(mfrow = c(1, 2))
Puts the graphic output in 1 row with 2 columns
Mean
Average of the data
Median
The middle data point
Which is more robust? The Mean or the Median
Median
What does it mean when a variable is classified as a 'factor' in R
It is Qualitative/categorical
What does it mean when a variable is classified as an 'int' in R
Quantitative, discreet
What does it mean when a variable is classified as a 'num' in R
Quantitative, continuous
What is the mean and SD of the standard normal curve?
Mean: 0
SD: 1
1 SD from the mean of a data set will capture what percentage of the data?
68%
2 SDs from the mean of a data set will capture what percentage of the data?
95%
3 SDs from the mean of a data set will capture what percentage of the data?
99.7%
Interquartile Range
Describes the spread of middle 50% of a data set, IQR = Q3 - Q1.