Research methods in psychology by B. Morling (third edition) – Chapter 5 summary

Construct validity refers to how well a study’s variables are measured or manipulated. There are three common types of measurement: self-report, observational and physiological. The conceptual definition, or construct, is the researcher’s definition of the variable in question on a theoretical level. The operational definition represents a researcher’s specific decision about how to measure of manipulate the conceptual variable.

SELF-REPORT
A self-report measure operationalizes a variable by reporting people’s answers to questions about themselves in a questionnaire or an interview. In research on children, self-reports may be replaced with parent reports or teacher reports.     

The problems with self-reports are the demand characteristics: a participant wants to be  a ‘good’ participant. People their self-perception is not always correct and the social desirability: people want to give a good impression about themselves.

OBSERVATIONAL MEASURES
An observational measure is sometimes also called a behavioural measure and operationalizes a variable by recording observable behaviour or physical traces of behaviour.

The problems with observational measures are:

1. Primacy effect
   The first observation sets the tone for the rest of the observations. (e.g: the first rated essay is very good, so the others that are not that good are automatically rated worse than they otherwise would have been rated)
2. Recency effect
   The last observation will be remembered best. (e.g: the last person at a job interview will be remembered the best, because that person was the last)
3. Halo effect
   A good rating on one dimension will influence the ratings on other dimensions. (e.g: if a person is friendly and that is rated first, then he will be more likely to receive higher ratings on other dimensions as well)

PHYSIOLOGICAL MEASURES
A physiological measure operationalizes a variable by recording biological data. The problem with physiological measurement is that not everything can be measured with biological data (at least not yet).

SCALES OF MEASUREMENT
All variables must have at least two levels. The levels of operational variables can be coded using different scales of measurement. 

1. Categorical variables (nominal variables).
   This are categories in which the variable fit. (e.g: sex, species)
2. Quantitative variables
   These variables are coded with meaningful numbers. (e.g: height, weight)

There are three kinds of quantitative variables.

1. Ordinal scale
   A ranking. (e.g: top 10 best-selling books) The distance between the subsequent numerals might not be equal.
2. Interval scale
   The interval between two ranked numbers means the exact same thing. The number ‘0’ doesn’t mean none. (e.g: the difference between IQ 105 and 110 is 5, so is the difference between IQ 110 and 115. The interval is the same)
3. Ratio scale
   There are equal intervals and ‘0’ truly means none. (e.g: a knowledge test with amount of questions correct)

RELIABILITY
Reliability refers to how consistent the results of a measure are. Validity refers to whether the operationalization measures what it’s supposed to measure. There are several types of reliability:

1. Test-retest reliability
   The researcher gets consistent scores every time the researcher uses the measure.
2. Interrater reliability
   Two or more independent researchers will come up with consistent (or very similar) findings.
3. Internal reliability
   There should be a consistency within a measure. (e.g: on a questionnaire question 1 measures the same thing as question 2, so people who agree with question one should also agree with question 2.)

The reliability is also measured in the statistics and is known as ‘p’. The closer Cronbach’s Alpha or coefficient alpha is to 1,0, the more reliable the measure is. To make sure that something is reliable researchers look for a Cronbach’s Alpha of at least 0.70 in self-reports.

VALIDITY
A measure is valid if it measures what it’s supposed to measure. There are multiple ways to check if a measurement is valid:

1. Face validity
   A measurement should subjectively be considered a good measure. (it should be a reasonable way to measure what you want to measure)
2. Content validity
   A measure must capture all parts of a defined construct. The measurement should contain all parts of the conceptual definition. This is also subjective.
3. Criterion validity
   A measure should correlate with key behaviours from the conceptual definition. (e.g: person that is very happy according to a measurement shouldn’t cry a lot) Criterion validity is especially important for self-report measures because the correlation can indicate how well people’s self-reports predict their actual behaviour. Another way to gather evidence for the criterion validity is to use a known-group paradigm. In this case you check if the measure can discriminate among two groups whose behaviour’s already been confirmed.
4. Convergent validity
   The measurement should be correlated (and thus associated) with other measurements that measure the same. (e.g: the results of a new IQ-test should be related to an already existing one)
5. Discriminant validity
   The association and correlation of the measurement cannot be stronger correlated with a unrelated variable. (e.g: a new measure to test for depression cannot be correlated higher with motivation than with similar depression measurement methods)

Reliability is necessary, but not sufficient for validity.