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;
20 Cards in this Set
- Front
- Back
comparing a proportion to a hypothesized value
|
binomial test
|
|
comparing a proportion to a hypothesized value if sample size is large
|
X2 goodness-of-fit test with two categories
|
|
comparing frequency data to a hypothesized value when data are approximately normal
|
one-sample t-test
|
|
comparing median to a hypothesized value when data are not normal (even after transformation)
|
sign test
|
|
comparing frequency data to a discrete probability distribution
|
X2 goodness-of-fit test
|
|
comparing data to the normal distribution
|
Shapiro-Wilk test
|
|
categorical explanatory variable and categorical response variable
|
contingency analysis
|
|
numerical explanatory variable and categorical response variable
|
logistic regression
|
|
numerical explanatory variable and numerical response variable when data are bivariate normal
|
linear and nonlinear regression, linear correlation
|
|
numerical explanatory variable and numerical response variable when data are bivariate normal
|
Spearman's rank correlation
|
|
test differences between two means for two treatments with independent samples assuming normal distribution
|
Two-sample t-test
|
|
test differences between two means for two treatments with independent samples assuming normal distribution but unequal variances
|
Welch's t-test
|
|
test differences between two means for two-treatments with independent samples assuming not normal distributions
|
Mann-Whitney U-test
|
|
test differences between two means for two treatments with paired data assuming normal distribution
|
paired-t-test
|
|
test differences between two means for two treatments with paired data assuming not normal distribution
|
sign test
|
|
test differences between two means for more than two treatments assuming normal distribution
|
ANOVA
|
|
test differences between two means for more than two treatments assuming not normal distribution
|
Kruskal-Wallis test
|
|
hypothesis testing in which a computer Is used to mimic repeated sampling from an imaginary population whose properties conform to those stated in the null hypothesis. The frequency distribution of test statistics calculated on the simulated samples gives a null distribution of the test statistic.
|
simulation
|
|
generate the null distribution for a measure of association between two variables by randomly rearranging the observed values for one of the variables. The frequency distribution of test statistics calculated on many randomized data sets gives the null distribution of the test statistic.
|
randomization
|
|
calculating standard errors of estimates and confidence intervals for parameters. It uses resampling from the data to approximate the sampling distribution for an estimate.
|
bootstrapping
|