Lecture 7
What are the 3 things you can tell from a scatterplot?
Trend, Direction, and Strength
It is risky use the regression line to make predictions about the y-value outside of the range of x-values given because of this.
Extrapolation
With random phenomena, will the predicted probability be closer to what is expected with a short amount of trials or a long amount of trials?
A long amount of trials.
What formula is this?
P(A|B) = P(A & B)/ P(B)
Conditional probability.
Worksheet 6 (Question 7)
Answer is A
This formula measures the strength and direction between two variables.
(hint: denoted by the letter r)
Correlation coefficient
X-value is relatively high or low compared to the rest of the data and/or observation is a regression outlier.
_____ is to an unordered collection as ______ is to an ordered collection.
Combination; permutation
This is the key word to let you know that you are doing conditional probability.
Given.
Worksheet 7 (Question 7)
Answer is D.
The regression line formula.
predicted y = a + bx
If reading level and shoe size are positively correlated, what is the lurking variable? − lurking variable = age
Lurking variable = age.
What is the formula for the union of two events?
P(A or B) = P(A) + P(B) - P(A and B)
I'm drawing cards from a standard deck without replacing them. I record the probabilities of getting reds or blacks. Draw a tree diagram showing the possible outcomes and their probabilities.
RR = .245
RB = .255
BB = .245
BR = .255
Worksheet 8 (Question 7)
Answer is D.
Which has the strongest association?
A: r = 0.12
B: r = 0.65
C: r = 1.-02
D: r = -0.79
D: r = -0.79
What is the main difference between lurking and confounding variables?
Lurking variables are not measured, while confounding variables are. Lurking variables have the possibility of becoming confounding.
I say I think that the president has a 25% chance of being elected again. Is this relative or subjective probability?
How can you tell if conditional probabilities are independent?
P(A|B) = P(A)
Worksheet 9 (Question 4)
Answer is B.
This measurement is defined as the percent of the variability in the response variable that can be explained by the linear relationship between x and y.
(hint: related to correlation coefficient)
Squared correlation (r2)
When the direction of an association between two
variables changes after we include a third variable
and analyze the data at separate levels of that
third variable.
Simpson's paradox.
I roll 2 dice. Whats the probability that I get a sum of 7?
1/6
P(A)= .257 and P(B) = .010
Is P(A|B) independent or dependent?
Dependent.
Worksheet 10 (Question 2)
P = .5982