inferential or descriptive statistics practice

Question 1

define inferential statistics

Answer 1

getting a sample that represents a population of people and then using those results to make in inference about the entire population. While this process isn’t perfect and it is very difficult to avoid errors, it allows researchers to make well reasoned inferences about the population in question. ex- election night results

Question 2

define descriptive statistics

Answer 2

statistics that are limited to your data and not giving any conclusions about a full population.
reduces mass of data to one or two relatively understood values
i. Measures of central tendency
ii. Correlation
iii. regression

Question 3

the average age of the students in a statistics class

Answer 3

descriptive

Question 4

The chances of winning the California lottery are one chance in twenty-two million

Answer 4

inferential

Question 5

There is a relationship between pregnant women smoking cigarettes and low-birth-weight-babies

Answer 5

inferential

Question 6

From past figures, it is predicted that 39% of the registered voters in Texas will vote in the June primary

Answer 6

inferential

Question 7

a survey that tells you how many people in a class prefer vanilla ice cream

Answer 7

descriptive

Question 8

wanting to know the favorite ice cream flavor of everyone in the world

Answer 8

inferential

Question 9

what is the relationship of reliability and validity?

Answer 9

a test can be reliable but not valid

Question 10

What two things impact error in classical test theory?

Answer 10

1. trait error - didn’t study, anxious, late to test

2. method errors - error that resides in testing situation - loud noises that distract test takers, hot.

Question 11

what are the four main types of reliability discussed in your text?

Answer 11

test-resest, parallel forms, internal consistency, and interrator reliability

Question 12

When do you use test-retest reliability and how do you do it?

Answer 12

when: you want to know whether a test is reliable over time
How: Correlate scores from one test taken at two different times.

Question 13

When do you use parallel forms and how do you do it?

Answer 13

when: you want to know if several different forms of a test are reliable or equivalent
how: Correlation between two test scores

Question 14

When do you use internal consistency reliability and how do you do it?

Answer 14

when: you want to know if the items on a test asses one, and only one dimension
how: correlate each individual item score with the total score


Question 15

When do you use interrator reliability and how do you do it?

Answer 15

when: you want to know whether there is consistency in the rating of some outcome
how: Examine agreement between raters (Judges)

Question 16

What is the Spearman-Brown Correction formula? Why would you use this?

Answer 16

Corrects lowered reliability - allows us to estimate what reliability would be if the test were not split in half. Typically reported as the “corrected” split-half reliability coefficient

Question 17

What is the range of a correlation coefficient (i.e. what would the number look like)? What else is this called?

Answer 17

a. A correlation coefficient ranges from -1.0 to +1.0.

b. Reliability Coefficient

Question 18

Be able to interpret a reliability coefficient. For example, if you see a coefficient of .88, how much is accounted for be true score variance, and how much would be considered error?

Answer 18

88% of the variance in test scores would be accounted for by true score variance and 12% would be accounted for be error score variance

Question 19

How can you usually increase reliability of a test?

Answer 19

increase the number of items

Question 20

What type of reliability would you typically use with a Likert scale?

Answer 20

internal consistency

Question 21

How do you compute test-retest reliability?

Answer 21

Interval of time should be long enough to reduce memory effects, but not so long that real changes could have occurred.

Question 22

What types of validity are concurrent validity and predictive validity?

Answer 22

criterion validity

Question 23

What is concurrent validity?

Answer 23

Criterion measures are obtained at approximately the same time as the test scores

Question 24

What is predictive validity?

Answer 24

predictive - to predict how something will be in the future. Give test to applicants for a position.
 For all those hired, compare their test
scores to supervisors’ rating after 6 months on the job.
 The supervisors’ ratings are the criterion.
 If employees scored on the test similarly to
supervisors’ ratings, then predictive validity of test is supported.

Question 25

What are the 3 types of validity?

Answer 25

content, criterion-related, construct

Question 26

When do you use content validity and how do you do it?

Answer 26

Often addressed in academic and vocational testing,
where items need to reflect the knowledge required for a given area (e.g., history) or job skill (e.g., accounting); licensing tests for psychologists.
Make sure the content is an accurate sample of what you want to test.

Question 27

When do you use criterion-related validity and how do you do it?

Answer 27

Demonstrated when a test is shown to be effective in estimating an examinee’s performance on some outcome measure
 EX – SAT (test) being used to predict GPA
(criterion)
 Chapel attendance used to predict
religiosity (criterion)

Question 28

When do you use concurrent validity and how do you do it?

Answer 28

concurrent- measures are obtained at the same time as the test scores. ex- diagnostic clinical tests (battery given at same time)

Question 29

What is face validity?

Answer 29

appears to be valid, makes intuitive or common sense

Question 30

What is a z score and why is it so cool?

Answer 30

a. Defined as the Number of standard deviations above or below the mean
b. Z scores across different distributions are comparable. A z score of 1 will always represent the same relative position in a set of scores regardless of mean and standard deviation. This is what makes it useful!

Question 31

What is the difference between a z score and a t-score?

Answer 31

Standard score that uses z scores and converts to positive number (eliminates negative numbers).

Question 32

Why is a standardization sample important?

Answer 32

because represent the population for which the test is intended

Question 33

Why are norms useful?

Answer 33

They allow us to compare outcomes with others in the same test-taker group.

Question 34

What is a raw score and how is it different from a percentile or standard score?

Answer 34

original, untransformed score - before any operation is performed on it. It is the observed score.
They form the basis for other scores, such as percentiles and standard scores

Question 35

What is a percentile rank?

Answer 35

Point in a distribution of scores below which a given percentage of scores fall; most common score for reporting test results. It is a location along a continuum from 0 to 99. It is NOT a percentage.

Question 36

What is construct validity and how do you use it?

Answer 36

A construct is a theoretical, intangible trait in
which individuals differ (EX –, hostility, depression)
 build a case for construct validity piece by
piece
 similarly to building evidence for a theory.
 EX – GPA is probably related to intelligence
but would not fully explain intelligence

Question 37

HOW DO WE MEASURE CONSTRUCT VALIDITY?

Answer 37

 Correlation with other tests measuring a
similar construct – don’t want the coefficient too high or you are measuring too much of the same thing.
 Can measure against a test that should be
measuring something independent (different) from your test
 Multitrait-Multimethod matrix

Question 38

What types of validity fall under construct validity?

Answer 38

convergent and discriminant

Question 39

correlations between two different methods of the same trait should be high – (convergent validity)

Answer 39

monotrait-heteromethod

Question 40

relationship between a single method of measuring two different traits should be low (discriminant validity)

Answer 40

Monotrait-heterotrait