Chapter 13 - from different treatments. For example...

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

View Full Document Right Arrow Icon
Chapter 13 Experiments ActivStats: 13 Read: Chapter 13 OBSERVATIONAL STUDY - a study based on observed data with no manipulation of factors employed (for example a survey ). Usually used to estimate population parameters Retrospective – data consist of past outcomes Prospective – data will consist of future outcomes EXPERIMENTS - a study based on manipulation of factors (treatments) employed and analysis of observed responses . Usually used to determine causal relationship. A researcher must identify at least one explanatory variable, called factor, and its values ( levels) to be assigned. Any combination of different factors and their levels is called a treatment. A researcher observes responses to different treatment. Principles of Experimental Design. 1. Control. C ontrol sources of variation other than coming
Background image of page 1

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

View Full DocumentRight Arrow Icon
Background image of page 2
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: from different treatments. For example blinding either subjects or those who evaluate responses or both single-blinding double-blinding Placebo- fake treatment 2. Block. Block or match subjects to reduce variability of responses to the same treatment. 3. Randomize. An experiment requires a random assignment of experimental units to treatments. Randomization allows to equalize the effects of uncontrollable sources of variation. completely randomized design- all experimental units have the same chance to receive any treatment randomized block design- randomization occurs only within blocks 4. Replicate. Replicate over as many subjects as possible and replicate entire experiment with different groups of subjects...
View Full Document

Page1 / 2

Chapter 13 - from different treatments. For example...

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

View Full Document Right Arrow Icon
Ask a homework question - tutors are online