Final Exam Flashcards
What is association?
There must first be a relationship or an association between the IV and the DV
Between-subjects design:
Each set of scores is obtained from different groups of participants
Within-subjects design:
Different sets of scores are obtained from the same group of participants
Characteristics of between-subjects design:
- Experimental research wherein a researcher manipulates an IV ► then measures the DV for each participant
- Goal: determine whether differences exist between two or more treatment conditions
Disadvantage of between-subjects design:
- large # of participants
- scores from each person is unique & may produce high variability in scores
What are the 2 major sources of confounding variables in between-subjects?
- confounding from ind. differences (assign. bias)
2. confounding from env. variables
What is a confounding variable?
any extraneous variable systematically differentiating the groups (ex: age)
What are the 3 techniques to limit confounding variables?
- random assignment
- matching groups
- holding variables constant
Large differences between treatments are good because…
they provide evidence of differential treatment effects
Large differences within treatments are bad because…
differences that exist inside the treatment conditions determine the variance of the scores (large variance can hide patterns in the data)
What is a factor?
The independent (or quasi-independent) variable that designates the groups being compared
What are levels?
Individual conditions or values that make up a factor
What is a factorial design?
A study that combines two or more factors
Alt Hypothesis H1:
There is at least one mean difference among the populations
Is between-treatments variance the numerator or denominator of the F-ratio?
numerator
Is within-treatments variance the numerator or denominator for the f-ratio?
denominator
F ratio formula:
differences including any treatment effects/differences with no treatment effects
If the null hypothesis is true….
then the value of F will be close to 1.00
What are the assumptions of a ANOVA?
- The observations within each sample must be independent.
- The population from which the samples are selected must be normal.
- The populations from which the samples are selected must have equal variances(homogeneity of variance).
- Violating the assumption of homogeneity of variance risks invalid test results.
What is a partial correlation?
A partial correlation measures the relationship between two variables while mathematically controlling the influence of a third variable by holding it constant
Pearson’s correlation uses:
data from interval or ratio measurement scales
Spearman (Rs) uses:
ranking (ordinal scale)
Point-biserial correlation:
One variable has only two values(called a dichotomous or binomial variable)
R2 (squared):
- measure of effect size
- amount of variance accounted for
Phi coefficient:
- Both variables are re-coded to values 0 and 1 (or any two digits)
- Both variables (X and Y) are dichotomous
Regression analysis
precisely defines the line.
General equation for a line:
Y = bX + a
Regression:
a line that is the best fit for the actual data that minimizes prediction errors.
What is latin squared?
a way to counterbalance
Beta coefficients in multiple linear regression
The higher the beta value the greater the impact of the predictor variable on the criterion variable
Mediator variables:
A mediation model is one that seeks to identify and explain the mechanism or process that underlies an observed relationship between a predictor variable and the criterion variable via the inclusion of the third hypothetical variable, that is, a mediator variable.
ex: iq –> study habits –> exam scores
Moderator variables:
Amoderator variable is a thirdvariablethat affects the strength of the relationship between a predictor variableand a criterion variable in regression analysis
Parametric tests share several assumptions:
- Normal distribution in the population
- Homogeneity of variance in the population
- Numerical score for each individual
Nonparametric tests are needed if…
if research situation does not meet all these assumptions.
For Chi-square &nonparametric tests:
do not state hypothesis in terms of a population parameter
Categorizing makes what?
nonparametric
Choice of statistical procedure determined primarily by the…
the level of measurement.
What is attrition?
People who drop out of the study
What is external validity?
The extent to which the results of a research study can be generalized
What is a threat to external validity?
Any characteristic of a study that limits the ability to generalize the study’s results
What are the 3 kinds of generalization, which can involve threats to validity?
- Generalization from a sample to the general population
- Generalization from one research study to another
- Generalization from a research study to a real-world situation
In a quasi experiment you don’t have…
control or manipulation
What are threats to internal validity in a quasi experiment?
- Retesting & Instrumentation
- Attrition
- History
- Maturation
- Regression toward the mean
Is effect size effected by increasing sample size?
