click below
click below
Normal Size Small Size show me how
SCI1020
Statistics
| Term | Definition |
|---|---|
| Simple Random Sampling | 1. All units in population have the same chance of being in the sample. 2. Every conceivable group of units required size has the same chance of being the selected sample |
| homogeneous population | relatively the same, not too much variability |
| heterogeneous population | there is variability between groups in the question of interest |
| stratified random sampling | Population divided into subgroups (strata) and random samples taken from each strata |
| table B (SRS) | small population |
| excel (SRS) | large population |
| Why use stratified sampling? | better representation when there are subgroups |
| cluster sampling | Divide the population area into sections (or clusters). Then randomly select some of those clusters. Now choose all members from selected clusters. |
| systematic sampling | The process of selecting a sample of subjects for a study by drawing every nth unit on a list |
| multistage sampling | a probability sampling technique involving at least two stages |
| selection bias | when some part of the population is not included in the sampling process |
| non-response bias | when a representative sample is chosen but a subset cannot be contacted or doesn't respond |
| response bias | when participant response differently from how they truly feel |
| what is measured | unit - a single individual or object bein measured. if an experiment, then called an experimental unit. when units are people, called subjects or participants. |
| explanatory variable | a variable that we think explains or causes changes in the response variable |
| response variable | a variable that measures an outcome of a study. |
| confounding variable | a variable that affects the response variable and also related to the explanatory variable. - known |
| lurking variable | potential cofounding variable but it is not really known or anticipated beforehand |
| observational study | researches observe or question participants about opinions, behaviors, or outcomes. the outcome (response) is associated with other features observed (explanatory) |
| experiment | researchers deliberately manipulate at least one explanatory variable (factor) and measure at least one response variable. |
| a type of observational study | case control study |
| experimental design steps | 1. control 2. randomisation 3. replication |
| types of control | treated identically in all aspects. placebo controlled placebo |
| single-blind | control : participants do not know which treatment they have received |
| double-blind | control: neither participant nor researcher making measurements knows who has which treatment |
| mathematical model | mathematical representation of the relationship between simply 2 different quantitative physical phenomena |
| categorical data | represents characteristics or qualities of people or things |
| distribution | statistics of a variable: shows how many times it shows |
| histogram | a graph of the distribution, bars are placed closer together |
| parameter | when describing the population |
| statistic | number taken from a sample |
| parameter mean symbol | mu (microgram) |
| statistic mean symbol | x bar |
| parameter standard deviation symbol | sigma |
| statistic standard deviation symbol | s |
| confidence interval | a probability that a parameter will fall between a set of values |
| level of confidence | the probability with which the estimation of the location of a statistical parameter in a sample population is also true for the population |
| degrees of freedom | maximum number of logically independent values, which are values that have the freedom to vary, in the data sample |
| matched pair | where subjects with same characteristics get paired up |