Stats-Midterm 1 Review ACTUAL UPDATED Questions and CORRECT Answers
Terms in this set (92)
Validity The extent to which your assessment actually measures what it intends to measure
(accuracy)
Reliability The extent to which your assessment yields consistent results (consistency)
Validity and Reliability of a Proper Ruler High validity and high reliability
Validity and Reliability of a Homemade Ruler Low validity and high reliability
Validity and Reliability of a Bungy Ruler Low validity and low reliability
Dependent Variable The variable being measured by experimentor, the data that is being recorded
(outcome)
Independent Variable The variable that is being manipulated by the experimenter (usually 2 'levels', can
be more)
Time Series Looking for trends over time; each observation represents a measurement at
some point in time, repeated measurements allow us to see trends
Cross Sectional Comparing groups; each observation represents a measurement at some point in
time, comparing across groups allows us to see differences
Random Assignment Any subject has an equal chance of getting assigned to either condition (true
experiment)
Non-Random Assignment Self selection or subject variables (quasi experiment)
True Experiment Random assignment to groups --> can be used as evidence for cause and effect
Quasi Experiment Non random assignment to groups --> cannot be used as evidence for cause and
effects, only that the variables tend to co-occur (correlation and subject variables
are always quasi)
Correlation Relationship between 2 dependent measures (no random assignment - always
quasi); range between 1 and -1, the closer to 0 the weaker the relationships and
the worse the prediction
Random Sampling Each person in the population has an equal chance of being selected to be in the
samples (not the same as random-assignment, nothing to do with true and quasi
experiments)
Population The entire group of people about whom a researcher wants to learn (Greek
letters - 'mew')
, Sample The group of people who actually participate in a research study (Roman letters -
'x bar')
Within Participant Study Each subject participates in every level on independent variable (aka repeated
measures); everyone in both/all groups
Between Participant Study Each subject participates in only 1 level of independent variable; split into
half/groups
Single Blind Participant doesn't know which condition they're in; designed to minimize
participant bias from expectations
Double Blind Neither participant nor experimenter know which condition they're in; designed to
minimize both participant and experimenter bias from expectations
Descriptive Statistics Organizing and summarizing data; measure all players height's on the basketball
team
Inferential Statistics Generalizing beyond actual observations making "inferences" based on data
collected; measure only a sample of the players height's on the basketball team
Parameter Numerical value calculated from a population (census); usually unknown and
represented by Greek letters (𝜇)
Statistic Numerical value calculated from a sample; usually represented by Roman letters
(x̄)
Likert Scale Measure a construct using a "level of agreement" for a series of items, responses
are summed up and the total is the measure of the construct
Construct (Likert Scale) Measure by 3 questions (the 3 questions are our operational definition of the
construct)
Scatterplot Displays correlation, relationships between 2 quantitative variables
Positive Correlation As values on one variable go up, so do values for the other variable; Income and
Travel
Negative Correlation As values on one variable go up, the values on the other variable go down;
Activity Level and Age
Perfect Relationship/Predictor r = +1.00 or -1.00
Good Relationship/Predictor r= +0.80 or -0.80
Poor Relationship/Predictor r= +0.20 or -0.20
Very Poor Relationship/Predictor r= 0
Terms in this set (92)
Validity The extent to which your assessment actually measures what it intends to measure
(accuracy)
Reliability The extent to which your assessment yields consistent results (consistency)
Validity and Reliability of a Proper Ruler High validity and high reliability
Validity and Reliability of a Homemade Ruler Low validity and high reliability
Validity and Reliability of a Bungy Ruler Low validity and low reliability
Dependent Variable The variable being measured by experimentor, the data that is being recorded
(outcome)
Independent Variable The variable that is being manipulated by the experimenter (usually 2 'levels', can
be more)
Time Series Looking for trends over time; each observation represents a measurement at
some point in time, repeated measurements allow us to see trends
Cross Sectional Comparing groups; each observation represents a measurement at some point in
time, comparing across groups allows us to see differences
Random Assignment Any subject has an equal chance of getting assigned to either condition (true
experiment)
Non-Random Assignment Self selection or subject variables (quasi experiment)
True Experiment Random assignment to groups --> can be used as evidence for cause and effect
Quasi Experiment Non random assignment to groups --> cannot be used as evidence for cause and
effects, only that the variables tend to co-occur (correlation and subject variables
are always quasi)
Correlation Relationship between 2 dependent measures (no random assignment - always
quasi); range between 1 and -1, the closer to 0 the weaker the relationships and
the worse the prediction
Random Sampling Each person in the population has an equal chance of being selected to be in the
samples (not the same as random-assignment, nothing to do with true and quasi
experiments)
Population The entire group of people about whom a researcher wants to learn (Greek
letters - 'mew')
, Sample The group of people who actually participate in a research study (Roman letters -
'x bar')
Within Participant Study Each subject participates in every level on independent variable (aka repeated
measures); everyone in both/all groups
Between Participant Study Each subject participates in only 1 level of independent variable; split into
half/groups
Single Blind Participant doesn't know which condition they're in; designed to minimize
participant bias from expectations
Double Blind Neither participant nor experimenter know which condition they're in; designed to
minimize both participant and experimenter bias from expectations
Descriptive Statistics Organizing and summarizing data; measure all players height's on the basketball
team
Inferential Statistics Generalizing beyond actual observations making "inferences" based on data
collected; measure only a sample of the players height's on the basketball team
Parameter Numerical value calculated from a population (census); usually unknown and
represented by Greek letters (𝜇)
Statistic Numerical value calculated from a sample; usually represented by Roman letters
(x̄)
Likert Scale Measure a construct using a "level of agreement" for a series of items, responses
are summed up and the total is the measure of the construct
Construct (Likert Scale) Measure by 3 questions (the 3 questions are our operational definition of the
construct)
Scatterplot Displays correlation, relationships between 2 quantitative variables
Positive Correlation As values on one variable go up, so do values for the other variable; Income and
Travel
Negative Correlation As values on one variable go up, the values on the other variable go down;
Activity Level and Age
Perfect Relationship/Predictor r = +1.00 or -1.00
Good Relationship/Predictor r= +0.80 or -0.80
Poor Relationship/Predictor r= +0.20 or -0.20
Very Poor Relationship/Predictor r= 0
