Regression Flashcards

1
Q

covariance

A

how 2 variables covary with each other. uses raw score units. unable to tell strength this way. s

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

correlation

A

scale-free degree of linear relationship between 2 varibles. r

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

scatterplot

A

strength of association, direction of it, shape of it

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

pearson correlation

A

magnittude and direction of linear relationship

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

change in magnitude

A

outliers, extreme #’s inflating the mean, curvlinear, errori in x or y

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

correlation does not equal

A

causality

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

correlation coefficient

A

strength of relationship between 2 variables. r

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

Y=mx + b in regression form

A

Y= a +bx, Y=bo + b1x

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

bo

A

regression constant, intercept

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

b1

A

regression coefficient, slope

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

when does regression line pass through y axis?

A

when x=0

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

regression line always passes through

A

x bar, y bar

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

means of predicted y

A

= means of observed y

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Error

A

actual - predicted Y

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

least squares criterion

A

slope and intercept to minimal distance between actual and predicted y. decreases sum of square residuals

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

improves ability to predict Y from using predictors (x)

A

regression

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

R

A

corrleation betwen observed and predicted = absolute value of correlation

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

Rsquared

A

proportion of variance in Y that is accounted for in linear relationship in x. biased, overestimates population

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

adjusted R squared

A

unbiased estimate of population

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
20
Q

stand error orf estimate

A

error present in predicting y from x. decrased SEE is more accurate

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
21
Q

constant unstandardized B

A

Regression constant, bo, intercept

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
22
Q

underneath the constant in unstandardized B

A

slope, regression coefficient

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
23
Q

unstandardized coeff

A

for every unit increase in x, there is a [ ] increase in y

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
24
Q

R2 = .43

A

approxing 43% of the variance in y is accounted for by its linear relationship with x

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
25
for every 1 unit increase in x, y increases by [what factor]
slope
26
multiple regression
looking at multiple predictors
27
1st order model
x has linear relationship with y and does not interact but can correlate
28
holding, controlling, partialling out
studing x1 on y, but x2 can affect that relationship (can be corr with x1, y or both, so we remove the effect of x2
29
effect size R^2
proportion of y that is accounted for in model
30
F test tells what is significantly different than zero
R, Rsquared
31
T test tells what is significantly different than zero
regression coeffecition (slope) when controlling for effects of other variables
32
APprox [ ] percent of the variance in y is accounted for in its linear relationship with x
adjusted r^2
33
a 1 unit increase in x1 is associated with a [-] in loans
decrease [slope]
34
unique contributors
looking at variance over one predictor over and above another
35
holding x2 constant, the predicited y increases by [. ] for every aditional unit of x1
positive slope
36
can pull regression line one way or another
outliers
37
cooks, leverage,
looks at outliers. >2 needs to delete
38
partial correlation
removing the effects of 1 or more varianbles (x2) from both variables (x1, y)
39
how to know variance with part or partial
square
40
part (semi-partial) correlation
removing the effects of one variable (x2) from 1 varianble (x1) but not the other (y)
41
variance accounted for in. x2, over and above the variance accounted for in x1
part
42
variables need to be controlled by
theory
43
common cause hypothesis
if a and b correlate, they share a common cause. Partialling out the effects of the common cause variable will yeild zero
44
common cause example
not wearing seatbelts in 80's caused astronaughts to die in space
45
mediation
if a and b correlate, b/c a causes b through 1 ore more mediator variables, then the correlation of a & b partional out the effects of. the mediator should equal zero
46
mediator efect on significance
can drastically decrease or make not significant
47
medeator causes what
outcome and explains underyling mechanism of relationshp
48
mediator example
grades cause happiness. grades lead to greater self esteem which causes happiness
49
moderation
when relationship of 2 variables depends on another in order to have an effect
50
moderator causes what
significant increase or decrease effect of x on y
51
moderator example
pscyhotherapy decreases depresion fro men more than women. gender is moderator
52
suppressor variables
uncorrelated w/ y but highly correlated with x causing an artificial improvement in x and y when x2 has no bearing on the relationship
53
suppressor reg coeff=
non zero
54
standard regression coeff for x1 is ___ correlated with criterorio
greater
55
x1 < x2(y) who is suppressor?
x1
56
spss suprressor. what will be greater than zero order?
Part
57
Correlation assumptions
x and y linear relationship, data pair independence (x 1 does not relate to x2), bivariate normality
58
correlation assumptions modifications
check scatterplot. should look evenly dispersed, random, no patterns
59
Regression assumptions
normality of residuals, homoskedasticity of residuals, model properly specified
60
sample size for regression
5(p) bare minimum, 20(p) good
61
Regression modifications
homo-plots, normality-histogram
62
model properly specified
no unnessary x's, all important x's in model, lineary between x and y
63
multicollinearity
high correlation between 2 ore more IV's (usually measures of similar constructs)
64
multicollinearity can cause
unstable coefficients, large changes in splope and sign changes, increased stand error. sig F test, but not sig t test
65
Detect multicollinarity
VIF & tol. VIF >3, tol
66
fixing multicollinarity
combine x's into one, drope 1 or more IV's, collect more data
67
Categorial values
need coding
68
Different types of coding
dummy, non weighted, weighted, contrast
69
What will change with coding
regression coeff. ANOVA output is the same
70
Curvlinear
1st order linear, 2nd quadratic, 3rd cubic
71
Determining curvlinear
a priori, scatterplot, problems in residual plot
72
centering
creates deviation around x & makes it meaninful an dmore interpreatable, decreases non essential multicollinearity
73
scaling
leads to non essential multicollinearity
74
enhancing interactions
strengthens relationship
75
buffering,
weakens or cancels out relationsihp
76
Buffering canceling out
life statisfaction= increased job stress, decreased marital problems
77
Logistic regression
predicting dichotomous outcomes
78
probability
uses percentages of something happening
79
odds
ratio of something NOT happening 1:2. (2 x's greater it won't happen)
80
logits
transfromed probabilty, linear
81
prob
negative logit
82
Prob > .5, odds >1
positive logit
83
Simultaneous regression
IV's treated simultaneous on equal footing. leaves every variable with squared partial correlation. restricts amount of variaces accounted for in y
84
hierarchial model
iv's entered cumlatively according to research design. needs r^2 and partial coeff at each point of additon to equation. variance get portioned by entry of variables. assigns causal priority to most appropriate. 1st entry gets greater variance in y than others
85
stepwise
selects predictors based on relative contribution to model. Uses algorithim, little control. a posterior; computer selects greates part2 and greatest contribution to r2. bwd-smalled statististically insignificant factors are dropped. doesn't rely on research question
86
sequential
multivariate technique of using missing data by using sequential regression models