μ¬ κ°μλΆν° Coursera μ Interaction Designμ΄λΌλ specialization μ΄ μκ²Όλλ° κ·Έ μ€ Designing, Running, and Analyzing Experiments ννΈλ μ΄λκ°μ λ°°μ°κΈ° νλ λ΄μ©μ΄λΌκ³ κ΅μλμ΄ λ£κΈ°λ₯Ό κ°λ ₯ μΆμ²νμ
¨μ§λ§ λΉμμλ λ£μ§ μμλ€(μ£μ‘ν©λλ€β¦). κ·Έλ¬λ€ μμ¦ νκΈ°μ κ²¨μΈ λ°©ν μ¬μ΄ μ½κ°μ νμ΄ μ겨 9 μ£Όμ§λ¦¬ μ½μ€μ§λ§ μ§μ€μ μΌλ‘ λ£κ³ , κ·Έμ€μ μ’ λ¨κΈΈ λ§ν λ΄μ©μ λ¨κ²¨λ³΄λ €κ³ νλ€.
Week1μλ μ€νμ΄ μ νμνμ§μ μ€ν λμμΈμ λν ν° κ·Έλ¦Όμ΄ λμ¨λ€.
μ€νμ΄ μ νμνκ°
μ°λ¦¬κ° μ€νμ ν΄μΌνλ μ΄μ λ λμμΈμ μμΉμ μΌλ‘ μ΄ν΄νκ³ , μ¦λͺ
ν΄μ κ²°κ΅ λμμΈμ κ°μ νλλ° λͺ©μ μ΄ μλ€. κ·Έ μΈ‘μ μ λμμ Performanceκ° λ μλ μκ³ , Preferenceκ° λ μλ μλ€. λν μ€νμ Exploratory ν μλ μκ³ , μλλ©΄ μ’ λ ꡬ체μ μΈ **Hypothesis&**λ₯Ό κ²μ¦νλ λ°©μμΌλ‘ μ§νλ μλ μλ€. κ°μμμλ μΉμ¬μ΄νΈμ λμμΈμ κ°νΈνμ λ μ¬μ©μμ μ νΈλλ₯Ό μμ보기 μν A/B Test λ₯Ό μλ‘ λ€μλλ°, μ¬μ€ μ΄ κ²½μ° μΈ‘μ μ€μ°¨ λλ¬Έμ λ κ°μ κ°μ λμμΈμ λκ³ μ€νν΄λ μ°¨μ΄κ° λνλ μ μλ€. (μ΄λ° ν¨κ³Όλ₯Ό μΈ‘μ νκΈ° μν μ€νμ A/A Testingμ΄λΌκ³ νλ€. Ron Kohavi λμ μ μ λ€ μ€μ μ΄ μͺ½μΌλ‘ μ¬λ°λ λ΄μ©μ΄ λ§λ€)
μ€ν λμμΈμ ν° κ·Έλ¦Ό
κ°μ°μκ° μ¬λΌμ΄λ νλ μμ΄ μμμ μ κ°μν΄μ (μΌλ¨ ν΄μ¦λ₯Ό νκΈ° μν΄) Bullet Point λ‘ μ 리νλ€.
Statistical significance vs. Practical significance
- Statistical significance: mathematical probability that a relationship btw. two or more variable exists
- Eg. Testing preference: We need hypothesis and test statistic. It returns confidence
- Practical significance: actual difference it is estimating will affect a decision to be made
4 Major considerations for every experiment
- Participants
- Sampling: how do they become part of our study?
- purpose: Make composition of sample similar to real
- Probability sampling: consisting randomness
- Non-probability sampling
- Convenience sampling: At researcherβs convenience
- Snowball sampling: Random first sample -> he/she introduce next sample
- Inclusion / Exclusion criteria
- If we experiment usersβs preference between old & new design of web site, we may exclude people who are already familiar with old design
- Apparatus
- What do we need in terms of equipment, space, and other resources
- Remote(same time, different place) / online study(different time and place)
- Do we build something? how to capture data? (human? video? log? )
- Procedure
- What do they actually go through as they come into the study
- There might be some side effect (fatigue effect, learning effect)
- Informed consent is very important!: something similar to IRB
- Donβt forget youβre in charge of their welfare during that time
- Is there any potential risk? Space should be accessible for blind, deaf, etcβ¦
- At the end of study, you have to debrief your study to participants
- You may have seperate MC for proceeding experiment, while other one recording data.
- Design and analysis
- What do they do on each site
P.S
- Week2 λΆν°λ μμ£Ό μ°μ΄λ λΆμμ R λ‘ νλμ© ν΄λ³Έλ€κ³ νλλ°, μΈμ κ° νλ‘λνΈμ λ£μ λλ₯Ό μκ°ν΄μ Python κΈ°λ°μ ν΄λ‘ λ°λΌκ° μλ μμκΉ κΆλ¦¬μ€μ΄λ€. μ΄κ±΄ λ€μ΄λ³΄κ³ μ
λ°μ΄νΈ.
- κ°μλ₯Ό μ‘°κΈ λ€μ΄λ³΄λ μ΄λ€ μ΄λ€ κ²½μ°μλ X λΆμμ λ리μΈμ. X λΆμμ μ΄λ°κ±°μμ. μμΌλ‘ κ°μκ° νλ¬κ°λ€. R λ‘ νλ μΌμ΄λΌκ³ ν΄λ΄€μ μ΄μ°¨νΌ λ°μ΄ν°λ₯Ό μ²λ¦¬ν΄μ λΈλ‘νΉ μ°μ° νλμ λ£λκ±°κ³ , λ³λ‘ λ¬΄κ±°μΈ κ²λ μμ΄μ Python κΈ°λ°μΌλ‘ νλ 건 νμν λ ν΄λ μΆ©λΆν νκ² λ€ μΆμλ€.