This is a visual English summary of the Measuring & Diagnosing 1 psychology course at the VU Amsterdam (first years). There is also a bundle available where this summary is combined with the Social Psychology course, you can find that bundle on this page as well. Good luck!
Diagnosing =
getting to know a situation through and through in order to be able to make decision
Psychodiagnostics =
getting to know an individual psychosocial functioning
↳ find for
goals : •
possible explanations problems
•
To test these explanations
find reliable & valid description of
•
a
psychosocial reality
↳ Concerns 2 factors : 1) Diagnostic assessment is ideally repeatable ( only influenced by the individual being tested )
2) Diagnostic assessment ideally approaches reality ( as close to someone's true behaviour as possible )
Psychodiagnosticshasseimitatiostodeawitho.TO
The constructs it deals with are difficult ,
complex & not
easily defined leg .
IQ )
⑦ There's only a Limited amount of time during which the diagnoses must be made
③ Examiners may
be vulnerable to confirmation bias
⑨ Examiners may be Vulnerable to availability heuristics
→ For diagnosing we use tests =
gather scientifically sound ,
reliable & objective information for decision
making
Testudo :
⑦ Problem analysis
② Classification & diagnosis
③ Treatment planning
④ Program 1 treatment evaluation
⑤ Self knowledge
-
⑥ Scientific research
A good test •
Permits the examiner to predict behaviors (doesn't need to mirror the to be -
predicted behaviors )
• Is standardized & has an instruction manual
•
Permits the deriv i cation of scores lnumbers and categories (makes it quantifiable )
2
types of test ⑦ Norm - referenced test = The performance of each examinee is interpreted in reference to a
-
relevant standardization sample ( the norm ) ←
most common in psych tests
.
② Criterion -
referenced test =
The performance of each examinee is interpreted in reference to
meeting or not -
meeting an
appropriate ,
specified criterion
Norm > criterion bc it takes prevalence of the disorder into account
,
criterion can over
diagnose
,Every test score contains measurement errors → leads to the formula of classical test
theory
Observed score = true score terror component to X -
-
Tt e
Measurement influence can be because of 1) Individual factors P
e.g .
Sleep deprivation .
test anxiety ,
mood
21 Situational factors → e.
g .
environment sounds ,
weather
,
cultural differences
3) Teserror5 P e.g . imperfectly defined constructs ,
bad question
I neglect use of a manual
easier to avoid with standardized tests = a test for which the procedures for administering it are uniform from
one examiner and setting to another
standardized :
⑦ Is repeatable as You should always get the same score ( if reliability I validity are present )
② Has integrality is You measure one
sample of behavior through a limited number of items
③ Will result in scores to
expressing the construct in numbers ↳ can have drawbacks :
① These scores can be interpreted → either norm or criterion Kat off - value •
Q 's can become overly specific
⑤ The test predicts specific behavior Q 's become
overgeneralizing
•
-
score non - test can
AssessmentsltestusageintheNetherlarfc.NL
P = Dutch association OC psychologists
↳ provide guidelines of professional ethics
↳ give
quality assurance through registration of educated psychologists & courses
•
COTA N = Dutch institute that assesses test quality
↳ Inform users about the quality of instruments
↳ Provide feedback to instrument developers
for each test 1 instrument there are psychometric criteria ( by COTA N ) & ethical use guidelines ( by hip )
COTANcriter
① Clear principles of test construction ( what's the goal focus group function etc . )
, ,
② Good standardization ( quality of test materials & manual )
③ Appropriately defined norms ( representative't y -
or the reference group to focus group )
④ Good reliability ( consistency / repeatability of scores )
⑤ Good validity ( the test should assess what it aims to assess )
NIP code of ethics Ethics for test developers
⑦ Only assess what is relevant
⑦ Psychometric characteristics must be up to date
⑦ Assessment must only be done by qualified individuals ③ Only qualified people are allowed to buy d use tests
③ Role integrity of the professional in question
③ Digital test use is not allowed
⑦ Confidentiality
⑤ Informed by
consent must
given by an informed client
⑥ Professional must take an independent & objective position
⑦ The professional must report without jargon
, Week 2 :
Classicaltesttheoryemeasurementerrorsclassical
test
theory = the theory of true & error scores
↳ It is based on the idea that observed test scores result from the true score t a measurement error
-
f ↳ Note that this can be :
Observed score = true score t measurement error - o X = Tt e ↳ Positive X >T =
positive e
l l
r t ↳
Negative x ' negative
-
-
tw÷i÷s÷÷÷%%i;y÷@
to measure ( e.g .
depression )
Sourcesofmeasurementerro
⑦ There is an actual difference I inconsistency in the construct we're
trying to assess
e.g .
a child is hyperactive at school ,
but not at home
③ Something caused there to be a measurement error
⑦ Item selection Since construct and thus take
to we cannot assess
every aspect of a we
only a
just the fact that you
'
the
'
sample of behavior items you choose or now
,
have less items can affect the e
② Test The the
administration To examinee ,
examiner and environment can also cause
inconsistency
in test results (e) .
