independent_t_test

# independent_t_test - Dr. King Psychological Statistics...

This preview shows pages 1–2. Sign up to view the full content.

Dr. King Psychological Statistics Hypothesis Testing Using Two Independent Samples - The Independent-Groups t-Test The Independent t-Test (also called the independent-measures or independent-groups or independent-samples t-test): The independent t-test is used to compare the means of two populations or of two treatment conditions. It is used when the experiment has one independent variable (IV) with two levels. Ideally, subjects are randomly assigned to the two groups (a true experimental design ), but they may also be self-selected or self-assigned or come pre-assigned "by nature" (a quasi-experimental design ). This between-subjects design is also called between groups, independent measures, or if subjects are randomly assigned a completely randomized design . The following assumptions must be met: 1) The samples should be selected by random sampling if inferences are to be made back to the populations. Without random sampling, random assignment is critical. Studies done without either random sampling or random assignment are of dubious value. 2) Each sample (group) consists of independent observations. 3) The two populations represented by the samples must be normally distributed. (Note: the independent t-test is robust to violations of this assumption provided the design is balanced and the groups are reasonably large.) 4) The two populations represented by the samples must have equal variances. This assumptions is called homogeneity of variance . (Note: there is a "work-around" called the unpooled variance t-test when this assumption fails. The version of the t-test presented here is called the pooled or pooled variance t-test .) The Dependent t-Test (also called the correlated-groups, correlated-samples, or related-samples t-test): The dependent t-test is used when you wish to compare the performances of a single sample of subjects that has been tested twice under two different levels of an IV. This creates a within-subjects or repeated-measures design . The dependent t-test is also used when scores in the two groups are correlated due to matching, a so-called matched-groups or matched-subjects design . The dependent t-test will be covered in detail in a future handout. It makes the

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
This is the end of the preview. Sign up to access the rest of the document.

## This note was uploaded on 05/22/2009 for the course DIP pp taught by Professor Pp during the Spring '09 term at A.T. Still University.

### Page1 / 4

independent_t_test - Dr. King Psychological Statistics...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online