EXPERIMENTAL DESIGNE, Founder, Importance, Principles, Independent Variable, dependent Variable,

What is Design of Experiment?
Experimental design is a study in statistics which deals with the design and analysis of experiments. It is a way to carefully plan experiments
in advance so that your results are both valid and objective.
Importance of Experimental Design.
Experimental designs are important for determining the cause and effect relationship between dependent variable and independent
variable.

It is a statistical method in which a researcher plans to observe
effect of desired factors on response.
 EXAMPLE
According to the Merck Manual, one factor which can greatly affect the way how a patient responds
to a drug is his/her age. Therefore, we have the risk that the results you are getting might be affected
by age as a confounding variable.




This randomized block design shown above in the image is containing equal blocks of 200 people
from each age group. Where these people are assigned randomly to either the real drug or the plac
ebo. Therefore, in this experiment age is removed as a potential source of variability.
While considering this experimental example we can also say that age is not the only potential source of bring a variability in the experiment.

1. EXPERIMENTAL DESIGN Hoor Bahadur L1F18BSFT0032

2. What is Design of Experiment? Experimental design is a study in statistics which deals with the design and analysis of experiments. It is a way to carefully plan experiments in advance so that your results are both valid and objective. “ “

3. Sir Ronald Fischer introduced this system of experimental design in 1935. He is a well known statistician, eugenicist, evolutionary biologist, geneticist. Founder of Experimental Design HE IS KNOWN AS THE FATHER OF MODERN STATISTICS .

4. Importance of Experimental Design. Experimental designs are important for determining the cause and effect relationship between dependent variable and independent v ariable. It is a statistical method in which a researcher plans to observe effect of desired factors on response.  

5. Design of Experiment Includes; 01 02 03 04 The systematic collection of data. A focus on the design itself, it should be easy and provide with the most efficient and best results. Planning changes to independent variables (input) and the effect on dependent variables also known as response variables. A good experimental design ensures that the results are valid, easily interpreted, and definitive.

6. Principles of Experimental Design Randomization Replication Blocking

7. DESIGNING AN EXPERIMENT Following parameters must be kept in consideration. $75 DETERMINE THE NEED FOR SAMPLE $80 POPULATION OF INTEREST $75 DEFINING THE PROBLEMS AND QUESTION

8. An independent variable is the one which is controlled or changed in a scientific experiment to examine the effects on the dependent variable. A dependent variable is the one which is being measured & tested in a scientific experiment, under specific conditions. Variables Used in Experimental Design Dependent Variable Independent Variable

9. MOST WIDEY USED EXPERIMENTAL DESIGNS CRD Completely Randomized Design FED Factorial experimental Design RBD Randomized Block Design

10. COMPLETELY RANDOMIZED DESIGN

11. DISADVANTAGES Less precise less valid results Chances of error are more ADVANTAGES Flexibility One way analysis Experimental units at random. COMPLETELY RANDOMIZED DESIGN CRD is the most simplest based on the randomization and replication. In CRD all treatments are allocated randomly among the experimental factors. This involves every experimental unit to have an equal probability of receiving a treatment.

12. Implementation of CRD A CRD, completely randomized design is generally implemented by: Listing the treatment levels or treatment combinations . Assigning each level a random number. Sorting the random numbers in order, to produce a random application order for the treatments 01 02 03

13. EXAMPLE OF CRD

14. FACTORIAL EXPERIMENTAL DESIGN

15. FACTORIAL EXPERIMENTAL DESIGN A factorial experimental design is the one which is used to investigate the effect of two or more independent variables on one dependent variable . Factorial experimental design is used to draw conclusions about more than one factor, or variable . The term factorial itself is used to indicate that all possible combinations of the factors are considered in this experimental design. Importance of Factorial Design Use of factorial experiments enables us to examine and determine one-factor at a time. These in return provides us with the most efficient results and the effects of possible interactions between several factors named as independent variables .

16. EXAMPLE Investigate a research work to examine the components for increasing SAT Scores. For the investigation on following work we need the following three components. The above mentioned values are the independent variables. Each of the independent variables is termed as a factor , and each factor comprises of two levels (yes or no). As this experiment consists of 3 factors with 2 levels , this is a 2 x 2 x 2 = 23 factorial design. An experiment with 3 factors and 3 levels would be a 33 factorial design. And an experiment with 2 factors and 3 levels would be a 32 factorial design. SAT intensive class (yes or no). SAT Preparation book (yes or no). Extra homework (yes or no).

17. RANDOMIZED BLOCK DESIGN

18. RANDOMIZED BLOCK DESIGN In randomized block design, the experimental subjects are divided into homogeneous blocks by the researcher And then the treatments are assigned randomly to them. In a good randomized block designed, the variability within blocks should always be greater than the variability between blocks. Advantages of Randomized Block Design Most efficient band best results without any variability. No restriction on the number of treatments Elimination of missing slots is very convenient. No restriction on the replication of treatments.  

19. EXAMPLE According to the Merck Manual, one factor which can greatly affect the way how a patient responds to a drug is his/her age. Therefore , we have the risk that the results you are getting might be affected by age as a confounding variable. This randomized block design shown above in the image is containing equal blocks of 200 people from each age group. Where these people are assigned randomly to either the real drug or the placebo. Therefore , in this experiment age is removed as a potential source of variability. While considering this experimental example we can also say that age is not the only potential source of bring a variability in the experiment.

20. Steps Involved In Experimental Designing 06 Defining problems and questions. Determining the objectives Formulation of hypothesis . Analyze and interpret the Data. Verify the predicted results . 01 02 03 05 06 Execution of Experiment . 04 Brainstorming Verify the predicted results. 08 07

21. Thank you