Term
Three ways of representing variablity |
|
Definition
|
|
Term
A correlation is a standardized representation of association between ______ variables. |
|
Definition
|
|
Term
What is a test score based on the sum of two or more variables? |
|
Definition
|
|
Term
Variance of a composite score is a function of the variance associated with the individual items and the ____________. |
|
Definition
Correlations amongst the items |
|
|
Term
An item in which responses range from 0 -1 (correct or incorrect) is? |
|
Definition
|
|
Term
Is the variance of a dichotomously scored item maximised when half of the people score 1 and the other half score 0? |
|
Definition
|
|
Term
The two most common psychological test score interpretations are: |
|
Definition
Relative & Abstract interpretations |
|
|
Term
Relative interpretations make reference to _____ and _____, which requires knowledge of ___ and ___? |
|
Definition
An entire population; where the individual falls; mean; SD |
|
|
Term
What is the most commonly used standardized score? |
|
Definition
|
|
Term
z-scores have a mean of __ and a SD of __. |
|
Definition
|
|
Term
______ can be used to compare scores across tests that are on different sized units |
|
Definition
|
|
Term
T-scores have a mean of ____ and a SD of ___ |
|
Definition
|
|
Term
________ ________ indicate the percentage of scores below a specific test score |
|
Definition
|
|
Term
A _______ sample provides "benchmarks" for evaluations compared to other people |
|
Definition
|
|
Term
The quality of the reference sample depends on how much it represents the ________ of interest. |
|
Definition
|
|
Term
Due to random sampling rarely occurring in practice, many test norms are based on __________ samples |
|
Definition
|
|
Term
In addition to having a normative sample that is "representative', is must also have sufficient ____. |
|
Definition
|
|
Term
What is a question with a fixed set of response alternatives? |
|
Definition
|
|
Term
What question type lets respondents answer in their own words? |
|
Definition
|
|
Term
The commonly used scale in which respondents provide how strongly they feel positively or negatively on an issue is called the |
|
Definition
|
|
Term
True or false: most respondents have experience with likert scales |
|
Definition
|
|
Term
A 6-point likert scale is better than a 5-point one because... |
|
Definition
It forces the respondent to make a decision |
|
|
Term
By including ________ keyed items, you are ensuring that respondents don't get into a response set (e.g., acquiescence) |
|
Definition
|
|
Term
An item with two or more questions in it is known as a _________ item. |
|
Definition
|
|
Term
Ultimately, items should use ______ language and be _______ in length. |
|
Definition
|
|
Term
Reliability is pertinent to the ________ of measurement |
|
Definition
|
|
Term
If nurse Barbara measured a baby at time 1 and a day later measured it at time 2, and found a discrepancy in the length, this must be due to ________ error. |
|
Definition
|
|
Term
Reliability and measurement error are essentially _________ |
|
Definition
|
|
Term
________ ________ ________ is a measurement theory that defines the conceptual basis of reliability |
|
Definition
Classical Test Theory (CTT) |
|
|
Term
A _____ score, is a score devoid from measurement error |
|
Definition
|
|
Term
True scores can be perfect from an _____ standpoint, but absolutely terrible from a valid representation of a _______ standpoint. |
|
Definition
|
|
Term
All other things equal, we want the observed scores to be as ____ to their corresponding true scores as possible |
|
Definition
|
|
Term
Reliability reflects the degree of correspondence between _______ scores and ______ scores |
|
Definition
|
|
Term
State the formula for CTT in words: |
|
Definition
Observed score as a function to true score plus error. |
|
|
Term
True or false: if Timmy wants good reliability, the observed scores and error scores should be uncorrelated. |
|
Definition
|
|
Term
|
Definition
- have a mean of zero - be a random process - be uncorrelated with true scores |
|
|
Term
When you _____ the reliability index, you get a conceptual estimation for reliability |
|
Definition
|
|
Term
Tests which are psychometrically identical but differ in item make-up are called |
|
Definition
|
|
Term
The assumption that true scores associated with each test represent the same construct is called: |
