Chapter 8 Hypothesis Testing, Two-Sample Inference
8.1 longitudinal and cross-sectional study
In a longitudinal or follow-up study the same group of people is followed over time.
In a cross-sectional study, the participants are seen at only one point in time.
Example: The relationship between oral contraceptive (OC) use and blood pressure in women.
Longitudinal study
- Start with women who are not using OC and measure baseline blood pressure.
- Follow them over time and identify those who begin using OC.
- Measure their blood pressure again at follow-up.
- Compare the same women before and after OC use.
Cross-sectional study
- Select one group of OC users and another group of nonusers.
- Measure blood pressure in both groups at the same time.
- Compare blood pressure between the two groups.
The longitudinal study represents a paired-sample design because each woman is used as her own control. The cross-sectional study represents an independent-sample design because two completely different groups of women are being compared.
The paired samples may also represent measurements on different people who are chosen on an individual basis using matching criteria, such as age and sex, to be very similar to each other.
Comparison
| Longitudinal (follow-up) | Cross-sectional | |
|---|---|---|
| Subjects | Same individuals over time | Two different groups at one time point |
| Conclusion | More definitive | Only suggestive |
| Confounding | Minimized (same person controls for individual factors) | High risk (e.g., OC users may weigh less, confounding BP comparison) |
| Control group | Needed to rule out other causes of change over time | — |
| Cost | More expensive | Less expensive; often more feasible |
| Statistical test | Paired-sample | Independent-sample |