Day 1:
Definition of essential terms:
1. Population:
- Entire group of observations
- Symbols for population: μ (mu) = mean / σ (sigma) = standard deviation
2. Sample
- Subset (parts) of population → for approximation
- Symbols for sample: X̄ = mean / s = standard deviation
- Selected randomly and independently from populations
Data classification
1. Nominal: only classification
2. Ordinal: classification + ranking
3. Interval scale: measurement with fixed unit an arbitrary starting point ( one
variable)
4. Ratio scale: fixed unit + fixed null point (relationship between two variables)
5. Censored data: one end of interval is not known → drug testing
Or in sample: s
,Day 2
Tips to approach probability question:
1. Analyze the given variables 🡪 let A be the first event… / B be the second event…
2. Write down the info known in numerical value 🡪 convert from %
3. Understand problem given in probability notation 🡪 conditional probability
phrase indication: “of this sample [outcome A], [probability] has also [outcome B]
….
4. Use appropriate equation given
Conditional probability (if NOT mutually independent)
Diagnostic test (*)
,Probability distribution with discrete (fixed) outcomes
1. Uniform probability → equal and unbiased probability for a particular
event
2. Binomial probability → 2 outcomes [e.g: Pr(A) and Pr (NOT A)]
n = sample size / 𝛑 = probability (must be FIXED)
3. Poisson probability → random event occurred independently at
particular time and space
, *Very large (unknown) sample size*
Expected outcome = variance = 𝛍
Day 3
Normal distribution
- Symmetrical
- Continuous variable
- Represented as X N ( μ , σ 2 )
Linear Transformation
Steps to approach a typical normal distribution question
1. Analyze the question first → find out what is μ∧σ given in the qn
2. Express the data in the form of X N ( μ , σ 2 )
3. Perform standardization (see formula below)
Definition of essential terms:
1. Population:
- Entire group of observations
- Symbols for population: μ (mu) = mean / σ (sigma) = standard deviation
2. Sample
- Subset (parts) of population → for approximation
- Symbols for sample: X̄ = mean / s = standard deviation
- Selected randomly and independently from populations
Data classification
1. Nominal: only classification
2. Ordinal: classification + ranking
3. Interval scale: measurement with fixed unit an arbitrary starting point ( one
variable)
4. Ratio scale: fixed unit + fixed null point (relationship between two variables)
5. Censored data: one end of interval is not known → drug testing
Or in sample: s
,Day 2
Tips to approach probability question:
1. Analyze the given variables 🡪 let A be the first event… / B be the second event…
2. Write down the info known in numerical value 🡪 convert from %
3. Understand problem given in probability notation 🡪 conditional probability
phrase indication: “of this sample [outcome A], [probability] has also [outcome B]
….
4. Use appropriate equation given
Conditional probability (if NOT mutually independent)
Diagnostic test (*)
,Probability distribution with discrete (fixed) outcomes
1. Uniform probability → equal and unbiased probability for a particular
event
2. Binomial probability → 2 outcomes [e.g: Pr(A) and Pr (NOT A)]
n = sample size / 𝛑 = probability (must be FIXED)
3. Poisson probability → random event occurred independently at
particular time and space
, *Very large (unknown) sample size*
Expected outcome = variance = 𝛍
Day 3
Normal distribution
- Symmetrical
- Continuous variable
- Represented as X N ( μ , σ 2 )
Linear Transformation
Steps to approach a typical normal distribution question
1. Analyze the question first → find out what is μ∧σ given in the qn
2. Express the data in the form of X N ( μ , σ 2 )
3. Perform standardization (see formula below)