|
Definition
|
|
Term
Without ______ you have no hope for ______ |
|
Definition
|
|
Term
________ is a necessary but not sufficient condition for _______ |
|
Definition
|
|
Term
If Jimbo did test 1 on Monday and then felt like he lost his confidence for test 2 on Tuesday, this would be an example of: |
|
Definition
|
|
Term
The administration of one test over two different occasions is known as: |
|
Definition
|
|
Term
Most test-retest studies use a _ to _ week interval |
|
Definition
|
|
Term
The reliability correlation from test-retest is also known as the |
|
Definition
|
|
Term
What reliability measurement is constructed to treat different items or groups of a test as different forms of the test |
|
Definition
Internal consistence reliability |
|
|
Term
What are the two factors that affect internal consistency reliability? |
|
Definition
1. The degree of consistency between the parts/items of the test 2. The length of the test |
|
|
Term
What reliability estimate represents the reliability in all possible split-halves? |
|
Definition
|
|
Term
Cronbach's Alpha formulae: |
|
Definition
the product of the number of items squared and mean inter-item covariance over the sum of square variance/covariance matrix. |
|
|
Term
Tau-equivalence is one of the assumptions of ________ |
|
Definition
|
|
Term
Name the 4 assumptions of cronbachs alpha: |
|
Definition
1. Tau-equivalence 2. Each items error term is uncorrelated with every other items error term 3. Error scores are uncorrelated with true scores 4. Items used to generate a composite score should measure only one construct or attribute |
|
|
Term
All you have to remember with standardized coefficient alpha is that... |
|
Definition
it is applied to standardized scores |
|
|
Term
What does the essentially tau-equivalent assumption model consist of: |
|
Definition
Equal true score variance, unequal means, unequal error variance |
|
|
Term
What reliability assumption model has equal true score variance, equal means, but unequal error variance? |
|
Definition
|
|
Term
True or false: Technically speaking, Cronbachs alpha only measures on attribute of interest |
|
Definition
|
|
Term
A homogenous sample will yield lower reliability estimates than a ____________ sample |
|
Definition
|
|
Term
A ________ __________ reflects a range of values that is often interpreted as a range in which the true score is likely to fall |
|
Definition
|
|
Term
_________ ________ ________ _________ represents the amount of error around a point-estimate |
|
Definition
standard error of measurement |
|
|
Term
To calculate a confidence interval you add or subtract the _______ ______ _______ ______ from the ______ _______ |
|
Definition
Standard error of the estimate; point estimate |
|
|
Term
To get the smallest confidence interval, one would need to increase _______ and decrease _______ |
|
Definition
|
|
Term
Although high levels of reliability are desired, they are not the only ________ |
|
Definition
|
|
Term
Which correlation uses the data you have and is affected by the degree of measurement error in your data. |
|
Definition
Observed score correlation |
|
|
Term
Explain what a true score correlation is |
|
Definition
A hypothetical correlation you can estimate, if you know the reliabilities associated with the scores. It also not compromised by measurement error |
|
|
Term
|
Definition
The maximum possible correlation between two variables is the square root of the product of their reliabilities. |
|
|
Term
Correction for attenuation formula is the: |
|
Definition
ratio of observed score correlation to the square root of the product reliabilities |
|
|
Term
An observed score correlation should be _______ _______ before being subjected to the correction for attenuation formula |
|
Definition
statistically significant |
|
|
Term
________ is the degree to which a test measures what it is supposed to measure |
|
Definition
|
|
Term
People (including researchers) no not tend to refer to a test as valid because: |
|
Definition
They don't know any better They get lazy |
|
|
Term
True or false: Validity is not a matter of degree |
|
Definition
|
|
Term
Name the two types of validity relevant to test content: |
|
Definition
1. content validity 2. face validity |
|
|
Term
|
Definition
When the items cover the entire breadth of the construct |
