Reading...
Play button
Play button
Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
25 Cards in this Set
- Front
- Back
|
What is the purpose of simple regression (one predictor)?
|
To predict the value of DV with knowledge of a given value of a predictor
|
|
|
What is the purpose of multiple regression (2+ predictors)?
|
To predict the value of the DV with an optimally-weighted combination of predictors
|
|
|
What is the slope of the regression line in the one predictor case?
|
The amount of expected change in the DV when a predictor increases by one unit
|
|
|
What is the intercept of the regression line in the one-predictor case?
|
The expected value of the DV when the predictor is set to zero
|
|
|
What is the intercept of the regression line when there are 2+ predictors?
|
The expected value of the DV when all predictors are set to zero
|
|
|
What does standardizing a variable accomplish?
|
Standardizing is a linear transformation that changes the variable’s mean to zero and its variance and standard deviation to one. (Note: This allows for direct comparison of variables, regardless of the nature of their units of measurement)
|
|
|
What is an interaction or moderation?
|
The nature of the relationship between the predictor and DV differs as a function of the level of another variable (i.e., the moderator)
|
|
|
What is Type 1 error?
|
The probability of detecting an effect in a sample that is not present in the population
|
|
|
What is Type 2 error?
|
The probability of failing to detect an effect in a sample that is present in the population
|
|
|
What is power?
|
The probability of detecting an effect in a sample that is present in the population
|
|
|
What is a sample?
|
A subset of the population that is examined for the purpose of rendering generalizations about relationships in the population
|
|
|
What is a population?
|
A group of units, with characteristics defined by the researcher, to which s/he wishes to generalize sample findings
|
|
|
What is the proper term for descriptives in a population?
|
Parameter estimates. Examples: µ = mean; σ2 = variance
|
|
|
What is the proper term for descriptives in a sample?
|
Statistics. Examples: x-bar = mean
|
|
|
Why does a large sample "n" allow for more accurate inferences, all else constant?
|
Because as sample "n" approaches infinity, the statistics values most closely match the parameter estimates
|
|
|
What is random sampling?
|
Each unit in the population has an equal and non-zero probability of being chosen for the sample
|
|
|
What is random assignment?
|
Each unit in the sample has an equal and non-zero probability of being assigned to each experimental group
|
|
|
What is internal validity?
|
The accuracy of the inference that the IV caused the DV
|
|
|
What are the three conditions for inferring causal relationship between X and Y?
|
a. X precedes Y in time.
b. X and Y are statistically correlated. (Note: There are caveats around this one as noted in Hayes, 2013). c. All other explanations have been ruled out. |
|
|
What is statistical conclusion validity?
|
The accuracy of the inference that the IV and DV are statistically correlated
|
|
|
What is external validity?
|
The accuracy of the inference that a causal relationship between the IV and the DV holds across various types of: (a) participants, (b) settings, (c) predictors, and (d) DV’s.
|
|
|
What is a confound variable?
|
An unmeasured variable that is not of interest to the researcher that is making it appear that the predictor is causing the DV, when it really is not. (Causes a Type 1 error and is a threat to internal validity).
|
|
|
What is a control variable (a.k.a. ‘covariate’)?
|
It is any variable that is:
a. Correlated with the DV. b. Not of primary interest to the researcher c. Measured in a study in order to disentangle its effects from the relationship between the predictor and DV. |
|
|
Conceptually explain the semi-partial variance for a given predictor (X)
|
The proportion of total variance in the DV that is explained uniquely by a given predictor
|
|
|
How to describe a moderation conceptually
|
“At low levels of the moderator, the relationship between the (insert predictor name here) and (insert DV name here) is (positive, negative, zero). Conversely, at high levels of the moderator, the relationship between the (insert predictor name here) and (insert DV name here) is (positive, negative, zero)"
|
