Send the link below via email or IMCopy
Present to your audienceStart remote presentation
- Invited audience members will follow you as you navigate and present
- People invited to a presentation do not need a Prezi account
- This link expires 10 minutes after you close the presentation
- A maximum of 30 users can follow your presentation
- Learn more about this feature in our knowledge base article
Copy of Studio IV: Restaurant Project
Transcript of Copy of Studio IV: Restaurant Project
(Yes, we know you know, but still :P) Design Of Experiment Lets begin with two examples The Mystery of
Three Romeos and
A Hi! So whats the story like? Will the DOE prove successful in such a situation? Principles Of DOE Randomisation Replication Now, Have you ever wondered what happens inside a popcorn packet? Basic Idea behind the
experiment Key feature of well designed experiment Proper determination of response variable Using multiple comparison test with ANOVA What is ANOVA ? Let me make it more clear with an Example Ho: The mean reaction time for all the groups are the same Test: How the different types of drinks effect the reaction time. basic idea is to find: The variance within blocks
The variance between blocks Example 1: There is a lot of variation within group There is not much variation within groups
but the groups are very different. In this case the type of drink makes a big difference The larger the ratio,the more likely it is that groups have different means(ie. we reject Ho) Calculate the degrees of freedom;
b-df for variance between group
w-df for variance within group The test statistic is
F= variance between groups/
variance within group Analysis Of the experiment So, how do we start making an experimental design? Identifying a response variable Determining the experiemental unit Investigating the important factors We use percentage to standardise results from different brands. Investigating Factors
-Some factors kept constant
-To accoubt for all other extraneous factors, randomisation is done Factors Microwave Cooking Time Brand Of Popcorn Expensive Brand- Cheap Brand- Office Microwave Home Microwave 105 Seconds 135 Seconds Rich Popcorn Common Popcorn Determining the Experimental Unit Statistically significant results are obtained when:
-Units are as similar as possible.
-Units are randomly assigned to treatment combos.
-Large enough sample sizes are used.
-Each bag of popcorn is the experimental unit here. Conslusion: There is NO difference in the response time due to the different beverages. 2 square facorial design in RBD A- Cooking time
ao: 105 sec
a1: 135 sec
bo: Common Brand
b1: Rich Brand Any day to day uses of DOE?
Ah, yes! Thank You :)
Randomisation - rolling of dice
External factors :
1) Dad's temper - didn't allow her to go out of home
2) Bad mood of Renu - didn't perform as expected
Replication - 2 sets of experimental runs What is a factorial design ?
- estimates main effects and interaction effects
3 factors - Naren, Ravi, Deepak
2 levels - absence, presence
Response - whether Renu says Hi or not
Effect - Difference in response DEEPAK - Clear winner!! :D