CHAPTER 1
1.3 Research process
research process
o collect data
o analyse data
1.5 Generating and testing theories and hypotheses
theory
o good theory allows us to make statement about state of world
hypothesis
o = explanatory statement about something, it is not itself observable
prediction
o = something derived from hypothesis that operationalizes it so that you can observe
things that help you to determine plausibility of hypothesis
o not hypothesis
1.6 Collecting data: measurement
1.6.1 Independent and dependent variables
independent variable
o = variable thought to be cause of some effect
o usually used in experimental research to describe variable that experimenter has
manipulated
dependent variable
o = variable thought to be affected by changes in independent variable
o can think of this variable as an outcome
predictor variable
o = variable thought to predict an outcome variable
o Basically another way of saying ‘independent variable’
outcome variable
o = variable thought to change as function of changes in predictor variable
, o term could be synonymous with ‘dependent variable’
variables can change or vary, btwn people, locations, or time
1.6.2 Levels of measurement
Level of measurement
o relationship btwn what is being measured and # that represent what is being measured
variables can be split into categorical and continuous, and within these types there are
different levels of measurement
categorical variable
o = entities are divided into distinct categories
o binary variable
o nominal variable
o ordinal variable
continuous variable
o = entities get a distinct score
o interval variable
o ratio variable
binary variable
o = there are only two categories
o e.g., dead or alive
nominal variable
o = there are more than two categories
o e.g., whether someone is an omnivore, vegetarian, vegan, or fruitarian
ordinal variable
o = same as a nominal variable but the categories have a logical order
o e.g., whether people got a fail, a pass, a merit or a distinction in their exam
interval variable
o = equal intervals on variable represent equal differences in property being measured
o e.g., difference between 6 and 8 is equivalent to the difference between 13 and 15
ratio variable
o = same as interval variable, but ratios of scores on the scale must also make sense
o e.g., score of 16 on anxiety scale means that person is, in reality, twice as anxious as
someone scoring 8
o for this to be true, scale must have meaningful zero point
,1.6.3 Measurement error
Measurement error
o = discrepancy btwn number we use to represent thing we’re measuring and actual
value of thing we’re measuring
o self-report measures: produce larger measurement error
1.6.4 Validity and reliability
way to ensure measurement error is kept to minimum
o determine properties of measure that give confidence that it is doing its job
o 1st property: validity
= whether instrument measures what is sets out to measure
criterion -
concurrent -
predictive -
content -
o 2nd property: reliability
= whether instrument can be interpreted consistently across situations
test-retest reliability
1.7 Collecting data: research design
correlational or cross-sectional research
o observes what naturally goes on in world without directly interfering w it
experimental research
o manipulate one variable to see its effect on another
1.7.1 Correlational research methods
longitudinal research
o measuring variables repeatedly at time points
limitation correlational research
o tertium quid
o = 3rd person or thing of indeterminate character
1.7.2 Experimental research methods
Experimental methods
o want to provide comparison of situations (called treatments or conditions) in which
proposed cause is present or absent
, 1.7.3 Two methods of data collection
between-groups/between-subjects/independent design
within-subject/repeated-measures design
1.7.4 Two types of variation
unsystemic variation
o due to experimenter doing something in one condition but not in other condition
o systemic variation
o due to random factors that exist btwn experimental conditions
1.7.5 Randomization
randomization
o to determine in which order conditions are completed
practice effects
boredom effects
1.8 Analysing data
1.8.1 Frequency distributions
frequency distribution or histogram
normal distribution
o A frequency distribution can be either a table or a chart that shows each possible score
on a scale of measurement along with # of times that score occurred in the data
Scores are sometimes expressed in a standard form known as z-scores.
To transform a score into a z-score you subtract from it the mean of all scores and divide
the result by the standard deviation of all scores.
The sign of the z-score tells us whether the original score was above or below the mean;
the value of the z-score tells us how far the score was from the mean in standard
deviation units.
