Keep calm and be normal
_________ is the extent to which scores in a dataset tend to vary around the mean.
Standard Deviation
What does the value in parentheses represent?
t(129) = 3.48, p = .04
Degrees of freedom
What does ANOVA stand for?
Analysis of Variance
A _______ indicate the direction and strength of a relationship between two variables.
Correlation
In which case is our risk of making a Type 1 error greatest?
a) when we set α = .10
b) when we set α = .05
c) when we set α = .01
when we set α = .10
Under the standard normal curve, what percentage of our data falls between -2 SD and +2 SD?
95.4%
Which statistical test can we perform to compare a sample mean to a population mean, when our population standard deviation is unknown?
One sample t-test
DOUBLE JEOPARDY
An ANOVA compares the variability due to _________, to the variability due to ___________
groups (IV), error (within groups)
Alex wanted to determine if one's self efficacy predicts hours spent studying for a class. What type of statistical analysis could he perform to answer his question?
Note: Self efficacy is measured from a sum score of a 10 item self efficacy measurement scale.
Simple linear regression
In the t test, the degrees of freedom are a function of_________
Sample size
In which of the following cases will we generate a greater z score
A) When raw score = 20, mean = 10, SD = 30
B) When raw score = 20, mean = 15, SD = 30
In case A:
when raw score = 20, mean =10, SD = 30
A parameter indicates information about a ________, whereas statistic indicates information about a ________.
Population, sample
A parameter indicates information about a population, whereas statistic indicates information about a sample.
If we ran a 2 x 2 factorial ANOVA, and found a significant interaction, what would be our next step to dissect and understand the interaction?
A “statistically significant” result is defined as an outcome that has a ______ probability of occurring if the ______ hypothesis is true.
A “statistically significant” result is defined as an outcome that has a SMALL probability of occurring if the NULL hypothesis is true.
Calculate the standard error when the population mean = 30, population standard deviation = 50, and the sample size = 100
Standard Error = pop. standard deviation / sqrt N
Standard Error = 50 / (sqrt of 100) = 50/10 = 5
Standard error = 5
This type of error indicates a failure to reject the null hypothesis, when the null hypothesis is actually false.
Type II error
There is less error variability in a repeated measures design.
Imagine we ran a multiple linear regression examining whether high-school GPA and SAT score predicted current college GPA.
Let's say we obtained an unstandardized regression coefficient of SAT score (bSAT = 1.34, p < .05). How would we interpret this regression coefficient?
For every one unit increase in SAT score, the model predicts a corresponding increase of 1.34 in college GPA, controlling for high-school GPA.
What is the purpose of running post hoc comparisons after conducting a one-way ANOVA?
To determine which groups are significantly different from each other
DOUBLE JEOPARDY
The theoretical probability distribution of a sample statistic ( e.g., sample mean) for all possible samples of a given size from a single population is referred to as _____________.
Sampling Distribution
The __________ test determines whether there is ______________, or whether two groups differ significantly in their variances.
Levene's Test, homogeneity of variance
Jess was interested in whether social media use and year in high school influence mental health. She interviewed an entire cohort of freshman students on their social media use (yes or no use) and mental health. She repeated this interview for three additional years, following the same cohort of students.
What statistical analysis can Jess perform to determine whether social media use and year in high school influences mental health?
2 x 4 Mixed Factorial ANOVA
_________ conveys information about how two variables vary together but, unlike a correlation, it is not scaled.
Covariance
Dividing the alpha level by the number of statistical comparisons being made is called ______.