NO
What is external validity?
extent to which the results of a research design can be GENERALIZED
What is ecological validity?
extent to which the research is conducted in situations that are similar to the everyday life experiences
What are field experiments?
experiments conducted in a natural environment (ex: library, school, anywhere other than a lab)
When n is small (less than 30), the t distribution will be…
flatter & more spread out than the normal z distribution
Does the t statistic require the population standard deviation?
no
Does the z test require the population standard deviation?
yes
Which combination of factors is most likely to produce a significant value for an independent-measures t statistic?
large mean difference & small variance
For an independent-measures t statistic, the estimated standard error measures how much…
difference is reasonable to expect between the sample means if there is no treatment effect.
For an independent measures research study, the value of cohen’s d or r squared describes what?
how much difference there is between the two treatments
Increasing the variance, increases the denominator, decreases the _________.
t-statistic
How does a repeated measures study reduce the variance?
by removing individual differences
Does an ANOVA allow researchers to compare several treatments conditions w/o a hypothesis test?
Yes
If the null hypothesis is true, the F-ratio for ANOVA is expected to be…
near 1.00
When are post hoc tests needed?
when you reject H0 (indicating at least one main difference)
What is a repeated-measures design also known as?
within-subjects design
What is a repeated-measures design?
- two separate scores are obtained for each individual in the sample
- same subjects are used in both treatment conditions
What are advantages of using a repeated-measures design?
- Requires fewer subjects
- Able to study changes over time
- Reduces or eliminates influence of individual differences
- Substantially less variability in scores
What does ANOVA stand for?
analysis of variance
What is an advantage of using a t-test?
can be used to compare more than two treatments at the same time
What is the null hypothesis for the ANOVA?
the level or value on the factor does not affect the dependent variable
What is the alt hypothesis (H1) for the ANOVA?
There is at least one mean difference among the populations
What is the goal of a experimental research study?
To demonstrate a cause-and-effect relationship between two variables
What are 3 techniques to control extraneous variables?
- Holding variables constant
- Matching values across treatment conditions
- Control by randomization
What Is not guaranteed to be successful in balancing variables?
randomization
What are manipulation checks?
- Directly measure whether the IV had the intended effect on the participant
- Ways to check the manipulation
What is pilot testing?
Studies conducted before the research to determine if the manipulation is impactful
What is the advantage of using ANOVA over a t-test?
can be used to compare MORE THAN TWO treatments at the same time
Phi coefficient:
dichotomous
Pearson:
interval & ratio
Spearman:
ordinal
What is a single-group design?
- a group of individuals are measured AFTER they have had the experience of interest
- cannot be used to draw conclusions about how an experience has affected individuals involved because there is no control group.
What is a comparison-group design?
- uses a comparison group that is expected to be similar but not equivalent to the experimental group
- need to draw definitive conclusions
What is a single-group before-after design?
(sometimes referred to as a pretest-posttest design) is a research study in which a series of observations is made over time for one group of participants
What is a comparison-group before-after design?
- (sometimes called pretest–posttest nonequivalent control group design) compares two non-equivalent groups
- One group is measured twice ►once before a treatment is administered and once after
- This design attempts to limit threats to internal validity
- Two way ANOVA used
What is a time series design?
- has a series of observations for each participant before a treatment or event and a series of observations after the treatment or event
- These are research designs with longitudinal research designs in which the dependent measure is assessed for one or more groups more than twice, at regular intervals, both before and after the experience of interest occurs.
What are the assumptions of a parametric test?
- normal distribution in the population
- homogeneity of variance in the pop.
- numerical score for each individual
What is a nonparametric test?
- they are needed if research situation does not meet all parametric assumptions
- doesn’t state the hypothesis in terms of a specific population parameter
What is regression?
a method of finding an equation describing the best fitting line for a set of data
What does r represent?
measures the correlation size
When to do a chi square test?
classification in non-numerical categories (ordinal or nominal)
When to do a t-test?
for numerical scores (interval/ratio scale)
When to use a pearson correlation?
for data having linear relationships (interval or ratio data)
What is a partial correlation?
measure the relationship between 2 variables while mathematically-controlling the influence of a 3rd variable
What is a correlation hypothesis test?
Sample correlation r used to test population ρ (rho)
What is a mediator variable?
seeks to identify & explain the mechanism/process that underlies an observed relationship between a predictor variable & the criterion variable
What is a moderator variable?
is a third variable that affects the strength of the relationship between a predictor variable & a criterion variable in regression analysis
What is a mixed factorial design?
an ANOVA using both repeated & independent measures
What are extraneous variables?
variables other than the IV that causes changes in the DV
Regression towards the mean:
ex: when someone takes the test more than once they score closer to the mean