Please enable JavaScript.

Coggle requires JavaScript to display documents.

STATISTICS, Make predictions, test hypothesis and make generalizations,…

- - - - Discrete
        
        Nilai yang tepat/bulat (bilangan anak, kereta, pelajar, rumah)
      - Non-Discrete (Selanjar)
        
        Nilai yg boleh dipecahkan (tinggi, berat, suhu, masa)
  - - - Ordinal
        
        Data kategori yang boleh disusun
        
        Tahap Kepuasan, Gred, Tahap Pendidikan
      - Nominal
        
        Data Kategori tanpa susunan
        
        Jantina, Bangsa, Warna, Negeri
- - - - Mean
        
        Purata x̄ = ( Σ xi ) / n
        
        Sensitif kepada outliers
      - Median
        
        (n+1) / 2
        
        Nilai di tengah data yang telah disusun
        
        Kurang sensitif kepada outliers
      - Mode
        
        Nilai yang paling kerap berlaku
        
        Boleh ada lebih dari satu mod
    - - Range
        
        nilai max - nilai min
      - Quartiles (Q1, Q2, Q3)
        
        Q1- 25% x n
        
        Q2 - 50% x n
        
        Q3 - 75% x n
      - IQR
        
        Q3 - Q1
      - Standard Deviation
        
        S = √S²
      - Outliers
        
        Outlier kiri --> Q1 - (1.5x IQR)
        
        Outlier kanan--> Q3 + (1.5x IQR)
      - Variance
        
        S²= ∑ (x-x̄)² / (n-1)
        
        Small variance - more consistent
        
        bigger variance - less consistent
    - - Skewness
        
        Positive (Right)
        
        ekor ke kanan
        
        Negative (Left)
        
        Ekor ke kiri
        
        Symmetric
        
        Seimbang
        
        Normal Distribution (bell curve)
        
        Mean, median, and mode are all equal
        
        Total area under the curve = 1 (100%)
        
        Key Parameters:
        
        μ (mu) = mean (average)
        
        σ (sigma) = standard deviation
        
        σ² = variance
        
        Important Formulas:
        
        NORMAL DISTRIBUTION FORMULA
        
        1 more item...
        
        Z-SCORE FORMULA (STANDARDIZATION)
        
        1 more item...
        
        PROBABILITY FORMULA
        
        2 more items...
      - Kurtosis (kepuncakan)
        
        Leptokurtic (lebih tinggi drpd normal)
        
        Platykurtic (lebih rendah drpd normal)
        
        Mesokurtic (normal)
  - - - SAMPLING DISTRIBUTION
        
        Based on central theorem
        
        Types of inferential statistics
        
        Estimation
        
        Point Estimation
        
        Interval Estimation
        
        Correlation
        
        Hypothesis testing
        
        H0,H1
        
        Regression
        
        Foundation for all inferential methods
        
        Population → Sample → Sampling Distribution
        
        Important Relationships to Understand:
        
        The mean of sample means equals population mean
        
        μx̄ = μ
        
        Standard deviation of sampling distribution (SE of Mean)
        
        σx̄ = σ/√n
        
        (How precise our samples are)
        These two relationships are the foundation for:
        
        2 more items...
        
        σ = population standard deviation
        
        n = sample size
        
        Large size of sample N≥30 = normally distributed sampling
        
        makin besar sample, graf akan menghampiri normal
        
        COLLECTION OF SAMPLE MEANS OF A PARTICULAR SIZE (N) THAT CAN BE OBTAINED FROM A POPULATION
        
        FORMULA
        
        MEAN
        
        POPULATION
        
        μ = ΣX / N
        
        (μ) = Population
        
        (ΣX) = Sum of all values
        
        N = population size
        
        SAMPLE
        
        (x̄) = (ΣX) / N
        
        (x̄) = Sample
        
        (ΣX) = Sum of sample values
        
        N = sample size
        
        DISTRIBUTION OF SAMPLE MEANS
        
        μx̄ = μ
        
        (μx̄) = Distribution of Sample Means
        
        (μ) = Equals population mean
        
        STANDARD DEVIATION/
        STANDARD ERROR
        
        POPULATION
        
        (σ) = √(SS/N)
        
        (σ) = Population
        
        √(SS/N) = where SS is sum of squares
        
        SAMPLE
        
        (s) = √(SS/(n-1))
        
        (S) = Sample
        
        √(SS/(n-1)) where n-1 is degrees of freedom
        
        DISTRIBUTION OF SAMPLE MEANS
        
        (σx̄) = σ/√n
        
        σ²x̄ = σ²/n
        
        (variance of sampling distribution)
        
        APPLICATION OF THE CENTRAL LIMIT THEOREM
        
        POPULATION DISTRIBUTION
        
        Z = (X - μ) / σ
        
        SAMPLING DISTRIBUTION
        
        Z = (X - μ) / (σ/√n)
        
        When we want to standardize our sampling distribution (get Z-scores), we use:
        
        2 more items...