Psychology 202 - Test 1 Flashcards
data
information
statistics
branch of mathematics focused on organization, analysis, and interpretation of a group of numbers
descriptive statistics
used to describe a group of numbers from a study
inferential
used to draw conclusions from collected data
variable
characteristic of something or someone that can have different vaules
i.e. people, [usually] mind
constant
if the characteristic does not/can not vary
- dependent on perspective
values
numbr or category
score
particular value on a variable
- tells how much there is of what is being measured
equal-interval variable
a variable in which the numbers stand for approximately equal amounts of what is being measured
i.e. in stress rating, difference between 4 & 6 is the same as the difference between 7 & 9
ratio scale
used if the equal-interval variable has an absolute zero point
i.e. number of siblings > zero means something and is important
absolute zero point
value of zero on the variable indicates complete absence of the variable
i.e. number of siblings > zero = no siblings
rank order variable
a variable where numbers stand ONLY for the relative ranking
- ordinal variables
- provides less info/less accurate than equal-interval but sometimes easier/only info available
i. e. olympics (1,2,3) but 1 & 2 can be close while three was far behind them
nominal variable
variable in which the values differ as names or categories
i. e. favorite sports team
* can go from nominal to numeric but not the other way around
discrete variable
specific values and nothing in between
continuous variable
has infinite number of values in between any two values
population
the entire group of people that is studied
- can range from small to the entire world depending on the question
sample
a subset of the population
- small/more manageable group to study
- (hopefully) identical to population > generalizability
frequency table
table that lists all values that are possible along with the number of cases that have that value
relative frequency table
tells frequency AND frequency relative to other scores
- divide number of cases in each value by total number of cases
histogram
graphic representatio of frequency of scores
- x = possible values
- y = number of cases
number of peaks (histogram)
1 peak = unimodal
2 peaks = bimodal
3+ peaks = multimodal
symmetrical distributions
roughly equal scores on both sides of the peak
skewed distributions
unequal scores on each side of the peak
- positively skewed > more scores on left side
- negatively skewed > more scores on the right side
normal curve
symmetrical, bell shaped curve that has changes in curve direction at exactly 1 standard deviation above and 1 standard deviation below the mean
- theoretical distribution
- mode, median, and mean are all exactly the same number
- Middle point = average point = most frequent point
- more scores you have = closer you get to normal distribution
- assume data would look like normal curve if we had enough
- 68.2% = 1 SD
- 95.4% = 2 SD
- 99.7% = 3 SD
platykurtic
most values have roughly the same frequency
- upside down plate
leptokurtic
very few values have a high frequency
- tower
measure of central tendency
single number that we use to describe a distribution of scores
- representative of all scores
mean
mathematical average of a group of scores
- μ = population, M = sample
- mean = Σx/N
- most stable measure of central tendency
- takes all scores into account
- can be value no one got
- incredibly sensative to outliers
mode
most frequent score in a distribution
- only measure that can be used with nominal data
- says nothing about other scores
- doesn’t tell the placement of the score
median
score in the middle of a distribution
- scores in order from smallest to largest and find middle score
- can be the same as mode
- can be score no one has/received
- does not mean there is equality in the range
variability
the amount of variation in a distribution of scores
range
the difference between the highest and lowest score
- very unstable
- no additional stats calculated
variance
measure of variability that considers how different each score in a distribution is from the mean
- extremely important in stats
- population = δ
- sample = SD
- variance = Σ(x - M)²/N
- SS = Σ(x - μ)²
standard deviation
the average amount that a set of scores differ from one another (how much scores vary)
- population =
- sample = SD
- standard deviation = √Σ(x - μ)²/N
z-score
number of standard deviations above or below the mean an actual score is
- standardizes scores
- z = (x - M)/SD
z-scores > percent to value
- go to closest percent
- find percent and look at corresponding z-score
- invert z-score equation
