Term | Definition |
Statistics | The science of collecting and analyzing data and drawing conclusions |
Variability | Natural differences that exist in data. It is universal. |
Population | Entire collection of individuals/objects which info is desired. |
Census | Performed to gather information about a population. |
Sample | A subset of the population selected for study. |
Descriptive Statistics | Methods of organizing and summarizing data. |
Inferential Statistics | Making generalization from the sample to the population. |
Variable | Any characteristics whose value may change from one individual to another |
Data | The values for a variable from individual observations. |
Categorical Variables | Identifies basic differentiating characteristics of a population. Quantitative. |
Numerical Variables | Observations/measurements that can be averaged. |
Discrete Numerical Variables | Isolated points along the number line. (counts) |
Continuous Numerical Variables | Can be any value on interval. (Measurements, amounts...) |
Confounding Variable | Related to both group membership and the response variable of interest. |
Simple Random Sampling | Everyone has an equal chance of being selected. Population representation is not guaranteed. |
Sampling Frame | List of all individuals/objects in population. |
Stratified Random Sampling | Broken up into non-overlapping categories and then do simple random sample. |
Cluster Sampling | Divided into non-overlapping groups call clusters. |
Systematic Sampling | Use rule/method to collect sample. |
Bias | The tendency for samples to differ from population in some systematic way. |
Selection Bias | Undercoverage. |
Convenience Samping | Easily available/convenient group. |
Measurement/Response Bias | Systematic differences (ex: improperly calibrated scale) |
Non-Response Bias | Sample doesn't respond. |
Response Varible | Not controlled. Variable that is measured. (Independent) |
Explanatory Variables | Controlled values. (Dependent) |
Extraneous Variables | Not an explanatory variable but can affect results. |
Direct Control | Holding extraneous variables constant so effects are not confounded with those of the experimental conditions. |
Blocking | Process by which an extraneous variable's effects are filtered out. |
Randomized Block | Units are blocked into homogeneous groups and then randomly assigned to treatments. |
Matched Pairs | Blocks consist of two experimental units that are similar with each being randomly assigned treatment. |
Variance | Estimated average of deviations squared. |
Interquartile Range (IQR) | The range of the middle half of the data. |
Extrapolation | Calculating numbers outside of the model. |
Residual | Deviation from the predicted value.
-No pattern: Linear
-Curved pattern: Not linear |
Five Number Summary | 1) Minimum
2) Maximum
3) Median
4) Lower Quartile
5) Upper Quartile |
Data Analysis Process | 1) Understand the nature of problem.
2) Decide what/how to measure (define variables)
3) Collect Data
4) Summarize data, perform preliminary analysis (range, deviation)
5) Formal analysis
6) Interpret Results |