Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
47 Cards in this Set
- Front
- Back
Measurement
|
assigning numbers to characteristics of objects according to prespecified rules
|
|
Scaling
|
creating a continuum upon which measured objects are located
|
|
Description
|
Nominal Scales
Unique labels or descriptors that are used to designate each value of the scale All scales posses description |
|
Scale Characteristics
|
Description
Order Distance Origin |
|
Order
|
Ordinal Scales
relative sizes or positions of descriptors denoted by greater than less than equal to |
|
Distance
|
Interval
Absolute differences between the scale descriptors are known and may be expressed in units |
|
Origin
|
The origin of characteristics means that the scale has a unique or fixed beginning or true zero point
|
|
4 Primary Scales of Measurement
|
Nominal
Ordinal Interval Ratio |
|
Nominal
|
numbers serve as labels and tags
one to one correspondence numbers don't reflect amount of characteristics |
|
Ordinal Scale
|
ranking scale
which do you prefer better? how many hours of hw did you do last night? more than ten, less than ten etc |
|
Interval Scale
|
-Numerically equal distances on the scale represent equal values
-Zero Pt Not fixed -Can do most statistical analysis. Even Mean. |
|
With an interval scale, can you say, people prefer the brand 2X as much?
|
No
|
|
Ratio Level
|
Represents a real #
Fill in the blank Constant Sum Difficult because people are sensitive and can't remember data |
|
3 Comparative Scaling Techniques
|
Rank Order
Paired Comparison Constant Sum |
|
What's the formula for #'s of comparisons you need to make for Paired Comparison?
|
[n(n-1)]/2
|
|
Paired comparison
|
Respondent is presented with two objects and asked to select one according to some criteria
Data is ordinal Most widely used comparitive scaling technique Possible to to convert data to a rank order |
|
Comparative vs Non Comparative
|
Comparative compares two objects
Noncomparative - item is evaluated alone |
|
Rank Order Scaling
|
respondents are presented with several objects simultaneously and asked to order or rank them
ordinal data n-1 scaling decisions need to be made |
|
Constant Sum Scaling
|
Respondents allocate a constant sum of units such as 100 points to attributes of a product to t reflect their importance.
can say 2x as important here |
|
What measurements can you get from nominal scales /
|
%
mode |
|
What measurements can you get from Ordinal
|
%
median |
|
What measurements can you get from Interval
|
range, mean, st dev
|
|
What measurements can you get from Ratio
|
all, geometric mean
|
|
Advantages of Comparative Scales
|
smalle differences btw stimulus objects can be detected
same known reference pt for all respondents easily understood and can be applied involve fewer theoretical assumptions tend to reduce halo or carryover effects from one judgment to another |
|
disadvantages of comparative scales
|
ordinal nature of data
inability to generalize beyond stimulus objects detected |
|
2 Non comparative rating scales
|
Continuous
Non continuous |
|
Continuous Rating scale
|
respondents rate the object by placing a mark at the appropriate position on a line that runs from one extreme of the criterion variable to the other
|
|
Itemized Rating Scales 3
|
Likert
Stapel Semantic Differential |
|
Likert
|
Most Common
Requires respondents to indicate a degree of agreement of disagreement with each of the series of statements about the stimulus objects IE Strongly Disagree Disagree Neither Agree/Disagree Agree Strongly Agree |
|
When do you reverse Scale
|
Likert scales--- to check for reliability to make sure respondent is paying attention.... write reverse statements.
|
|
Semantic Differential Scale
|
7 or 5 * or 3 point rating scale with end points associated with bipolar labels that have semantic meaning
Sears is POWERFUL ............ WEAK |
|
Stapel Scale
|
Unipolar rating scale with ten categories numbered from -5 to +5 without a neutral point. This scale is usually presented vertically.
Kind of confusing |
|
Reliability Measures
|
test-retest
alternative forms internal consistency split half reliability coefficient alpha |
|
Validity Measures
|
Criterion validity
Construct validity Convergent validity Discriminant validity Nomological validity |
|
test retest reliability
|
respondents are administered identical sets of scale items at two different times
degree of similarity btw the two is measured |
|
alternative forms reliability
|
two equivalent forms of the scale are constructed and the same respondents are measured at two different times with a different form being measured each time
|
|
internal consistency reliability
|
determines the extent to which different parts of a summated scale are consistent in what they indicate about the characteristic being measured
|
|
split half reliability
|
the items on the scale are divided into two halves and the resulting half scores are correlated
|
|
coefficient alpha
|
or Cronbachs alpha is the average of all possible split-half coefficients resulting from different ways of splitting the scale items.
|
|
criterion validity
|
reflects whether a scale performs as expected in relation to other variables selected as meaningful criteria
|
|
construct validity
|
addresses the question of what construct or characteristic the scale is in fact measuring
|
|
convergent
|
construct validity
extent to which scale correlates positively with other measures of the same construct |
|
discriminant
|
is the extent to which a measure does not correlate with other constructs from which it is supposed to differ
|
|
nomological validity
|
is the extent to which the scale correlates in theoretically predicted ways with measured but related constructs
|
|
if a measure is perfectly valid, is it perfectly reliable?
|
yes
|
|
if a measure is unreliable, can it be valid?
|
no
@ minimum, random error is present |
|
if a measure is reliable, can it be valid?
|
no
systematic error |