1. Experimental Design Ch 12

2. Can you prove a cause and effect relationship. Explain
Can you prove a cause and effect relationship? Explain. Yes, with a well-designed, well-controlled experiment. (control, replication, randomization)

3. The ONLY way to show cause & effect is with a well-designed, well-controlled experiment!

4. 3: Fertilizer types A, B, & C
Example 1: A farm-product manufacturer wants to determine if the yield of a crop is different when the soil is treated with three different types of fertilizers. Fifteen similar plots of land are planted with the same type of seed but are fertilized differently. At the end of the growing season, the mean yield from the sample plots is compared.
Experimental units?
Factors?
Levels?
Response variable?
How many treatments?
Plots of land or soil
Type of fertilizer
3: Fertilizer types A, B, & C
Crop yield 3

5. Why is the same type of seed used on all 15 plots?
A farm-product manufacturer wants to determine if the yield of a crop is different when the soil is treated with three different types of fertilizers. Fifteen similar plots of land are planted with the same type of seed but are fertilized differently. At the end of the growing season, the mean yield from the sample plots is compared.
Why is the same type of seed used on all 15 plots?
What are other potential extraneous variables?
Does this experiment have a placebo? Explain
It is part of the controls in the experiment.
To control the factor of type of seed.
Type of soil; amount of water, sunlight, etc.
No, one would compare the three types of fertilizers
Weather, type of soil, amount of water, etc.
NO – a placebo is not needed in this experiment

6. *Specifically describe the random assignment*
Experiment Designs
Completely randomized – all experimental units are allocated at random among all treatments
Experimental units
Treatment 1
Treatment 2
Treatment 3
Compare
Response
Variable
Random Assignment
*Specifically describe the random assignment*
Ex: number all experimental units and using a random number generator select random units

7. Completely randomized design
Treatment A
Treatment B
Treatment C
Treatment D
Randomly assign experimental units to treatments
Completely randomized design

8. *Specifically describe the random assignment*
Randomized block – units are blocked into groups and then randomly assigned to treatments
Compare
Response
Variable
Experimental units
Group1
Treatment 1
Treatment 2
Treatment 3
Group2
Random Assignment
*Specifically describe the random assignment*
Ex: number all experimental units and using a random number generator select random units

9. Randomized block design
Treatment B
Treatment A
Treatment A
Treatment B
Put into homogeneous groups
Randomly assign experimental units to treatments
Randomized block design

10. Where does randomization happen in each of the previous designs?
Completely Randomized- at the beginning
Randomized Block- after you block them (within each group)

11. Experiment Designs
Number all 15 plots of land and using a random number generator select 5 numbers for each treatment

12. Matched pairs - a special type of randomized block design
match up experimental units according to similar characteristics & randomly assign on to one treatment & the other automatically gets the 2nd treatment
have each unit do both treatments in random order

13. Pair experimental units according to specific characteristics.
Treatment A
Treatment B
Next, randomly assign one unit from a pair to Treatment A. The other unit gets Treatment B.
Pair experimental units according to specific characteristics.
This is one way to do a matched pairs design – another way is to have the individual unit do both treatments (as in a taste test).

14. 12) Confounding variable – the effect of the confounding variable on the response cannot be separated from the effects of the explanatory variable (factor)
Suppose we wish to test a new deodorant against one currently on the market.

15. Treatment & group are confounded
New deodorant
Old deodorant
One group is assigned to treatment A & the other group to treatment B.
Old deodorant
New deodorant
Confounding does NOT occur in a completely randomized design!
Treatment & group are confounded

16. Yes b/c a treatment is imposed
Example 2 Four new word-processing programs are to be
compared by measuring the speed with which tasks can
be completed. 100 volunteers are randomly assigned to
one of the 4 programs and their speeds are measured.
Is this an experiment? Why or why not?
b) What type of design is this?
c) Name the factors and levels.
d) How many treatments?
e) What’s the response Variable?
Yes b/c a treatment is imposed
Completely randomized
1 factor (program) with 4 levels 4
Processing speed

17. What type of design is this? Why use this method?
Example 3:Suppose a manufacturer wants to test a new fertilizer against the current one on the market. Each plot is divided into 2 parts, one half of the each plot is treated with the current fertilizer and the other one with a new fertilizer. Wheat is planted and the crop yield is measured.
What type of design is this? Why use this method?
When does randomization occur?
Matched pairs(randomized block), because you want to control as many confounding variables as possible (terrain, location)
Yes, a treatment was imposed
Completely randomized
one factor, word processing program & 4 levels, the four new programs
Speed at which standard tasks can be done
Select which half gets what fertilzer

18. Example 4: What are the effects of repeated exposure to an advertising message? An experiment investigated this question on undergraduate students. All subjects viewed a 40 minute television program that included ads for a 35 mm camera. Some subjects saw a 30-second commercial; others, a 90 second version. The same commercial was repeated either 1, 3, or 5 times during the program. After viewing, all of the subjects answered questions about their recall of the ad, their attitude toward the camera, and their intention to purchase it.
Yes, a treatment was imposed
Completely randomized
one factor, word processing program & 4 levels, the four new programs
Speed at which standard tasks can be done

19. recall of ad, attitude and intention to purchase camera
What is the response variable(s)?
Name the factor(s) and the number of level(s) for each
How many treatments?
Draw a diagram.
recall of ad, attitude and intention to purchase camera
2 factors( length of ad, and repetition)
Length has 2 levels, Repetition has 3 levels
2x3=6

20. Random Assignment- Number all students and using a random # generator on a calculator select students for each treatment

22. Is there another way to reduce variability?
Randomization reduces bias by spreading any uncontrolled confound ing variables evenly throughout the treatment groups.
Is there another way to reduce variability?
Blocking also helps reduce variability.
Variability is controlled by sample size. Larger samples produce statistics with less variability.

23. The primary purpose of:
Randomization is to reduce bias
Blocking is to reduce variability