Independent samples T-tests Flashcards
For between subject designs
how do t tests help us
tell us how likely we are to obtain the observed difference between conditions if null hypothesis is true
What does the T statistic represent?
t = variance explained by our IV / unexplained variance
How do we test for normality of assumptions?
Shapiro-Wilk Test
What is a One Sample T-test
compares data from your experiment with one single number
- e.g. did your participants score significantly higher than the national average
- one dependent variable and no manipulation
What are the assumptions for a One Sample T-test
- data are independent
- data are continous
- data are normally distributed
What is a non parametric alternative for the One Sample T Test
one sample wilcoxon signed rank test
What are the assumptions for an Independent Samples T test
- data are independent
- data are interval or ratio
- N of over 12
- data are normally distributed
- homogeneity of variance
What is Homogeneity of Variance
Is the variance in condition 1 like the variance in condition 2
Look at the descriptive statistics
Similar SD / SEM / Confidence Intervals in each condition?
Visualise the data
Observe the graphs (histogram/box plot)
Are they roughly the same shape?
Run a homogeneity of variance test
Levene’s Test
What is the test we run to test for Homogeneity of Variance
Levene’s test
What are Q-Q plos
Quantile-Quantile plots
- ordered data (like for median and inter quartile range)
sectioned into quantiles and plotted
- Homogenous data will fall roughly on the diagonal line
What’s the non parametric alternative for an Independent Samples T test?
Mann Whitney U test
What is the difference between a one sample and indendependent sample t tests
One sample T test compares one sample to a single value
Independent Sample T test compares the means of two groups or conditions