Search
Create
Chi square, t-test, ANOVA, and a smidge of correlation
STUDY
Flashcards
Learn
Write
Spell
Test
PLAY
Match
Gravity
Terms in this set (12)
What are the three short cut versions of r (correlation)?
1. Phi
2. Point biserial
3. Spearman Rho
When is Phi used for correlation?
Phi is used when both variables are dichotomous (has 2 levels only) such as male/female, yes/no, or pass/fail. Since both variables only have 2 levels, a short cut version of r can be used.
When is Point biserial used for correlation?
when you correlate one variable that is dichotomous with another variable that is continuous (vs Phi where BOTH variables are dichotomous)
When is Spearman Rho used for correlation?
when you have 2 sets of ranks, you use Spearman Rho. For instance if you ask 2 groups to rank a list of stressors from most stressful to least stressful.
It is sometimes referred to as nonparamtric (e.g. distribution free), but it actually is parametric
from wiki → It assesses how well the relationship between two variables can be described using a monotonic function. If there are no repeated data values, a perfect Spearman correlation of +1 or −1 occurs when each of the variables is a perfect monotone function of the other.
What is chi square?
Chi square is the most commonly reported NONPARAMETRIC statistic. It is used when the data is NOMINAL. Chi square can be used with one or more groups.
What is a t-test?
∗Parametric
∗tests differences between 2 groups
∗Interval and ratio level data
∗good for after-only design groups, such as:
R X O2
R O2
∗a correlated t-test would be:
O1 X O2
What is ANOVA?
Analysis of variance
Symbol is F
Used when you have more than two groups, such as the true experimental:
RO1 X O2
RO1 O2
And also the Non-equivalent control group design:
O1 X O2
O1 O2
What is a one way ANOVA?
there is only one independent variable
What is a two way ANOVA?
there are two independent variables
How many "degrees of freedom" or df numbers are there in ANOVA?
2
for example in our article critique, the F results would look like this:
F(1,71)= 4.46
The "1" and the "71" are df numbers
How is the 1st number df calculated?
it is the # of groups minus one
so if you had three groups, 3-1=2. So the 1st number df would be 2 in this example
How is the second number df calculated?
it is the total # of subjects minus the number of groups
so if you had 60 subjects and 3 groups, 60-3=57. So the 2nd number df would be 57 in this example.
;