week 6 Flashcards
Define factorial design including the term factor
factorial design: a design that includes two or more independent variables
Factor: the independent variable, or predictor variable,
-we refer to factors in studies when we have more than one independent variable within one project.
A 2 x 3 factorial design is a two-factor design with ______ levels of the first factor and ______ levels of the second factor
2 levels of the first factor
3 levels of the 2nd factor
define a main effect for one factor and an interaction between factors
Main effect –
When we have multiple factors in a study, we can explore main effects and we can explore interaction effects.
-one main effect of our independent variable–> difference between Treatment A and Treatment B,
-one factor (independent variable) → there’s only one effect
interaction –
- occur when the effect of one factor depends on the different levels of another factor.
- “depends” is a really good word when interpreting interaction effects,
- on a graph - The interaction effects have more to do with the slope of the lines. when the slope of the lines Intersect → there’s an interaction; or parallel line –> no interactions, but we have main effects,
example: Differences in mean scores on BNT for Treatment A differ from Treatment B depending on whether a person received treatment 1x/week or 5x/week.
pg 319
a factorial study measures allergy symptoms before and after taking medication for a group taking the real medication and a control group taking a placebo. What kind of design is being used?
mixed factorial designs –> a factorial study that combines 2 different research designs
a group of 10 individuals who receive treatment A. And they have a pretreatment test and then a posttreatment test-.
A different group of 10 could be in treatment B and have a pretreatment test and a posttreatment test.
this has a mix of both between and within. Between would be treatment type, and within would be pre- to posttreatment.
describe the two general categories of statistics, descriptive and inferential, and explain the purposes of each
descriptive research,–>
-describe the data/variables → not looking at relationships.
-Statistical tests used for descriptive research:
measures of central tendency, → mean, median, and mode.
range → to describe the range of scores that we observe.
standard deviation, typically, to indicate variance, or variability.
inferential statistics
- are used when we’re trying to infer characteristics about a population from a small sample of participants.
- inferential statistics help to differentiate between results that represent real, actual true patterns and those that are indicative of sampling error.
- inferential statistics are a systematic procedure that allow us to find support for our hypotheses, or they allow us to refute our hypotheses
define the null hypothesis and the alternative hypothesis
null hypothesis → this is a statement about the population indicating that there’s no effect, no change, no difference, no relationship between your variables.
- When we reject the null hypothesis, we in turn find support for the alternative hypothesis
- Ho
alternative hypothesis -
- aka researcher’s hypothesis (will be stated as the hypothesis, not the alternative hypothesis)
- HA
- Statement is a positive → there is an effect, there is a change, there is a difference between groups, there is a relationship between these factors.
- The goal of the researcher is to reject the null hypothesis, using our hypothesis tests, our inferential statistics after collecting data.
explain what p < .05 means
p-value, p is the significance value (from significant testing) that we’ve obtained after we do our hypothesis testing.
- If p is < 0.05 means that there’s less than a 5% chance that our data resulted from chance.
- This means that there’s a 95% chance that our results were due to the variables that we were studying and not just due to random chance.
define effect size
With significant differences we can quantify the magnitude if we calculate effect size.
effect size is a standardized measure of the magnitude of the observed effect.
Cohen’s d
Pearson’s correlation coefficient r
what elements are required for a single-case research study to qualify as an “experiment”
single-subject experimental designs –>
- aka single case designs or single-subject design.
- results from one participant to establish a cause and effect relationship between variables.
- can use several participants, but analyzing each individual themselves → NOT averaging across people.
have to include manipulation of the independent variable, strict control of extraneous variables
traditional statistics (means, variances and hypothesis tests) are NOT used to evaluate results from a single-case design consisting of the following four phases in the order given: baseline, treatment, baseline, treatment. What is?
Visually inspect graphs of participant data
Want to see:
Large difference between baseline and posttreatment conditions
Small variability in performance within each tx condition
Strict controls of all other variables
what name is given to a single-case design consisting of the following four phases in the order given: baseline, treatment, baseline, treatment
ABAB reversal design
what is an ethical concern for the ABAB design
withdrawing treatment ay not result in change of behavior; even though the researcher may return to baseline by removing the treatment, the participant’s behavior may not return to baseline
withdrawing a successful treatment (possibly with the intention of having the client’s behavior revert to original problem condition)
describe the structure of a multiple-baseline design
- Two simultaneous baselines for 2 diff behaviors or participants, then tx applied to 1 behavior/participant, baseline continues for other behavior/participant then applied later
- When that other participant has treatment applied, we should then see changes in their behavior.
- -we can try to control for these other extraneous factors by taking multiple baselines.
identify the primary strength of a multiple-baseline design
primary strength
- Establishes cause-effect relationships
- Flexible, bc researcher comes with general plan but if participant fails to respond to tx, they can modify conditions (possible bc looking at each individual separately)
- Combines elements of experimental design with clinical practice > good generalizations to clinical settings
identify the appropriate statistical test for each of the following situations: a between-subjects study comparing two groups’ means
independent-samples t-test
