click below
click below
Normal Size Small Size show me how
stats miderm form
| Name | fomula |
|---|---|
| Mean Absolute Deviation | MAD = (โ |x_i - xฬ| ) / n |
| Median Absolute deviation | Median( ๐ฅ1 โ ๐ , ... , ๐ฅ๐ โ ๐ ) |
| variance | ๐ 2 = (๐ฅ1 โ ๐ฅ 2 )+ โฏ + (๐ฅ๐ โ ๐ฅ 2 )/ ๐ โ 1 |
| standard deviation | ๐ = sqrt((๐ฅ1 โ ๐ฅ 2 )+ โฏ + (๐ฅ๐ โ ๐ฅ 2)/๐ โ 1) |
| Rule of Thumb 1 | Observations are considered outliers if they are more than 3 standard deviations away from the mean to the left or the right. In other words, if they are either: โข Less than าง ๐ฅ โ 3 ร ๐ โข Greater than าง ๐ฅ + 3 ร ๐ |
| Rule of Thumb 2 | Observations are considered outliers if they are either: โข Less than ๐1 โ 1.5 ร ๐ผ๐๐ โข Greater than ๐3 + 1.5 ร ๐ผ๐๐ |
| Five Number Summary | Minimum, 1st quartile, median, 3rd quartile, and maximum |
| Boxplot | introduced by Tukey in 1977, are based on percentiles and give a quick way to visualize the distribution of data. |
| Scatterplot | graphical display of the relationship between two numeric variables |
| Positive | response tends to increase |
| Negative | response tends to decrease |
| Neither | no obvious change in response |
| Linear | response tends to change(increase/decrease) at about the same rate across all values of explanatory |
| Curved | rate at which response changes depends on value of explanatory |
| Covariance | measure of joint variability between two numeric variables |
| Correlation | measure of the strength and direction of the linear relationship between two numeric variables |
| Marginal Distribution | In a contingency table, is the distribution of either variable alone |
| Distribution | is a list of all the possible values of the variable and the relative frequency of each value. |
| Conditional Distribution | shows the proportion (or percentage) of observations in each response category given that an observation falls into a specific explanatory group |
| Side-By-Side Bar Graph | It is a graphic way to visualize the relationship between two categorical variables |
| Simpson's Paradox | a phenomenon that occurs when there appears to be a trend in a set of data, but the trend disappears or reverses when the data is separated |
| Random Experiment | any process that leads to one of several potential results which cannot be predicted |
| Trial | an attempt of a random experiment |
| Outcome | result of a random experiment |
| Event | any combination of outcomes, typically shown as a capital letter or word |