|
|
Term
Constructs like personality make content validity assessment very ____. |
|
Definition
|
|
Term
Face validity appearance is in the judgement of _________. |
|
Definition
|
|
Term
Name the 5 NEO-PI R dimensions |
|
Definition
1. Neuroticism 2. Openness 3. Extraversion 4. Agreeableness 5. Consciousness |
|
|
Term
What do researchers use to evaluate factorial validity? |
|
Definition
|
|
Term
When the way in which individuals respond to the way they are meant to respond is known as: |
|
Definition
|
|
Term
The relation between test scores and tests of related constructs is known as: |
|
Definition
|
|
Term
The use of seeing whether test scores are uncorrelated with tests of unrelated constructs is known as: |
|
Definition
|
|
Term
Constructs should not correlate with everything under the sun, and if they do, it means their boundaries are overly ________. |
|
Definition
|
|
Term
When scores from one measure correlate in a theoretical meaningful way with the scores of another measure which is considered the "gold standard' we call this: |
|
Definition
Concurrent Validity Evidence |
|
|
Term
In the cases of concurrent validity evidence, there can be no _______ _______ measure to refer to |
|
Definition
|
|
Term
When we compare the test scores to the relevant variables in a future point we call this: |
|
Definition
Predictive validity evidence |
|
|
Term
When the test possesses items that could have social/personal consequences we call this: |
|
Definition
|
|
Term
Reliability is a property of test scores, while validity is a property of test score ________ |
|
Definition
|
|
Term
The definition of dimensions are defined by which items ____ onto which dimension |
|
Definition
|
|
Term
Three types of dimensional tests: |
|
Definition
1. Unidimensional 2. Multidimensional (uncorrelated) 3. Multidimensional (correlated) |
|
|
Term
Multidimensional correlated tests produce a variety of scores: |
|
Definition
Subtest scores Area scores Total scores |
|
|
Term
Most ability tests have correlated dimensions, however personality tests usually have __________ dimensions |
|
Definition
|
|
Term
When inter-item correlations cluster together we can form a hypothetical basis on what ________ they are loading on |
|
Definition
|
|
Term
what are the threshold values for communalities in reference to items and sub-scales |
|
Definition
items: more than .04 sub-scales: more than .09 |
|
|
Term
Minimum values for component loadings for sub-scales and items? |
|
Definition
Items: 0.2 Sub-scales: 0.3 |
|
|
Term
To help achieve simple structure we: |
|
Definition
|
|
Term
If you are only extracting one component there is no need to |
|
Definition
|
|
Term
Before conducting convergent or discriminant validity you should: |
|
Definition
Make sure we have evaluated internal consistency and factorial validity issues |
|
|
Term
The interconnections between one construct and other related constructs is known as the: |
|
Definition
|
|
Term
A measure of predictive validity is also known as the: |
|
Definition
|
|
Term
What are validity generalizations |
|
Definition
Evaluating tests validity coefficient over a large set of studies |
|
|
Term
Subjective judgement of a nomological network and its patterns can help us merit ______ |
|
Definition
|
|
Term
The MTMM overcomes the problem of correlations between two scores may conflate two sources of variance: |
|
Definition
Trait Variance Method Variance |
|
|
Term
In the MTMM we want _____________ correlations to be meaningfully larger than the _____________ correlations |
|
Definition
monotrait-heteromethod; heterotrait-monomethod |
|
|
Term
What predicts the magnitude of a correlation between the measure of interest and its selected criteria? |
|
Definition
quantifying construct validity |
|
|
Term
Validity coefficients are typically: |
|
Definition
|
|
Term
There are two realistic cases where the amount of variability is lower than it should or could be: |
|
Definition
The measure is not sensitive enough to distinguish people The Sample is more homogenous than the populations of interest |
|
|
Term
Personality tests can be used for: |
|
Definition
- Research - Clinical and Counseling - Personnel management |
|
|
Term
A test measuring an individuals personality using ambiguous stimuli is known as: |
|
Definition
|
|
Term
Which reliability measures have high outcomes in the Rorschach test? |