Two main ways distribution can deviate from normal
o skew: lack of symmetry
o kurtosis: pointyness
Skew
1.3 Research process
research process
o collect data
o analyse data
1.5 Generating and testing theories and hypotheses
theory
o good theory allows us to make statement about state of world
hypothesis
o = explanatory statement about something, it is not itself observable
prediction
o = something derived from hypothesis that operationalizes it so that you can observe
things that help you to determine plausibility of hypothesis
o not hypothesis
1.6 Collecting data: measurement
1.6.1 Independent and dependent variables
independent variable
o = variable thought to be cause of some effect
o usually used in experimental research to describe variable that experimenter has
manipulated
dependent variable
o = variable thought to be affected by changes in independent variable
o can think of this variable as an outcome
predictor variable
o = variable thought to predict an outcome variable
o Basically another way of saying ‘independent variable’
outcome variable
o = variable thought to change as function of changes in predictor variable
, o term could be synonymous with ‘dependent variable’
variables can change or vary, btwn people, locations, or time
1.6.2 Levels of measurement
Level of measurement
o relationship btwn what is being measured and # that represent what is being measured
variables can be split into categorical and continuous, and within these types there are
different levels of measurement
categorical variable
o = entities are divided into distinct categories
o binary variable
o nominal variable
o ordinal variable
continuous variable
o = entities get a distinct score
o interval variable
o ratio variable
binary variable
o = there are only two categories
o e.g., dead or alive
nominal variable
o = there are more than two categories
o e.g., whether someone is an omnivore, vegetarian, vegan, or fruitarian
ordinal variable
o = same as a nominal variable but the categories have a logical order
o e.g., whether people got a fail, a pass, a merit or a distinction in their exam
interval variable
o = equal intervals on variable represent equal differences in property being measured
o e.g., difference between 6 and 8 is equivalent to the difference between 13 and 15
ratio variable
o = same as interval variable, but ratios of scores on the scale must also make sense
o e.g., score of 16 on anxiety scale means that person is, in reality, twice as anxious as
someone scoring 8
o for this to be true, scale must have meaningful zero point
,1.6.3 Measurement error
Measurement error
o = discrepancy btwn number we use to represent thing we’re measuring and actual
value of thing we’re measuring
o self-report measures: produce larger measurement error
1.6.4 Validity and reliability
way to ensure measurement error is kept to minimum
o determine properties of measure that give confidence that it is doing its job
o 1st property: validity
= whether instrument measures what is sets out to measure
criterion -
concurrent -
predictive -
content -
o 2nd property: reliability
= whether instrument can be interpreted consistently across situations
test-retest reliability
1.7 Collecting data: research design
correlational or cross-sectional research
o observes what naturally goes on in world without directly interfering w it
experimental research
o manipulate one variable to see its effect on another
1.7.1 Correlational research methods
longitudinal research
o measuring variables repeatedly at time points
limitation correlational research
o tertium quid
o = 3rd person or thing of indeterminate character
1.7.2 Experimental research methods
Experimental methods
o want to provide comparison of situations (called treatments or conditions) in which
proposed cause is present or absent
, 1.7.3 Two methods of data collection
between-groups/between-subjects/independent design
within-subject/repeated-measures design
1.7.4 Two types of variation
unsystemic variation
o due to experimenter doing something in one condition but not in other condition
o systemic variation
o due to random factors that exist btwn experimental conditions
1.7.5 Randomization
randomization
o to determine in which order conditions are completed
practice effects
boredom effects
1.8 Analysing data
1.8.1 Frequency distributions
frequency distribution or histogram
normal distribution
o A frequency distribution can be either a table or a chart that shows each possible score
on a scale of measurement along with # of times that score occurred in the data
Scores are sometimes expressed in a standard form known as z-scores.
To transform a score into a z-score you subtract from it the mean of all scores and divide
the result by the standard deviation of all scores.
The sign of the z-score tells us whether the original score was above or below the mean;
the value of the z-score tells us how far the score was from the mean in standard
deviation units.
Two main ways distribution can deviate from normal
o skew: lack of symmetry
o kurtosis: pointyness
Skew
