Chapter 1 - Variables And Measurement Scales (Lecture Slides) Flashcards
What is an observational study?
Measure or survey members without trying to affect them.
What is an experimental study?
Assign people or things to groups and apply some treatment/experimental condition to one of the groups, while the other group does not receive the treatment or receive another experimental condition (control group).
Define population
The entire group of individuals that are of interest in a study.
What is a sample?
A subset of respondents from the population (may or may not be random;
representative).
Often represented as “N.”
Researchers don’t have the time or resources to engage the entire population, so they use a sample to (hopefully) approximate the population.
What is a variable?
An attribute that takes on DIFFERENT
values across persons.
For Example: Variables in GPA, personality, IQ, interpersonal relationships, reaction time, substance use, etc.
What are the variable measurement scales?
Categorical/qualitative (Nominal & Ordinal)
Numerical/quantitative (Interval & Ratio)
What is a categorical/qualitative variable?
Describes data that fits into categories.
They cannot be added, subtracted, divided, or multiplied (no arithmetic operations).
There are two types: Nominal & Ordinal
Examples:
* Academic degree
* Political party affiliation
* Type of pet owned
* Gender
* Letter grades
What is a nominal variable?
It is a categorical/qualitative variable.
Can only be discrete
Responses are grouped into mutually exclusive categories with no inherent rank order.
Groups cannot be ordered from higher to lower, better to worse, etc.
There is no particular relationship between the different possibilities.
They cannot be added, subtracted, divided, or multiplied (no arithmetic operations).
Examples:
* Gender
* Treatment condition (treatment vs. control)
* Marital status
* Eye color
* Transportation type (train, bus, car, bike)
In short, nominal scale variables are those for which the only thing you can say about the different possibilities is that they are different. That’s it.
What is an ordinal variable?
It is a categorical/qualitative variable.
Can only be discrete
Responses are grouped into categories that can be rank ordered.
There is a natural, meaningful way to order the different possibilities, but you can’t do anything else.
Categories are not equidistant (the difference between a B and a C is not the same amount of knowledge as the difference between a B and an A).
They cannot be added, subtracted, divided, or multiplied (no arithmetic operations).
For instance:
Bachelor+Master ≠ Ph.D.
Grade A- Grade B ≠ Grade B- Grade C
Examples:
* Academic degree
* Letter grades
* Likert-type scales (strongly disagree, disagree, agree, strongly agree)
* Home value
* Finishing position in a race
What is a numerical/quantitative variable?
You can carry out arithmetic operations. If you can add it, it’s numerical/quantitative.
There are two types: Interval & Ratio
Examples:
* GPA
* Number of pets owned
* Number of stars in a galaxy
* How many cousins you have
* The amount of your paycheck
What is an interval variable?
It is a numerical/quantitative variable.
Can be both continuous & discrete
You can carry out arithmetic operations (you can add and subtract but multiplication and division is not permitted because there is no absolute zero)
A measurement where the difference between two values is meaningful.
The differences between the numbers are interpretable, but the variable doesn’t have a “natural” zero value.
The interval between measurements is the same (the difference between a
100 degrees and 90 degrees is the
same as the difference between 90 degrees and 80 degrees).
Examples:
* Temperature on Fahrenheit & Celsius.
* pH values
* SAT score
* Credit score
* The year you went to school
What is a ratio varibale?
It is a numerical/quantitative variable.
Can be both continuous & discrete
You can carry out arithmetic operations (we can perform all arithmetic operations including proportions, ratios, percentages, and fractions. In terms of statistical analyses, we can calculate the mean, geometric mean, harmonic mean, median, mode, variance, and standard deviation).
It has all the properties of an interval
variable but also has a clear definition of 0 (when the variable equals 0, there is none of that variable).
Examples:
* Age
* Height
* Weight
* Temperature in Kelvin
* Response time
* The number of questions you get right on a true-or-false test
NOTE:
* Temperature, expressed in Fahrenheit or Celsius, is NOT a ratio variable. A temperature of 0* F or C does not mean ‘no heat’. BUT Kelvin is a ratio variable because for Kelvin, a value of zero means no heat.
* The difference between 5° F and 10° F is the same as that between 10° F and 15° F. But 10° F is not twice 5° F.
What is a continuous variable?
One in which, for any two values that you can think of, it’s always logically possible to have another value in between.
Examples:
* Seconds (30.5 seconds)
* Response time
* Temperature on Fahrenheit & Celsius
* Speed in miles per hour
What is a discrete variable?
It’s often the case that there’s nothing in the middle. But nothing is absolute.
Examples:
* The year you went to school (it can’t be 2015.5)
* Transportation type (There isn’t a type of transportation that falls “in between” trains and bicycles)
* Finishing position in a race (Although “2nd place” does fall between “1st place” and “3rd place”, there’s nothing that can logically fall in between “1st place” and “2nd place”)
* The number of questions you get right on a true-or-false test
What is the Likert Scale?
Four (or more) point rating scale items.
Considered a discrete variable
They’re obviously NOT a nominal scale, since the items are ordered
And they’re NOT ratio scale either, since there’s no natural zero
Considered ordinal variables, though technically they are categorical.
Psychology researchers often view Likert scale items as though they are quasi-interval (i.e., we assume that any 1-point increase or decrease reflects the same amount of attitude change).
Likert scales are not numerical variables and should not be treated as intervals, even though researchers often do to simplify analysis methods.
Example:
* Questionnaires that ask you to rate something on a scale of 1-5 for instance
