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;
12 Cards in this Set
- Front
- Back
|
Regression
|
Observed differences between the treatment groups on the the dependent variable
|
|
|
Testing for statisical significance
|
Testing for observed differences - are they due to chance
|
|
|
Two regression statisitics used in experimental research to describe the effect of independent variable
|
difference in means and difference in proportions
|
|
|
Mean
|
add the numerical value of a variable and divide my the total number of subjects in the tx group
|
|
|
Proportion
|
divide the number of subjects who fall into the given category of the variable by the total number of subjects in the treatment group.
|
|
|
Correlation statistics
|
Correlation ratio, Somer's D, gamma, Kendall's tau, phi square
0 value= no diff in tx groups 1 or -1 (if relationship is negative) diff between tx group but no difference between subjects in tx group |
|
|
Test statistics
|
F or Students's t, Mann-Whitney U and chi square
assess the probability the difference between tx groups could be do to chance |
|
|
Level of measurement
|
what kind of mathematical operations are theortically meaningful in talking about variation in the variable
|
|
|
Nominal scale variable
|
is variable classified as same category (=) or not =
|
|
|
Ordinal scale variable
|
categories show more of a variable >,<,
ex. anxiety low, moderate, high |
|
|
Interval scale variables
|
can be used to determine how much higher(or lower) one subject is onthe variable than another subject
ex. temperature and BP |
|
|
Ratio scale variable
|
compare proportional extent to which one subject has a higher score than another
ex. # of days a pt stays in hospital after surgery |
