14
MMK (Fach) / Übung Fakten (Lektion)
Anzeige
- Measurement techniques in psychological assessment2 Psychological tests1• Personality questionnaires• Projective techniques• Systematical behavior observation
- Quality criteria in psychometrics objectivity (independence from psychologist)• reliability (degree of formal accuracy)• validity (refers to the correctness of the measurement withregards to the content)• standardization (permits the placement of the individualmeasurement result of a person within the distribution ofall results of a population)• unfakeability (measurement instrument doesn’t allowindividual control of type and content of the desired information)
- Additional psychological measurement techniques - Sociogram (relations between persons in a small group)• Survey questionnaires (observation of opinions andattitudes)• Ratings• Q-sort (persons, activities, situations)• Semantic differential (seven-level scale ratings)• Method of pair-wise comparison.• Content analysis
- Steps of empirical research 1.Exact formulation (specification) of the scientific question.2.Definition of certain precision requirements for the final conclusions,required for answering the scientific question.3.Selection of the statistical model for the planning and analysis of thestudy.4.(Optimal) planning of the study.5.Realisation of the study.6.Statistical analysis of the collected data.7.Interpretation of the results and conclusions.
- Factor - character, designated to several treatment conditions discrete and continuous characterscharacter generally postulated as being determined bychance/ factor cat be modelled as being not randomA factor is used for storing categorical data. Supposeyou have data on some people and you want to storetheir sex. You could use a numeric code - 0 for male, 1for female, or you could use a character code - `M' formale and `F' for female. But you should use a factor.
- Median number separating the higher half of a data from the lower half.• based on outcomes being ranked• works even for ordinal-scaled characters• works perfect against outliers
- Charts visual expression of information from extensive data setsCharts must be• designed simple• immediately comprehensible• must not detract or hide the essential information
- Mode - Modus - a value whose observed frequency is greater then those ofthe two neighboring values• => Distributions may have several modes (multimodaldistributions vs. unimodal distributions)
- Range difference between the largest and the smallestmeasurement value• => Describes the maximum difference that is shown by alloutcomes)• extremely dependent on outliers• unlike the standard deviation and the interquartile range, itcannot become any smaller by adding other research units• does not make any sense in the case ordinal-/nominalscaledcharacters
- Skeweness γ1 g2 • quantifies the asymmetry of a distribution with respect tothe mean• γ1 = 0 for normal distribution• γ1 > 0 and g1 > 0 - positive skewness, right-skeweddistribution or left-steep distribution• γ1 < 0 and g1 < 0 - negative skewness, left-skewed orright-steep distribution
- Anzeige
- Probablity P(E) for any event E a real number between 0 and 1 with certain mathematicalproperties• f(E) - relative frequency of the event E• E - in the case if the event E does not occur (events E andE are complementary)• f(E) = 1 − f(E)
- Probablity P(E) for any event E a real number between 0 and 1 with certain mathematicalproperties• f(E) - relative frequency of the event E• E - in the case if the event E does not occur (events E andE are complementary)• f(E) = 1 − f(E)
- Addition and Multiplication theorems P(A ∪ B) = P(A) + P(B) − P(A ∩ B) • P(A ∩ B) = P(A) · P(B|A) = P(B) · P(A|B) • P(A ∪ B ∪ C) = P(A) + P(B) + P(C) + P(A ∩ B) − P(A ∩ C) − P(B ∩ C) + P(A ∩ B ∩ C)
- Binomial distribution Consider n identical independent runs of an experiment (nindependent research units);let P(E) = p - probability of the occurrence of eventE–’success’. The number of successes is then a random variabley with possible values k = 0, 1, 2, . . . , n