Terms For The Second Research Methods Exam

Front 1

standard error of measurement

Back 1

the standard deviation of an individual’s observed scores from repeated administrations of a test (or parallel forms of a test) under identical conditions; characterizes the accuracy of an individual score

Front 2

standard error of the estimate

Back 2

the standard deviation of the errors of prediction; a measure of the average deviation of the prediction errors about the regression line; a measure of prediction accuracy

Front 3

standard error of a statistic

Back 3

the standard deviation of the sampling distribution of that statistic; depends on the sample size, the larger the sample size the smaller the standard error

Front 4

squared correlation coefficient

Back 4

r2 (r squared) is the Coefficient of Determination – the proportion of the total variability in Y that is accounted for by X; the proportion of variance in common

Front 5

observed score model (classical test theory)

Back 5

an individual’s observed score on a test is the sum of a true score component for the test, plus an independent measurement error component.
X = T + E
X = person’s observed score on the test; T = true score; E = error (E = X – T)

Front 6

Assumptions made about the Observed Score Model’s Components

Back 6

X = T + E, where (mean of the error = 0), rTE = 0 (correlation of the true score and error = 0), rEE’ = 0 (correlation of the error and the predicted error = 0)

Front 7

Relationship between Validity Coefficients and Reliability Coefficients

Back 7

the correlation between the predictor and criterion cannot exceed the square root of the reliability coefficient of the predictor

Front 8

Effect of the Test Length on the Validity

Back 8

the general formula for the correlation of any two sums may also be utilized to determine the effect of test length upon test validity

Front 9

base rate

Back 9

The true proportion of a population having some condition, attribute, or disease; proportion of individuals that would be successful (ex: at a job).

Front 10

selection ratio

Back 10

the number of individuals you select from your applicant pool to fill the [job] position.

Front 11

Taylor & Russell Tables

Back 11

the values in the table are the conditional probabilities of success given that you have been selected. Use the Base Rate, Selection Ratio, and Correlation between the Criterion and Predictor to get your Conditional Probability

Front 12

Spearman-Brown prophecy formula

Back 12

refers to the psychometric reliability to test length; used to predict the reliability of a test after changing the test length

Front 13

multiple regression (correlation)

Back 13

allows the simultaneous testing and modeling of multiple independent variables; only has one dependent variable

Front 14

true positive

Back 14

A test diagnoses you as having a disorder and you actually have it

Front 15

true negative

Back 15

A test does not diagnose you as having a disorder and you do not have it.

Front 16

false positive

Back 16

A test diagnoses you as having a disorder when you do not actually have it.

Front 17

false negative

Back 17

A test does not diagnose you as having a disorder and you have it

Front 18

scales of measurement

Back 18

Nominal Scale – categorizes items without order; ex: gender; Ordinal Scale – classifies and ranks elements/scores; ex: letter grades; Interval Scale – aka: equal unit scale; orders and establishes and equal unit in the scales so that distances between two scores are of known magnitude; ex: performance on a standardized achievement test; Ratio Scale – has equal units and also has an absolute zero in the scale; ex: height

Front 19

reliability of measurement

Back 19

consistency or repeatability of the measures used

Front 20

parallel forms reliability

Back 20

correlation of scores on 2 alternate forms of a test. Reflects consistency across items. (coefficient of equivalence)

Front 21

split-half reliability

Back 21

an internal consistency reliability measure; the correlation between the scores on these two half-tests, adjusted via Spearman-Brown; provides an estimate of the alternate-form reliability of the total test

Front 22

Kuder-Richardson Formula 20 & 21 Reliabilities

Back 22

These are alternative formulas for calculating how consistent subject responses are among the questions on an instrument. Items on the instrument must be dichotomously scored (0 for incorrect and 1 for correct). All items are compared with each other, rather than half of the items with the other half of the items. It is actually the mean of all split-half coefficients resulting from different splittings of a test. K-R 21 assumes that all of the questions are equally difficult. K-R 20 does not assume that.

Front 23

Cronbach's coefficient alpha

Back 23

An internal consistency reliability coefficient based on the number of parts into which the test is partitioned, the interrelationships of the parts, and the total test score variance

Front 24

reliability coefficient

Back 24

the proportion of observed score variance that is due to true score variance

Front 25

validity of measurement

Back 25

The greater the degree of validity of the data collection device, the more confident you will be that the results you achieve reflect true differences in the scores of your subjects and not some random or constant error, the degree of validity will reflect the degree to which we are controlling accounting for constant error. Methods of establishing validity of the measurement technique fall into one of three categories: self-evident measures, pragmatic measures, and construct validity.

Front 26

validity coefficient

Back 26

calculated as a correlation between the two items being compared; the square root of the reliability

Front 27

Criterion-Related/Concurrent Validity

Back 27

the extent to which test scores predict or correlate with performance on an external criterion

Front 28

predictive validity

Back 28

a variant because the criterion is in the future

Front 29

concurrent validity

Back 29

the extent to which test scores predict or correlate with performance on an external criterion

Front 30

construct-related validity

Back 30

indicates that the test scores are to be interpreted as indicating the test taker’s standing on the psychological construct measured by the test

Front 31

content-related validity

Back 31

items on the test measure what they are supposed to fully

Front 32

discriminant validity

Back 32

testing statistically whether two constructs differ

Front 33

convergent validity

Back 33

testing two constructs are similar

Front 34

Likert scale

Back 34

a type of psychometric response scale often used in questionnaires, and is the most widely used scale in survey research; the sum of responses on several Likert items

Front 35

semantic differential

Back 35

measures the connotative meaning of concepts on a bipolar scale; perform factor analyses on the responses

Front 36

analysis of variance (ANOVA)

Back 36

a hypothesis-testing procedure that is used to evaluate mean differences between two or more treatments or populations

Front 37

F-distribution

Back 37

all the possible F values, varies with degrees of freedom (both numerator and denominator); always positive, positively skewed, median F value = approximately 1; used most commonly with ANOVA

Front 38

contingency table

Back 38

the array into which a set of numeration data may be grouped according to two or more classification variables

Front 39

analysis of covariance (ANCOVA)

Back 39

statistical control of variability when experimental control cannot be used; a statistical method for reducing experimental error or for removing the effect of an extraneous variable; removes variability of the pretest in the posttest

Front 40

bivariate normal distribution

Back 40

describes the joint probability distribution of two variables, say X and Y, that both obey the normal distribution; zero correlation (r=0) necessarily means that X and Y are independent random variables

Front 41

error suppressor

Back 41

A predictor variable with a very small correlation with the criterion can still increase the multiple correlation coefficient if it has a large correlation with another predictor. It removes the part of the variable that does not correlate with the predictor, leaving behind that which does correlate with it. ex: Reading Comprehension Tests use speed as a factor. If we do not want speed as a factor in our analysis, we adjust for it and therefore suppress it.

Front 42

isodensity contours of the bivariate normal distribution

Back 42

the set of points for which the values of x1 and x2 give the same value for the density function ; looking at the picture of the bivariate normal distribution like a topography map, it is the concentric ellipses, the height is the same all the way around the ellipse for each line