PSY 3213 Exam Study Questions with 100% Verified
Answers
Levels of measurement
Categorical and Continuous
types of Categorical measurement
Dichotomous variable
Nominal variable
Ordinal variable
Dichotomous variable
there are only 2 categories
Nominal variable
more than 2 categories
Ordinal variable
the same as nominal, but in logical order. ie. income groups on most surveys
Continuous
numbers in order, and everyone gets a distinct score, not put into a group of scores
How to design a new scale
1. what do you want to measure? (construct approach: a theory containing various conceptual
elements)
2. Begin writing items- the more the merrier- each one give s a quantifiable value for a trait-
should be clear and simple-and should discriminate among test takers-total score should have
NORMAL DISTRIBUTION
3. Give the survey to a lot of people- this helps us determine which items were useful.. aka. how
, well does each item correlate with the total.
4. Do the scores predict behavior
What is reliability?
the repeatability of findings
What is validity?
are the findings genuine? was the experiment credible?
internal validity
the instruments or procedures used in the research measured what they were supposed to
measure.
external validity
the results can be generalized beyond the immediate study. It should also apply to people
beyond the sample in the study.
Experiments
are always studies...
-where a variable was manipulated and the effects of that variable were observed in a
laboratory setting.
Studies
Are NOT always experiments
-most are empirical and thus correlational studies
Correlational studies
attempt to show the extent to which two different variables relate to each other.
-positive correlation- as X increases, Y increases
-negative correlation- as X increases, Y decreases
Pearson's R
Answers
Levels of measurement
Categorical and Continuous
types of Categorical measurement
Dichotomous variable
Nominal variable
Ordinal variable
Dichotomous variable
there are only 2 categories
Nominal variable
more than 2 categories
Ordinal variable
the same as nominal, but in logical order. ie. income groups on most surveys
Continuous
numbers in order, and everyone gets a distinct score, not put into a group of scores
How to design a new scale
1. what do you want to measure? (construct approach: a theory containing various conceptual
elements)
2. Begin writing items- the more the merrier- each one give s a quantifiable value for a trait-
should be clear and simple-and should discriminate among test takers-total score should have
NORMAL DISTRIBUTION
3. Give the survey to a lot of people- this helps us determine which items were useful.. aka. how
, well does each item correlate with the total.
4. Do the scores predict behavior
What is reliability?
the repeatability of findings
What is validity?
are the findings genuine? was the experiment credible?
internal validity
the instruments or procedures used in the research measured what they were supposed to
measure.
external validity
the results can be generalized beyond the immediate study. It should also apply to people
beyond the sample in the study.
Experiments
are always studies...
-where a variable was manipulated and the effects of that variable were observed in a
laboratory setting.
Studies
Are NOT always experiments
-most are empirical and thus correlational studies
Correlational studies
attempt to show the extent to which two different variables relate to each other.
-positive correlation- as X increases, Y increases
-negative correlation- as X increases, Y decreases
Pearson's R
