Please enable JavaScript.
Coggle requires JavaScript to display documents.
DESCRIPTIVE STATISTIC - Coggle Diagram
DESCRIPTIVE STATISTIC
-
-
MEASURE OF LOCATION
MEDIAN
- For OOD number, median is the middle no
- For EVEN number, median is the mean of two middle no
- Median used for - RATIO, INTERVAL, ORDINAL data
- MEDIAN =MEDIAN(data range)
-
-
When to use MEDIAN instead of MEAN?
- When we have outlier or extreme data, use MEDIAN
-
TOOLS
-
- Enter Input Range
- Labels (optional)
- Check Summary Statistics box
-
If MULTIPLE, SEPERATE data set
INTRODUCTION
Why sample - obtain info, get result and do VALID INFERENCES about the population
-
-
CHEBYSHEV'S THEOREM
k>1, because 1-1/k kuasa 2
k= 2, at least 3/4 or 75% of the data lie within two SD of mean
k=3, at least 8/9 or 89% of data lie within three SD of mean
-
-
MEASURE OF SHAPE
SKEWNESS
-
- Distribution off to the RIGHT, POSITIVELY SKEWED
- Distribution off to the LEFT, NEGATIVELY SKEWED
-
- CS is NEGATIVE for left-skewed data
- CS is POSITIVE for right-skewed data
- |CS| > 1 suggests HIGH DEGREE of skewness.
- 0.5 ≤ |CS| ≤ 1 suggests MODERATE skewness.
- |CS| <0.5 suggests RELATIVE SYMMETRY.
KURTOSIS
Peakedness (HIGH, NARROW) / flatness (SHORT, FLAT-TOP) of HISTOGRAM
-
- CK<3 - data is FLAT , WIDE degree of dispersions
- CK >3 - data us PEAK, less dispersions
-
-
DISPERSION
-
Key measures
RANGE
- Simplest
- Difference MAX and MIN value
=MAX (data range) - MIN (data range)
- Often use in small data
-
VARIANCE
- AVERAGE of SD
- Population =VAR.P (data range)
- Sample =VAR.S (data range)
- Difference is DENOMINATOR
STANDARD DEVIATION
- Square root of Variance
- Population =STDEV.P (data range)
- Sample = STDEV.S (data range)
MEASURE OF ASSOCIATION
COVARIANCE
- Measure of LINEAR association between 2 VARIABLE
- Population =COVARIANCE.P(array 1, array 2)
- Sample =COVARIANCE.S(array 1, array 2)
CORRELATION
- Measure of the linear relationship between two variables, X and Y, which DOES NOT DEPEND on the units of measurement.
- Measured by the correlation coefficient, also known as the PEARSON PRODUCT MOMENT CORRELATION COEFFICIENT
=CORREL(array 1, array 2)
Positive Cerrelation, graf menaik, negatif (menurun)
No correlation ( bersepah), Nonlinear relay with no linear correlation (graf bentuk U)
MIDRANGE
- Average GREATEST and LOWEST value
- Only use TWO PIECES DATA
- ROUGH ESTIMATE than mean
- Use in SMALL SAMPLE size
- Midrange =(MIN data + MAX data)/2
MEASURE OF LOCATION
- Kira MEAN, MEDIAN MODE
- Buat frequency, relative frequency, cumulative frequency
- 90% cumulative tunjuk area mana