|
Definition
|
|
Term
What is a hopeful measure of validity in the Rorschach test? |
|
Definition
|
|
Term
True or false: The Rorchach test has high reliability for many scores, and high factorial and predictive validity |
|
Definition
|
|
Term
Oi bro, name me the two personality theories |
|
Definition
|
|
Term
Trait theory measures are very typically __________ in nature |
|
Definition
|
|
Term
Self-report questionnaires are also referred to as |
|
Definition
"objective personality tests" |
|
|
Term
Name the three main personality trait theory tests: |
|
Definition
Five-factor model (NEO PI-R) HEXACO THE BIG FIVE (HEHEHEHE) |
|
|
Term
We measure the validity of task-based personality tests through: |
|
Definition
correlating the task-based scores with self-report scores |
|
|
Term
a bias that obscure or cause differences among groups of respondent test scores unjustifiably is known as: |
|
Definition
|
|
Term
|
Definition
Construct Bias Predictive Bias |
|
|
Term
What occurs when a tests use has different implications for two (or more) groups: |
|
Definition
|
|
Term
The two methods for identifying the two types of test score biases: |
|
Definition
Internal methods = construct bias External methods = predictive bias |
|
|
Term
In reference to internal methods of identifying construct bias we can see if it is bias if: |
|
Definition
1. People belonging to different groups responded in different ways to an item 2. it can be shown that these differing responses were not related to group difference associated with the psychological attribute |
|
|
Term
A test item is considered bias if you take two people (i.e. Tony Abbott & Kevin Rudd) who have the same level of an attribute (being a terrible PM) but tend to respond _________ to that particular item |
|
Definition
|
|
Term
The item discrimination index is a method which is |
|
Definition
more of historical importance |
|
|
Term
The correlation between factor loadings is known as the: |
|
Definition
factor congruence coefficient |
|
|
Term
What analysis measures construct validity through using the test data by determining whether the trait levels and item responses match up in the same way for both groups |
|
Definition
Differential Item Functioning (DIF) analysis |
|
|
Term
Rank-order consistency consists of: |
|
Definition
calculating means for each item separately for each group and then calculate a spearman correlation between them |
|
|
Term
The two steps towards analysing predictive bias: |
|
Definition
1. determine whether test scores predict the dependent variable to start with 2. determine whether these scores predict well across groups |
|
|
Term
What do you need to conduct to perform an analysis for predictive validity: |
|
Definition
|
|
Term
Describe the intercept and the slop of a regression analysis |
|
Definition
Intercept (B0) - Expected value of Y when X is 0, point where it crosses the y-axis Slope (B1) - Increase of decrease in dependent variable, Y as a function of X |
|
|
Term
|
Definition
|
|
Term
If the common regression equation and the group-level regression do not match we can conclude by saying there is |
|
Definition
|
|
Term
In the context of predictive bias, if the intercepts of two groups do not match up we call this: |
|
Definition
|
|
Term
As well as having predictive bias in a regression analysis, you can also get _______ bias |
|
Definition
|
|
Term
There are occasions where one group will have less reliable scores than the other groups, this can cause difference in the slopes and intercepts. The differences in this reliability are a form of _______ bias which can an effect on ________ bias. |
|
Definition
|
|
Term
In the terms of test bias we also need to keep in mind that the lack of difference between two means might be caused by _______ bias |
|
Definition
|
|
Term
Modern test theory is also known as |
|
Definition
Item Response Theory (IRT) |
|
|
Term
The IRT operates under the pretence that any item response if influenced by two factors: |
|
Definition
1. Qualities of the individual 2. Qualities of the item |
|
|
Term
Trait level and item difficulty are intrinsically connected concepts in the _____. |
|
Definition
|
|
Term
Trait levels and item difficulties are usually have a M=___ and SD=___ |
|
Definition
|
|
Term
If an item has a difficulty level of -1.5, then a person with a trait level of 1.0 would have a |
