Lec14.Design

Lec14.Design - I ntr oduction to Design of Exper iments...

Info iconThis preview shows pages 1–12. Sign up to view the full content.

View Full Document Right Arrow Icon

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

View Full DocumentRight Arrow Icon

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

View Full DocumentRight Arrow Icon

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

View Full DocumentRight Arrow Icon

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

View Full DocumentRight Arrow Icon

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

View Full DocumentRight Arrow Icon

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

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

Unformatted text preview: I ntr oduction to Design of Exper iments KNNL Ch. 15 Design Ter minology • Factor is an explanatory variable in the experiment (independent variable) • Factor levels are the forms of the factor used in the experiment • A treatment is a combination of factor levels • Experimental unit is the object a treatment is assigned to What is an Exper iment? • In a (comparative) experimental study , randomization is employed to assign a set of treatments to the experimental units, and the observed outcomes among the treatment groups are compared to assess treatment effects. • Cause and effect relationships between the experimental factors and the outcome or response variable can be established. Exper imental Studies vs. Obser vational Studies • In Experimental Studies treatments are randomly assigned to experimental units. • In Observational Studies treatments are not randomly assigned to experimental units due to ethical or practical reasons. • Studies can be mixed (both experimental and observational) when multiple factors are involved in the study. Causation vs. association • In regression, we often cannot randomize the predictor to the experimental units. Thus, in regression analysis we can often only conclude an association between two variables. Basic Concepts • The design of an experiment includes a description of the following: • Explanatory factors • Treatments • Experimental units • Response or outcome measured on experimental units • Procedure by which treatments are randomized to experimental units Example: Quick Br ead • An experiment is conducted to study the effect of baking temperature on the volume of a quick bread from a package mix. • Four oven temperatures – low, medium, high, and very high – were randomly assigned to two package mixes each. • Eight package mixes were used in this experiment. A Completely Randomized Design • This design structure is called a completely randomized design ; each treatment (oven temperature) has an equal chance to be assigned to each of the experimental units (8 package mixes). Randomization • Technique introduced by Sir Ronald A. Fisher in the early 1920’s • Purpose of randomization is to obtain a random sample from the population of experimental units. • This will reduce bias, and validate assumptions for the experiment (independent sample) H ow to Randomize # define treatments (here are two ways) my.trtmts = c("low","med","high","very high") my.trtmts = c(1,2,3,4) # obtain a random ordering of 4 treatments to # assign to the 8 experimental units sample(rep(my.trtmts,2)) _____________________________________________ ______...
View Full Document

This note was uploaded on 04/17/2010 for the course STSCI 3200 taught by Professor Sullivan during the Spring '10 term at Cornell.

Page1 / 42

Lec14.Design - I ntr oduction to Design of Exper iments...

This preview shows document pages 1 - 12. Sign up to view the full document.

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