Study sets, textbooks, questions
Upgrade to remove ads
Com 304 Final
Terms in this set (64)
what is the purpose of conducting experimental studies of communication?
test whether changes in a dependent variable (DV) can be attributed to (are caused by) an independent variable (IV)
What are three features of a "true" experiment?
1. Researcher manipulates the IV
2. Researcher randomly assigns participants to conditions
3. Researcher controls extraneous variables
What term refers to pre-existing quality of participants, can't be manipulated by researcher (e.g., biological sex, race/ethnicity, age, trait verbal aggressiveness)?
What term refers to a procedure for assigning participants to conditions, such that every participant has an equal probability of being in each condition?
Why is random assignment important?
helps control for even unanticipated factors - b/c they are equally likely to end up in each condition
What term refers to any variable beyond those in RQs (beyond focus of experiment)?
What are the ways we can control extraneous variables?
1. assign participants randomly
2. keep experimental procedures consistent across conditions
3. add extraneous variable as another IV
What are 3 criteria for making causal claims?
2. Time Order
3. Alternative Explanations
Why is correlation necessarily but not sufficient to establish causation?
there could still be other factors involved
What term refers to X and Y related only because both are being caused by Z - wouldn't be related if took Z into account (controlled it)?
What does it mean to say that another variable might be "confounded" with the IV?
a third factor (Z) also occurs along with the independent variable (X) and hence one can't tell whether changes in Y are being caused by X or Z
How are experiments designed to rule out alternative explanations?
Researcher randomly assigns participants to conditions
Researcher holds everything else except manipulation of IV constant
Researcher may include a control group to isolate the impact of the treatment from other factors
What term refers to the degree to which changes in DV can be attributed with confidence to the IV, not other factors?
What term refers to the degree to which research findings can be generalized with confidence to the larger population?
What term refers to something used to draw conclusions about what's likely true in a larger population based on findings from a sample?
What do we use inferential statistics to do?
make inferences about population from results of sample
What is the main difference between inferential and descriptive statistics?
descriptives are just about the sample and inferential predict the larger population
What are the three types of distributions?
1. population distribution
2. sample distribution
3. sampling distribution
What are the 2 ways we can describe sampling distributions of means?
1. central tendency
2. dispersion (standard error of the mean)
Whats the formula for standard error of the mean?
sample SD/square root of n
When does SEm decrease?
as n increases
variability in pop scores decreases
What is the idea that when draw all samples of size "N" randomly from a larger population, the distribution of sample means (sampling distribution) will be approximately normal EVEN IF the distribution of raw scores (population or sample distribution) is skewed?
central limits theorem
When does the CLT apply?
always unless n is tiny
Why is the CLT important for the logic of inferential statistics?
can apply knowledge about standard normal curve to describe sampling distribution
can make probability judgements about whether a sample is likely to have come from a larger pop with a specific parameter
what term refers to a range of values within which there can be some degree of confidence that the true parameter (µ) is likely to fall?
What is the z value within which 95% of means in a sampling distribution of means will fall in terms of standard errors?
What is the z value within which 99% will fall?
What happens when you use a CI99 versus a CI95?
you're more confident but less precise
What's the formula for confidence intervals?
M +/- (1.96 or 2.58)(SEm)
What is the null hypothesis?
the hypothesis of no difference
When we conduct a study, which hypothesis do we actually test directly?
What is statistical significance?
we unlikely would get a difference that large simply by chance (sampling error)
What is a "p" value, and what does it tell us?
probability of getting these findings if the null hypothesis were true is LESS than 5 in 100
What are the steps in hypothesis testing?
1. formulate your research hypothesis
2. formulate the null hypothesis
3.select level of statistical significance
4. select appropriate inferential statistic to test
5. compute the inferetial statistic
6. test the the stat for signficance
What is the cut off points that we get from the table in the book called?
What types of hypotheses would you use a one-sample z-test for?
when comparing one individual score to the mean of the sample
What type of hypothesis is a chi-square statistic used to test (when do we use it)?
hypotheses involving only categorical variables
How do you calculate df for a two-way chi-square?
If you have a table of observed frequencies, how do you come up with the expected frequencies?
FOR EACH CELL: (row total x column total)/N(grand total)
What's the chi square formula you then follow after you've calculated the expected frequencies?
add up all the cells
What is Cramer's V (phi), and what does it tell us about the impact of a categorical IV on a categorical DV?
Effect Size: How large is the difference between the different conditions?
What are rules of thumb for small, medium, and large effects with Cramer's V?
.10 = small effect
.24 = moderate effect
.37 = large effect
Why should we look at effect size and not just statistical significance?
effect size can tell us how large the difference is
What type of hypothesis is Pearson's r statistic used to test?
a hypothesis with 2 quantitative variables
What does the sign of Pearson r tell us?
direction of relationship b/t X and Y
What does the size of Pearson r tell us?
strength of relationship b/t X and Y
What are rules of thumb for small, medium, and large effects with Pearson r?
r = .10 (+/-) = weak relationship
r = .24 (+/-) = moderate relationship
r = .37 (+/-) = strong relationship
What are the degrees of freedom for Pearson's r?
For a Pearson's r test, do you want r to be larger or smaller than the critical value you looked up in the book?
What type of hypothesis would be tested with an independent t-test?
when IV is categorical and DV is quantitative
What is the denominator of a t test called?
standard error of the difference between means
What are the degrees of freedom for a t test?
What is the formula for a t-test?
What are rules of thumb for small, medium and large differences with Cohen's d?
d at .20 (.15-.39) is a small effect
d at .50 (.40-.74) is a medium effect
d at .80 (.75-1.09) is a large effect
What is a Type I error?
false positive, when the null is actually true but the research rejects the null
What is a Type II error?
false negative, when the null is actually false but the researcher says its true
What single factor determines how likely a researcher is to make a Type I error?
the level of statistical significance
What is statistical power?
1 - rate of Type II error
What are ways of increasing power and reducing the risk of Type II errors?
1. increasing level of statistical significance
2. bigger N
3. design experiment to maximize effect size
What ethical concerns did the Tuskegee syphilis study raise?
they werent giving people penicillin on purpose
What ethical concerns did the Milgram study raise?
they probably caused permanent damage to those people
What are three ethical principles for conducting communication research?
1. respect for persons
2. beneficence (maximize benefits/minimize harm
What term refers to panel of faculty (investigators) and others who review all research proposals involving human participants (biomedical, behavioral)?
Institutional Review Board
When using the critical value chart for chi square tests do you want your chi square value to be bigger or smaller than the critical value?
Recommended textbook explanations
A First Course in Probability
The Practice of Statistics for the AP Exam
Daniel S. Yates, Daren S. Starnes, David Moore
Mathematical Statistics with Applications
Dennis Wackerly, Richard L. Scheaffer, William Mendenhall
Statistics and Probability with Applications
Daren S. Starnes, Josh Tabor
Sets with similar terms
Final Exam KUANG NEW
PSYC295 - Test 2
Other sets by this creator
Anth 407-Exam 3
Anth 341 Midterm
Com 324 Midterm
Anth 201 FINAL
Other Quizlet sets
Essential Christianity Test 2
Biology Lab Final 2013
Metabolism Handout Vocab