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;
12 Cards in this Set
- Front
- Back
Interval Data
|
- "continuous data"
- known interval between each successive value - continuous and integer - continuous-height, weight, lab values - integer - # of bacterial colonies on a plate |
|
Nominal data
|
- occurs in categories without order
- aka categorical - separate categories or options - Ex= positive/negative, male/female |
|
Ordinal data
|
- inherent ordering w/o standard intervals between measurements
- Ex= pain scales, heart murmurs (I, II, III, IV) |
|
Mean, median, mode
(if you don't know these ...) |
mean= average, sum of all values divided by the number of measurments
median= number of observations above equals the number below (the "middle" data point) mode= the most frequent occuring value |
|
Range, standard deviation, percentile
|
range= lowest to highest values
standard deviation= absolute value of the average differences of individual values from the mean percentile= the proportion of all observations falling between specified values |
|
Using mean and median
|
- with outliers, mean may not be a good measure, use median
- if normal distribution, these are the same |
|
P (probability values)
|
- p values measures how likely a particular difference between groups is to be due to chance
- NOT associated with any statistical test - .05 or smaller to be significant |
|
T Test and Chi square
|
- Use T Test when= measurements are interval and two groups being compared
- Use Chi square when measurements are nominal (categorical) |
|
T Test
|
- most commonly used stat test in literature
- data must be approximately normally distributed and only two groups can be compared |
|
ANOVA
|
- interval data and 3 or more groups to be compared
|
|
Confidence Intervals
|
- convey both variability and statistical significance
- |
|
Confidence intervals vs. P values
|
- both convey statistical significance
- CI gives more info than p values alone because reader cna view a range of "true" values - CI give a perspective concerning sample size and power |