click below
click below
Normal Size Small Size show me how
stats exam 1
| Term | Definition |
|---|---|
| mean | x bar, sensitive to outliers, sum of individuals divided by total (n), the numeric average |
| median | the point that divides a distribution in half, not sensitive to outliers, order from low to high and find middle value to calculate |
| mode | the most frequently occurring value, not sensitive to outliers |
| standard deviation | sx, measures the average distance from the mean of the observations, square root of variance |
| gee whiz graph | misleading, does not start at 0 |
| skew left | tail on left side of graph, mean decreases |
| skew right | tail on right side of graph, mean increases |
| outliers | observations that lie further from the center |
| absolute figure | can be interpreted without any context, has some intrinsic meaning |
| relative figure | has meaning only in comparison to something else |
| normal distribution | data that are symmetrical around their mean in a bell shape |
| n | total individuals/observations |
| Σ | sigma, sum of/add |
| Xi | value of each individual |
| data | pieces of information |
| dataset | spreadsheet/table containing data |
| individuals | observations, cases, objects described by a database |
| variables | a characteristics of an individual, varies (has more than one value or attribute), each column in a dataset represents a unique variable |
| variation | differences across individuals |
| categorical variables | not numeric in a way that permits sensible mathematic operations (ex. political views, grades A, B, C), pie charts, bar graphs |
| quantitative variables | individuals have numeric value (ex. # of states visited, grades 100, 90, 80), histograms, time plots |
| in a spreadsheet... | each column is a variable, each row is an individual |
| how to make a pie chart | list all the values (categories) a variable takes, then count the # of individuals that take on each value |
| how to make a bar graph | bars do not touch, x-axis has categories, y axis has frequency/%, identify the values of the variable, count up # of individuals in each value, draw & label axes and values |
| time plot purpose | allow use to see change and trends over time |
| measures of central tendency (averages) | allow us to find and describe the average or typical tendency in a distribution, mean, median, and mode |
| median location formula | M=(n+1)/2 |
| bimodal | two values of mode tied for most frequently occurring |
| no mode when... | there is not one number that occurs more than the others |
| when will mean, median, and mode be the same value | symmetrical distribution (bell curve) |
| histogram | a vertical bar graph showing the distribution of a quantitative variable, bars touch |
| how to create a histogram | identify range, pick amount of bars (6-20), find bar width, create intervals starting from lowest value, count the # of individuals in each interval, and draw |
| range of a histogram | max-min |
| bar width formula | range/# of bars |
| x axis | variable values/ intervals |
| y axis | frequency, number of individuals |
| spread of a histogram | the min and max intervals |
| sampling goal | generalize to the larger population of interest from samples |
| population | the entire set of individuals/things we are interested in |
| population parameter | # that comes from a population, often impossible to calculate parameters |
| sample | a subset of the pop from which we generalize |
| statistic | a # that comes from a sample |
| simple random sampling | everyone in pop has the same probability of inclusion |
| probability based | each member of pop has an known chance of inclusion in sample |