basic statistics

Statistics

concepts

1. central tendency

• mean(average): dividing the sum of data by the count of the data
• median: 50% of a quantile or the data in the middle of the whole data
• mode: the frequent count of data
• quantile: 25%, 50%, 75% of the whole data

1. measurement of distribution

• variance: how widely the whole data distribute
• std(standard deviation): the square root of variance

1. coefficient

• correlation coefficient: the size of the relation between two variances / range must be within [-1, 1].
  the degree of the change to one variance as another one also changes
• covariance: the degree of how far both two variances are distant from each mean value / when one variance is in faraway point from its mean, how far another variance is distant from its mean

1. regression

• Linear regression => regressional coefficient (the size that the independent variance impacts the dependent variance)

  important: minimizing the errors of data

• for the prediction