Help
Options
Didn't know it?
click below
click below
Knew it?
click below
click below
Don't Know
Remaining cards (0)
Know
retry
shuffle
restart
0:00
Embed Code - If you would like this activity on your web page, copy the script below and paste it into your web page.
Normal Size Small Size show me how
Normal Size Small Size show me how
Statistics Terms
Terms and definitions
| Question | Answer |
|---|---|
| What is the term for planning the development of a survey questionnaire? | Blueprint |
| What procedure identifies people to answer your survey? | Sampling |
| What two errors can be controlled as the survey is created? | Coverage errors & sampling errors |
| What is collecting information using multiple methods? | Mixed modes |
| Two types of survey's in cyberspace. | Email & Internet |
| Three purposes of surveys: | Public opinion poll Developmental survey Follow-up survey |
| Survey that is conducted to determine the status of a group after some period of time. | Follow up survey |
| Concerned primarily with variables that differentiate people at different levels of age, growth, or maturation | Developmental survey |
| Descriptive survey that is used to determine how different groups of people feel about political, social, educational, or economic issues. | Public Opinion Poll |
| Survey classifications | Cross sectional or longitudinal |
| Types of longitudinal surveys | Panel surveys, trend studies, cohort studies, follow-up studies |
| Three data collection methods in survey research | 1-Survey by mail, email, or internet 2-Interview survey 3-Telephone survey |
| Four sources of survey error: | Sampling error, coverage error, measurement error, nonresponse error |
| The result of surveying only some, and not all, elements of the survey population | sampling error |
| The result of not allowing all members of the survey population to have an equal or known nonzero chance of being sampled for participation in the survey | Coverage error |
| The result of poor question wording or questions being presented in such as way that inaccurate and interpretable answers are not obtained. | Measurement error |
| The result of people who respond to a survey bing different from sampled individuals who do not respond, in a way relevant to the study. | Nonresponse error |
| Two types of question structures | Open ended, closed ended |
| 4 types of sampling procedures | 1-simple random sampling 2-systematic random sampling 3-stratified random sampling 4-cluster random sampling |
| Randomly choosing individuals from one list of names. | simple random sampling |
| Randomly choosing ONE individual from some fraction of ONE list of names, which in turn selects the rest of the sample | Systematic random sampling |
| From two or more lists of names, randomly choosing individuals to serve as sample of each population | stratified random sampling |
| without a list of names, individuals are randomly chosen according to a group membership | cluster random sampling |
| Margin of Error is sometimes referred to as the | bound |
| Formula for Bound | B is 2 times the square root of variance |
| Find total if the sample mean is $50 and the population is 1000 | $50,000 |
| Estimation can be used for testing | nondirectional hypotheses |
| Tchebysheff's theorem | Range = 4SD so 1/4 range is an estimate of SD |
| Good coverage of range is | 5-10% |
| Standard variance for proportions use | +-.25 |
| A set of procedures for conducting successful self-admimistered surveys that produce both high quality information and high response rates | Tailored Design Method |
| The prescribed order in which we want people to process words and symbols used to convey the questions. | Information organization |
| The graphical symbols and layout used to visually direct people in a survey | Navigational guides |
| A theory of human behavior used to explain the development and continuation of human interaction | Social Exchange |
| What one expects to gain from an activity | rewards |
| what one gives up or spends to gain rewards | Costs |
| The expectation that in the long run the rewards of doing something will outweight the costs | trust |
| Ways of providing rewards in Social Exchange theory | 1-show positive regard 2-say thank you 3-ask for advice 4-support group values 5-give tangible rewards 6-made questions interesting 7-give social validation 8-inform that opportunities are scarce |
| Ways of reducing social costs in Social Exchange theory | 1-avoid subordinating language 2-avoid embarrassment 3-avoid inconvenience 4-Make questionnaires short & easy 5-Keep requests similar to others |
| Ways of establishing trust | 1-provide token in advance 2-sponsorship by legit authority 3-make task appear important 4-invoke other exchange elements |
| 5 contacts | 1-prenotice letter 2-questionnaire mailout 3-Postcard thank you 4-First replacement questionnaire 5-Invoking of special procedures |
| All the units that you will generalize survey results to | Survey population |
| the list from which a sample is drawn | sample frame |
| units drawn from a population | sample |
| all the units that return the completed survey | completed sample |
| Three steps of constructing a questionnaire | 1-Define a desired navigational path for reading all information 2-Create visual navigational guides that will assist respondents to correctly interpret written info 3-Develop additional visual navigational guides to interrupt & redirect ie skip pattern |
| Standard deviation in plain language | average difference in scores from the mean |
| variance | the average squared differences from the mean |
| Variability | the spread of the data |
| Margin of error = | Critical value times standard error |
| reliability | being able to get the same results (consistency) |
| Reliability is a necessary but not sufficient condition for _______ | validity |
| Classical true score model | Observed score = true score + error |
| Reliability coefficient r squared | effect size - the squared relationship between observed and true scores |
| if Cronbach's alpha is 70 then | 70% of the observed score is accounted for by the true score, leaving 30% error |
| Reliability per standard literature | .7 or higher |
| systematic random error | same as bias - |
| When a test is biased against a subset population (yielding lower scores based on their true ability) | reliability (Chronbach's alpha) goes up |
| Theory of validity (new) | tests are not valid, the scores are |
| All statistics are essentially | correlational |
| You have to use squared correlations | to get effect size |
| The correlation or R squared is the relation between the two variables or | the overlap in the venn diagram |
| if there is no variance in items | there is no reliabiltiy |
| In spss rows are for | people |
| In spss columns are for | variables |
| Assuming the null hypothesis is true how likely am I to see this data (or how likely are my results) | p value |
| What are defective items according to Dillmans? | open ended questions and check all that apply questions |
| Cohen's article interpreting P value | What we want to know is: Given this data, what is the probability that the null is true? What it actually tells us is that given that the null is true, what is the probability of these data? |
| Statistical analysis is | testing the null hypothesis |
| Definitions associated with Social Exchange theory | cost, reward, trust |
| What does probability tell you? | The likelihood of an event occuring |
| R squared | explains part of the variance in a dependent variable due to an independent variable |
| Variance accounted for | r squared |
| What is standard error? | The standard deviation of the sampling distribution of the sample means. SE - SD/√n (SD=Pop SD) |
| Type 1 error | Probability of rejecting the null when it is true |
| Type 2 error | Probability of failing to reject the null when the alternative hypothesis is true |
| P value | probability that Null is true |
| Cronbach's alpha | reliability coefficient that measures internal reliability (how closely related a set of items are as a group) |
Created by:
barbserianni
Popular Academic Vocabulary sets