Chapter 2

Question 1

All behavioral research attempts to answer questions about…

Answer 1

behavioral variability

Question 2

Five ways variability is central to research process

Answer 2

1. Psychology and other behavioral sciences involve the study of behavioral variability
2. Research questions in all behavioral sciences are questions about behavioral variability
3. Research should be designed in a manner to answer questions about behavioral variability
4. The measurement of behavior involves the assessment of behavioral variability
5. Statistical analyses are used to describe and account for the observed variability in the behavioral data

Question 3

What are the 3 ways behavior varies?

Answer 3

1. Across situations. people act differently in diff situations. Act diff whether room is hot or cold…
2. Among individuals. Several people will behave differently in the same situation (opposite of first one!) Some ppl shy at a party, some are not
3. Behavior varies OVER TIME. a baby that couldn’t walk a few months ago can run today. A task that was interesting an hour ago has become boring.

Question 4

A well-designed study is one that permits researches to…

Answer 4

describe and account for the variability in the behavior of their research participants. At each step of design and execution, researchers must be sure that their research lets them asnwer their questions about behavioral variability.

Question 5

Descriptive vs Inferential Statistics

Answer 5

Descriptive: Summarize/Describe behavior of participants in a study. Reduce tons of data to simple and interpretable numbers like ratios/averages/percentages
Inferential: Used to draw conclusions about the reliability and generalizability of one’s findings. Can I generalize my findings? How likely was this all due to randomness?

Question 6

Variance

Answer 6

The amount of observed variability in participants’ behavior.
OR
It’s just an indication of how tightly or loosely a set of scores clusters around the mean of scores!

Question 7

Range. Why inadequate?

Answer 7

Difference between larges and smallest scores
OR
Lowest score vs Highest Score
Does not take into account the scores within the range and how much they vary!

Question 8

How does variance use the mean?

Answer 8

It’s just an indication of how tightly or loosely a set of scores clusters around the mean of scores!

Question 9

Steps to get variance

Answer 9

1. Calculate mean
2. Subtract mean from each score. Called DEVIATION SCORE
3. Square all deviation scores
4. Add all the squared deviation scores up (AKA THE TOTAL SUM OF SQUARES)
5. Divide by ONE LESS than the number of participants (Gives us S2!!)

Question 10

S2 (squared)

Answer 10

The variance!

Question 11

The statistical notation for getting S2

Answer 11

S2 = E(yi-y)2 / (n-1)

Second y has a bar over top

Question 12

yi

Answer 12

Symbol for each individual participant’s score

Question 13

y with bar on top

Answer 13

mean

Question 14

Systematic Variance

Answer 14

The part of total variance that is related systematically to the variables being investigated.

Question 15

Error Variance

Answer 15

• Not a mistake!

- The portion of total variance that is unrelated to the variables under investigation

Question 16

How can error variance obscure the systematic effects of other variables?

Answer 16

-Analagous to how white noise can cover up the song or signal you’re trying to listen to… So too many competing variables

Question 17

Effect Size. What mean if .00 or 1.00?

Answer 17

The proportion of Systematic Variance to total variance.
.00 means none of the variance in participants responses is systematic variance
1.00 means perfect relationship. Strongest relationship possible. One variable goes up, the other goes up just as much.

Question 18

Rarely see Effect sizes over?

Average effect sizes fall in?

Answer 18

Rarely ever go above 40%

Average effect sizes fall in the .1-.2 range of r

Question 19

D-based effect sizes

Answer 19

Size of the difference between the means of two groups, such as men and women. Or between participants in two diff experimental conditions.

Question 20

R-based effect size

Answer 20

Already know this! from .00-1.00

The size of correlation between two variables.

Question 21

Odds-ratio effect size

Answer 21

Ratio of odds of an event occurring in one group to the odds of the event occurring in another group.
1.0 = equally likely
<1.0 = odds of event is greater in one group than another, the higher it is the stronger the effect.
e.g. 1 1st years group takes study skills course and one does not. Want to know odds of student dropping out and if the course affects that.

Question 22

When is odds-ratio effect size statistics used?

Answer 22

When the variable being measured only has two levels.

Question 23

Meta-analysis

Answer 23

used to analyze and integrate the results from a large set of individual studies
Explores the degree to which variables are related and also explores the factors that affect their relationship (i.e. was the relationship stronger for men than for women?)