Reading...
Play button
Play button
Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
4 Cards in this Set
- Front
- Back
|
Explain how a clinical study represents a sample from a population and describe how the method of sampling may limit the conclusions.
|
A clinical study should try to obtain a sample that is representative of the entire population with respect to the characteristic under investigation. In order to achieve this goal, one must have a random sampling such that the probability of people being chosen is known for each person. If the sampling is biased, then we cannot make conclusions that may be extended to the general population.
|
|
|
Give a description of a clinical study and its variables, distinguish between continuous and categorical variables.
|
Continuous: uses numbers (think spectrum)
Categorical: uses categories such as diseased/non-diseased, etc. |
|
|
For continuous variables, state when it is preferable to use the mean vs. median, the standard deviation vs. standard error, and standard deviation vs. range
|
Default for continuous variables is to use mean and standard deviation to describe central tendency and spread.
If there are many outliers, or if extreme values tend to occur above or below the middle rather than equally, then median and range are better representatives of the central tendency and spread. Standard deviation and range are used to quantify the spread in a sample or population. Standard error is used to quantify the accuracy of a sample estimate of a population quantity (standard deviation of the sampling distribution of a statistic) PRECISION OF AN ESTIMATE. A PRECISE ESTIMATE IS ONE THAT IS LIKELY TO YIELD A SIMILAR VALUE IF WE REPEATED THE SAMPLING AND ESTIMATION OVER AND OVER. for example, say that 9% is a quantity that we calculated. The standard error of 0.7% would mean that we expect to get 9% give or take 0.7%. the larger the sample, the more likely the sample estimate will be close to the true population value |
|
|
Know how to arrange the null and alternative hypotheses
|
Null: usually means "no difference"
Alternative: what we're trying to prove, (i.e. there is a difference) |
