DATA COLLECTION METHODS The Scientific Method Four main

DATA COLLECTION METHODS

The Scientific Method • Four main steps of scientific investigation: 1. Observe 2. Detect Regularities 3. Generate Hypothesis (concept, theory) 4. Observe In principle, this cycle never ends. It continues to be updated with new information 2

Operationalizing a concept • • • To study a concept scientifically, we need to convert it into a variable That is, a score or a category we need an operational definition to make a concept into a variable 3

Examples • e. g. operationalize ‘intelligence’ by assigning numbers: – – – • A. an IQ test B. talking speed C. score on general knowledge test e. g. operationalize shyness with a rating scale: I am shy person • 1 (never) 2 (sometimes) 3(usually) 4(always) 4

Techniques 1. Naturalistic Observation 2. Case Studies 3. Surveys 4. Psychological tests 5

1. Naturalistic Observation • recording behavior as it occurs naturally – Example: observe children playing at a daycare centre • Limitation • reactivity • Reduce it by: – Participant observation: blending into the group – Unobtrusive recording 6

Two examples 7

2. Case Studies • details about a single case • the source of (many of) Freud’s ideas • Limitation: – representativeness: can we generalize from this one individual to human beings ? 8

3. Surveys • e. g. , marketing research or political polls • small amount of information from many people – By telephone, interview, – on-line • Limitation: – Need a representative sample of participants (volunteers) – Are respondents being truthful? 9

4. Psychological Tests • mainly designed to measure individual differences • 1. Achievement tests: Measure knowledge of a topic • 2. Aptitude tests: Measure potential for success in a subject or profession • 3. Intelligence tests: general aptitude • 4. Personality tests: daily behavior Limitation: takes time to create 10

EXPERIMENTS

Correlation vs. causation Even a strong correlation does not guarantee causation Allows prediction, but not control Could be a third variable at work A common link that could explain the correlation If so, we call the original correlation a 12 spurious correlation It may be a fact --but it’s not causal

Examples: Correlation between: (a) Amount a child watches violent television and (b) a child’s aggression as a teenager A third variable may cause both (a) and (b): Parenting style Genetics Poverty 13

Other spurious correlations? Higher grades in the front row Body modification & sexual promiscuity Smoking & lung cancer Tooth-brushing and cavities 14

In an experiment… The researcher actively manipulates (alters) the situation in order to demonstrate an effect Example: Deliberately expose children to different films: one group watches violent film One group watches non-violent film Later, observe aggression in each group 15

Traditional terms Independent Variable: The aspect of the environment that is manipulated in an experiment (at least two conditions) Example: Violent show and nonviolent show Dependent Variable: The behavior that is measured in an experiment Example: Amount of aggressive behavior after watching the show 16

Independent Variable 17 Dependent Variable

Importance of Control • Experimental and control group must be similar except with regard to independent variable. • Everything else must be controlled • Same room, conditions, time of day • Also a Control group 18

Randomization • Random selection from population • Random assignment to conditions 19

Problems & solutions • Participants may guess what the researcher expects to find – Then, may change behavior to fit expectations • Ways of reducing expectancy effects: – Give placebo to those in the control group – Don’t tell participants which group they are in (single-blind study) – Make sure neither researcher nor participants knows which group is which (double-blind study) 20

Limitation of experiments: too artificial? – Would participants have behaved the same way outside of the artificial laboratory situation? • Example: Would children in the television study behave the same way at home or school? – i. e. , Do the results generalize to realworld situations? 21

PROS AND CONS OF METHODS: It’s a trade-off • Methods that permit control tend to be more artificial • sometimes less ethical • Solution: use multiple methods 22