|
Definition
much greater than 50% chance of answer the question correctly |
|
|
Term
In the context of IRT the degree to which an item indicates the relevance of the trait being measured by the test is known as |
|
Definition
|
|
Term
The main difference between the one-parameter model and the two-parameter model is: |
|
Definition
the addition of the description of an item (parameter 2) |
|
|
Term
What is the third parameter in the three-parameter logistic model |
|
Definition
3. the probability with which the question can be answered by guessing |
|
|
Term
the graph which is made to evaluate the quality of an item is known as the: |
|
Definition
Item Characteristic Curve (ICC) |
|
|
Term
|
Definition
Test development and improvement Differential item functioning Person fit Computer-Adaptive testing |
|
|
Term
The test that increases item difficulty as the respondent answers correctly is known as: |
|
Definition
Computer adaptive testing (CAT) |
|
|
Term
Across time the CAT will _______ a persons latent trait variable |
|
Definition
|
|
Term
The CAT will stop once the |
|
Definition
Standard error of estimate confidence interval has narrowed sufficiently |
|
|
Term
Describe 2 + and 2 - of CAT: |
|
Definition
+ = 50% less time to test respondents are tested more in their area of difficulty
- = more time/money to develop participants don't trust it |
|
|
Term
a bias that obscure or cause differences among groups of respondent test scores unjustifiably is known as: |
|
Definition
|
|
Term
|
Definition
Construct Bias Predictive Bias |
|
|
Term
What occurs when a tests use has different implications for two (or more) groups: |
|
Definition
|
|
Term
The two methods for identifying the two types of test score biases: |
|
Definition
Internal methods = construct bias External methods = predictive bias |
|
|
Term
In reference to internal methods of identifying construct bias we can see if it is bias if: |
|
Definition
1. People belonging to different groups responded in different ways to an item 2. it can be shown that these differing responses were not related to group difference associated with the psychological attribute |
|
|
Term
A test item is considered bias if you take two people (i.e. Tony Abbott & Kevin Rudd) who have the same level of an attribute (being a terrible PM) but tend to respond _________ to that particular item |
|
Definition
|
|
Term
The item discrimination index is a method which is |
|
Definition
more of historical importance |
|
|
Term
The correlation between factor loadings is known as the: |
|
Definition
factor congruence coefficient |
|
|
Term
What analysis measures construct validity through using the test data by determining whether the trait levels and item responses match up in the same way for both groups |
|
Definition
Differential Item Functioning (DIF) analysis |
|
|
Term
Rank-order consistency consists of: |
|
Definition
calculating means for each item separately for each group and then calculate a spearman correlation between them |
|
|
Term
The two steps towards analysing predictive bias: |
|
Definition
1. determine whether test scores predict the dependent variable to start with 2. determine whether these scores predict well across groups |
|
|
Term
What do you need to conduct to perform an analysis for predictive validity: |
|
Definition
|
|
Term
Describe the intercept and the slop of a regression analysis |
|
Definition
Intercept (B0) - Expected value of Y when X is 0, point where it crosses the y-axis Slope (B1) - Increase of decrease in dependent variable, Y as a function of X |
|
|
Term
|
Definition
|
|
Term
If the common regression equation and the group-level regression do not match we can conclude by saying there is |
|
Definition
|
|
Term
In the context of predictive bias, if the intercepts of two groups do not match up we call this: |
|
Definition
|
|
Term
As well as having predictive bias in a regression analysis, you can also get _______ bias |
|
Definition
|
|
Term
There are occasions where one group will have less reliable scores than the other groups, this can cause difference in the slopes and intercepts. The differences in this reliability are a form of _______ bias which can an effect on ________ bias. |
|
Definition
|
|
Term
In the terms of test bias we also need to keep in mind that the lack of difference between two means might be caused by _______ bias |
