Chapter 8 - Hypothesis Testing (Two-Sample) Flashcards Preview

Statistics > Chapter 8 - Hypothesis Testing (Two-Sample) > Flashcards

Flashcards in Chapter 8 - Hypothesis Testing (Two-Sample) Deck (10):

Two-sample hypothesis testing

- in a two-sample hypothesis-testing problem, the underlying parameters of two different populations, neither of whose values are known, are compared
- different tests are available, depending on study design


Longitudinal or follow-up study

- the same group of people is followed over time
- also, this represents a paired-sample design because each person is used as his or her own control


Cross-sectional study

- the participants are seen at only one point in time
- this study represents an independent sample design because two completely different groups of people are being compared
- a cross-sectional study is also less expensive than a follow-up study


Types of two-sample data

- paired samples
- independent samples


Paired samples

- when each data point in the first sample is matched and is related to a unique data point in the second sample
- may represent two sets of measurements on the same people
- or, on different people who are chosen on an individual basis using matching criteria


Independent samples

- when the data points in one sample are unrelated to the data points in the second sample


Two-sample t-test for independent samples

- the two-sample t-test for independent samples is used to test hypotheses of independent samples


F distribution

- not a symmetric distribution
- positively skewed
- family of distributions that depend on degrees of freedom


Two-sample t-test for independent samples with unequal variances

- since variances are unequal, we shouldn’t use a pooled estimate of variance
- instead, the traditional estimates for variances are used


Estimation of sample size for two-sample hypothesis tests

- sample size estimation is more difficult for two-sample tests of hypotheses because there are two samples sizes to consider
- for some study designs, estimating equal sample sizes is appropriate, but some health conditions (eg. a rare disease), it may be unrealistic to obtain equal sample sizes