Please enable JavaScript.
Coggle requires JavaScript to display documents.
Chapter 10: The t Test for 2 Independent Samples - Coggle Diagram
Chapter 10: The t Test for 2 Independent Samples
independent-measure research design or between-subjects design
uses a completely separate group
allows to make a comparison
involves two separate samples need a special notation to specify
goal is to evaluate the mean difference between two pops
subtract the 2 means
Repeated-measures research design or a within-subjects design
two sets of data are obtained from the same group of participants
single-sample t statistic
and the new formula as the
independent-measure t statistic
t= actual difference between sample data and the hypothesis/expected difference between sample data and hypothesis w/ no treatment effect
standard error in denominator measures how much error is expected between the sample statistic and the pop parameter
M1 - M2
pooled variance is used for correcting the bias in the standard error by combining the 2 sample variances into a single value
directional hypotheses and one-tailed tests
3 assumptions that should be satisfied before you use independent-measure t formula for hypothesis testing:
observations within each sample must be independent
two pops from which the samples are selected must be normal
two pops from which the samples are selected must have equal variances
homogeneity of variance
violating the homogeneity can negate any meaningful interpretation of the data
Hartley's F-Max test
confidence intervals can be alternative method for measuring and describing the size of the treatment effect
reports typically present the descriptive statistics followed by the results of the hypothesis test and measures of effect size
a factor that contributes to size of standard error is the amount of variance in the sample data