|
Definition
|
|
Term
Modern test theory is also known as |
|
Definition
Item Response Theory (IRT) |
|
|
Term
The IRT operates under the pretence that any item response if influenced by two factors: |
|
Definition
1. Qualities of the individual 2. Qualities of the item |
|
|
Term
Trait level and item difficulty are intrinsically connected concepts in the _____. |
|
Definition
|
|
Term
Trait levels and item difficulties are usually have a M=___ and SD=___ |
|
Definition
|
|
Term
If an item has a difficulty level of -1.5, then a person with a trait level of 1.0 would have a |
|
Definition
much greater than 50% chance of answer the question correctly |
|
|
Term
In the context of IRT the degree to which an item indicates the relevance of the trait being measured by the test is known as |
|
Definition
|
|
Term
The main difference between the one-parameter model and the two-parameter model is: |
|
Definition
the addition of the description of an item (parameter 2) |
|
|
Term
What is the third parameter in the three-parameter logistic model |
|
Definition
3. the probability with which the question can be answered by guessing |
|
|
Term
the graph which is made to evaluate the quality of an item is known as the: |
|
Definition
Item Characteristic Curve (ICC) |
|
|
Term
|
Definition
Test development and improvement Differential item functioning Person fit Computer-Adaptive testing |
|
|
Term
The test that increases item difficulty as the respondent answers correctly is known as: |
|
Definition
Computer adaptive testing (CAT) |
|
|
Term
Across time the CAT will _______ a persons latent trait variable |
|
Definition
|
|
Term
The CAT will stop once the |
|
Definition
Standard error of estimate confidence interval has narrowed sufficiently |
|
|
Term
Describe 2 + and 2 - of CAT: |
|
Definition
+ = 50% less time to test respondents are tested more in their area of difficulty
- = more time/money to develop participants don't trust it |
|
|
Term
Response biases are affected by: |
|
Definition
1. Test content 2. Test context 3. Test format |
|
|
Term
The type of respond bias where an individual agrees with statements without actually regarding their meaning is: |
|
Definition
|
|
Term
In practice it is impossible to know how much of the correlation is due simple to acquiescence rather than truly shared construct variance. This type of correlation is know as a |
|
Definition
|
|
Term
"Nay-sayers" are individuals who constantly respond to _______ items |
|
Definition
|
|
Term
Factors that increase acquiescence: |
|
Definition
1. Ambiguity of the question 2. Length of the question 3. Large number of items |
|
|
Term
Which is one method of measuring acquiescence bias? |
|
Definition
|
|
Term
Explain extreme and moderate responding: |
|
Definition
Extreme: Difference in the tendency to use or avoid extreme response options Moderate: Some people respond more in the middle to avoid making strong claims |
|
|
Term
True or false: there is a way to measure extreme responding |
|
Definition
|
|
Term
The response bias in which individuals respond in a way that seems socially appealing to them is known as: |
|
Definition
|
|
Term
Social desirability affects: |
|
Definition
|
|
Term
A person with high autonomy would be less likely to respond in a _________ ________ way |
|
Definition
|
|
Term
The two processes of measuring social desirability responding is: |
|
Definition
impression management & self-deceptive enhancement |
|
|
Term
A lot of research has ______ to find support for socially desirability responding |
|
Definition
|
|
Term
Tharen and Henry are on the hunt for some dexies. They decide they will pretend to act as if they have ADHD. As they take the test, they purposely perform "poorly" to gain use of these plumcious beauties. This type of response bias is known as: |
|
Definition
|
|
Term
Ture or false: Malingering occurs in a lot of psychological and forensic evaluations |
|
Definition
|
|
Term
Damo, the lazy bloke responds to all the questions the same way without even reading them. This response bias is known as: |
|
Definition
Careless or random responding |
|
|
Term
Tharen was a naughty boy and didn't study for his statistic multiple choice exam. He went into the exam and simply took a guess on each question, and in turn got a HD. This type of response bias is known as: |
