Vocabulary Ch 1 Flashcards
Mean
Arithmetic average
The sum of the scores divided by the number of scores
Median
Arrange numbers in order from smallest to largest
Midpoint of the list
Remember: with even numbers, we add the middle numbers
Ex: 1,1,4,5,7,8
4+5/2=9/2 or 4.5
Mode
The score or category that has the greatest frequency
Std
On average, how far any given data point is away from the mean
Average distance from the mean
If it is 0, then it is the exact same score, so there is no variation
- M=80 so our s= 4, what does it mean? 4 pts away from the mean
Statistically significant
The results are not likely not due to chance
Ex: cheerleaders and pizza
Non cheer:3.4
Cheer:1.5
For what type of data, would you typically use the mode?
Nominal data
When we use the median instead of the mean:
Huge # for sample we use the ______ instead of the mean
Pie chart
Hard to compare sections
We avoid them
Study
- observe/ assess without changing the environment
- correlational studies
Experiments
- manipulates variables while observing them, then examines how changes in one/ more variables affect changes in others
- cause and effect
Mode
Describes the Ideal form of central tendency measurement for nominal, it is the______
Median
Describes the ideal form of central tendecy for ordinal, it is the ______.
Mean
Describes the ideal form of central tendency measurement for interval, it is the ____.
Standard deviation
On average, how far any given data point is away from the mean.
Measure of how spread out data is
If it is 0, then it is the exact same score for everything, no variation.
Stats
Collecting, analyze, and understanding data Goal: effective decision making Bring life to a data table Turn ugly data into a beautiful princess Gain insight Find solutions
Outliers
Data points away from the others
Qualitive research
Quality Words Observed but not readily measured Smells, colors, appearance, beauty, etc. Friendly demeanor, positive outlook, considerate, etc. Interview style
Quantative research
"Quantity" #'s Data easy to quantify Data Can be measured Height, weight, age, income Ex: 57 males, 63 females 47% on deans list Transfer rate 72%
Descriptive stats
Summary of info regarding one variable
Ex: mean, median, mode, etc
Small part of stats
Inferential stats
"We have a sample, let's see how we can relate it to the population" "Want to infer an unknown quantity" Big part of stats Ex: sample of elac students Sample to population
Primary data
Data you gather yourself
Pro:
-phrase it yourself
Design questionnaire
Secondary data
Secondary analysis Gather from someone else Pro: -set for you, so you just analyze it -No bias b/c it is a big population Con: - you can get stuck with how it is phrased
Cross sectional data
Do it all at the same time w/ diff groups More pratical, can get data collection done Ex: remember class demonstration with marriage
Longitudinal data
Same group, but follow over time
Stronger design overall b/c work with same people
Operationalize
How you measure concepts
reliability
Consistency of mesurement
Consistency
Ex: watch and time
Validity
Accuracy
To have validity, you have reliability
Stronger than realibility
“Consistency plus getting the right answer”
Stronger
Ex: watch is always consistent with time but may not be valid
Weigh self: says you’re 186 when you are really 190
Consistent but not valid
Interrator realibility
Used to assess the degree towhich different raters/ observers give consistent estimates of the same phenomenon
Type 1 error
Alpha False positive Rejecting a true null hypothesis Ex: pregnancy test tells you pg but arent Replicate study to prevent it
Type 2 error
Beta False negative Accepting a false null hypothesis Ex: tells you you arent pregnant, but are Increase sample size
Nominal
Weakest
Categories only, no ordering to it
One is not higher or better than the other
Ex: county you live in, car you drive,hair color
Categorical data-race