E.g .
A
noisy room has a
negative effect f- e ) on T
③ Type of test scoring E Multiple choice questions are clear cut
,
however when
working with open
there subjectivity into
essay questions always play
comes = e
,
⑨ Systematic errors To This type of error is not random I thus does not fluctuate .
Mainly caused by
of measurement
test
↳
in asses ed construct
= "
construction or manual errors or
inconsistency
:÷÷÷÷:::::
Characteristics of systematic errors ( within population)
i÷÷÷÷÷÷÷i÷÷÷÷÷i÷÷:÷:i÷ be the individual be
→ e 's will either positive one negative thus average too
Systematic
•
errors are also referred to as a measure of
validity
→ bc these errors affect whether you are measuring the intended construct or not
Bo All other influences on e are
unsystematic (random) errors = Eu
÷÷:÷i÷÷÷÷÷÷÷÷ ::÷÷÷÷i÷÷÷i÷÷÷i÷i
characteristicsofunsystematicerrors-lwit.tnin population)
Classical test theory focusses This measurement
•
error ku ) is random and can thus be positive for one leg .
nice examiner)
fore seen as non existent
.
:÷÷÷÷:÷÷÷÷÷÷÷÷÷÷÷÷÷÷
Unsystematic referred to the
-
. •
errors are also as a measure of reliability as Eu 's affect
consistency of the scores
The do calculations
normally distributed
•
measurement errors are →
why we can
, We use CTT to determine confidence intervals around the scores since that C I .
.
will be more representative
of the true score
for this (unsystematic, to be
normally distributed
.
→ we assume measurement errors
↳ we use a normal distribution to figure out how
(ab ) normal a
giver average obtained score is
population variance = 02
population =
'
sample Variance = SD
Sample =
-
3 SD -
2 SD * ISD M t y SD +2 SD t 3 SD
→
We also know that in
large enough sample that the measurement will equal to 0 (everything cancels
a
average error
eachother out )
↳ so X = Tt e -
D µ× =
Htt t O -
D
Hx a flt → so
average test score =
average true score
↳ But in reality this is not possible ( can't assess
everyone) so we take a sample
↳ To calculate for a sample we use the variability of the test score
↳ so X -
Tt e b of, = of to :-D So variance or the test
-1
-
-
Variance of the true score t variance of m errors
.
.
O
population term
'
note .
O is still a
Example
Q : What is the measurement error of the scale ?
→ Stand on the scale 1000 X
Result : weight varies from 57.8 to 62.5 but has a mean of
60kg (M -
-
Go ) & SD -
-
I -0 So T -
-
60kg
+ The average measurement error = o ( large enough sample)
↳ The
'
variance of e is SD so 12 = 1
Reliability
of
measure
consistency
= a in measurement over several assessments
Reliability = r and it shows the ratio of true scores to observed scores
↳ so r =
Ix →
reliability =
-
true
Observed scores
scores
→ thus the closer TIX are ,
the higher r will be ( bc I -
-
t -
-
perfect r )
( in terms
of test scores
LD r will always be between o d l
)
Example
In a depression questionnaire : true score = 15 I observed score -
-
16
↳ 15/16 =
0.93 D
highly reliable
-
But it could 've also been : true score = 15 I observed score = 21
LD 15/21 = 0.71 → less reliable
Reliabilitycoefficient
However ,
in general you do not knew people's true scores
, you get only the observed scores
Thats with the coefficient terms the
→
why reliability ,
we calculate reliability in of variance of obtained scores
' '
Variance population = o Variance in a sample = SD
Voordelen van het kopen van samenvattingen bij Stuvia op een rij:
Verzekerd van kwaliteit door reviews
Stuvia-klanten hebben meer dan 700.000 samenvattingen beoordeeld. Zo weet je zeker dat je de beste documenten koopt!
Snel en makkelijk kopen
Je betaalt supersnel en eenmalig met iDeal, creditcard of Stuvia-tegoed voor de samenvatting. Zonder lidmaatschap.
Focus op de essentie
Samenvattingen worden geschreven voor en door anderen. Daarom zijn de samenvattingen altijd betrouwbaar en actueel. Zo kom je snel tot de kern!
Veelgestelde vragen
Wat krijg ik als ik dit document koop?
Je krijgt een PDF, die direct beschikbaar is na je aankoop. Het gekochte document is altijd, overal en oneindig toegankelijk via je profiel.
Tevredenheidsgarantie: hoe werkt dat?
Onze tevredenheidsgarantie zorgt ervoor dat je altijd een studiedocument vindt dat goed bij je past. Je vult een formulier in en onze klantenservice regelt de rest.
Van wie koop ik deze samenvatting?
Stuvia is een marktplaats, je koop dit document dus niet van ons, maar van verkoper FabienneDenberg. Stuvia faciliteert de betaling aan de verkoper.
Zit ik meteen vast aan een abonnement?
Nee, je koopt alleen deze samenvatting voor €8,99. Je zit daarna nergens aan vast.