|
Definition
|
|
Term
3 methods of managing with response biases: |
|
Definition
1. Manage test context 2. Manage test content 3. Use specially designed bias tests |
|
|
Term
Some examples of managing text context to cope with response biases: |
|
Definition
- Make it anonymous - Create a test situation that minimizes respondent fatigue, stress, distraction and frustration (i.e. a test for less than an hour) - Bogus pipeline technique (telling the respondents that faking or lies can be detected, respondents believe this) |
|
|
Term
One of the major downfalls of force-choice formats in the context of coping with response biases is that: |
|
Definition
It is very hard to calculate internal consistency realiablity |
|
|
Term
Ultimately, in reality it is very difficult to _______ the existence of responses bias. |
|
Definition
|
|
Term
Instead of trying to eliminate response bias, we try to ______ it. |
|
Definition
|
|
Term
One way to manage guessing is to: |
|
Definition
Inform the person that they will be penalized if they guess |
|
|
Term
Such inventories like the MMPI incorporate ______ _______ to measure the degree of response bias |
|
Definition
|
|
Term
What are the three scales in a validity scale? |
|
Definition
|
|
Term
Two most popular tests that measure SDR: |
|
Definition
Marlowe-Crowne Social Desirability Scale Balanced Inventory for Desirable Responding |
|
|
Term
What specialized test is used to measure malingering? |
|
Definition
|
|
Term
Acquiescence Dedicated tests have thus far: |
|
Definition
|
|
Term
|
Definition
what a person does when they don't know what to do |
|
|
Term
digit span _______ is a better indicator of intellectual functioning than digit span ______ |
|
Definition
|
|
Term
True or false: working memory is a fundamental basis of intelligence |
|
Definition
|
|
Term
Raven's is ____ a pure measure of general intelligence |
|
Definition
|
|
Term
Processing speed can be broken into: |
|
Definition
Reaction time Inspection time |
|
|
Term
The measure of processing speed in which participants must choose between two alternatives on a screen as fast as they can is known as: |
|
Definition
|
|
Term
Movement time is mostly a _______ process while reaction time is mostly a _______ process |
|
Definition
|
|
Term
Clinicians don't use reaction time and inspection time as a measure of processing speed, instead they use ______ or ______ _ and _ |
|
Definition
|
|
Term
What is positive manifold? |
|
Definition
The positive correlations between cognitive abilities |
|
|
Term
One of the first researched to observe the positive manifold was |
|
Definition
|
|
Term
Fluid intelligence peaks around __ years, while crystallised around __ years old |
|
Definition
|
|
Term
Gignac & Vernon found a correlation of ____ between self-report IQ and self-report questionnaire |
|
Definition
|
|
Term
True or false: personality and intelligence research use mostly self-reports |
|
Definition
|
|
Term
Two overall dimensions to blooms taxonomy: |
|
Definition
Knowledge dimensions The cognitive processing dimension |
|
|
Term
With blooms new taxonomy he added "______" at the top of the model |
|
Definition
|
|
Term
|
Definition
|
|
Term
Mathematics reports tend to be associated with much _______ marking score reliability than English type essays |
|
Definition
|
|
Term
Simple strategies to improve reliability of essay marks: |
|
Definition
- Have all candidates write on the same topic - Remove names from the essay - Have a detailed marking key - Train markers on the marking key - Mark essays by at least two different raters |
|
|
Term
Two attributes of psychological tests: |
|
Definition
|
|
Term
2 purposes of a psychological test: |
|
Definition
Measure between people - inter-individual differences Measure |
|
|
Term
What are the 5 principles of a test: |
|
Definition
1. content 2. administration 3. intended purpose 4. type of responses 5. time constraints |
|
|
Term
What is a criterion test? |
|
Definition
A test where a cut off point is made |
|
|
Term
what is a norm-based test? |
|
Definition
Comparing individual to the average of the population |
|
|
Term
In the context of scaling, what the 3 properties? |
|
Definition
1. properties of identity 2. properties of order 3. properties of quanitity |
|
|
Term
________ implies unit size of measurement doesn't change as units increase |
|
Definition
|
|