1/55
Looks like no tags are added yet.
Name | Mastery | Learn | Test | Matching | Spaced |
---|
No study sessions yet.
Population
A parameter, true mean
Simple Random Sample steps
1. Label individuals
-assign numbers, write names on strips of paper
2. Randomize
-Random number generator(no repeats)
-Random digit table
-Names in hat (shuffled)
3. Select
-BS results, corresponding name with #
4. Repeat process
-until total sample size
Explain clearly how you would use your calculator to choose a sample of 75 students for this study.
You should assign numbers 1-3478 to the students, making sure each student has a unique number. Using your calculator you can generate 75 random numbers 1-3478. If a number repeats you can reenter the operation (1, 3478, 75). Do this until 75 random numbers are selected. Then you can use random assignment again to split the students into groups.
simple random sample
A sample of size n selected from the population in such a way that each possible sample of size n has an equal chance of being selected.
simple random sample example
In an effort to identify whether an advertising campaign has been effective, a marketing firm conducts a nationwide poll by randomly selecting individuals from a list of known users of the product
systematic sampling
Every nth item in the target population is selected.
Pros: Easy to gather data if pop units are lined up, and unbiased
Cons: only useful in certain scenarios
systematic sampling example
Starting with a randomly chosen ice cream customer, every 5th customer was chosen and that customer was asked to fill out a survey.
cluster sampling
Randomly choose 1 or more cluster and sample everyone in that cluster.
Pros: Easiest to implement, unbiased, accurate
Cons: If large variation in between clusters it's imprecise
cluster sampling example
Students from Waterloo Region, randomly selects 20 schools from 120 schools, then contacts every student from each of the 20 chosen schools
stratified random sampling
Population divided into subgroups (strata) and random samples taken from each strata
Pros: can be very precise, and unbiased
Cons: sometimes can be difficult to implement
stratified random sampling example
divide demographics by age, gender etc., then random sample each 'strata'
Judgemental/convenience sample
Someone is easily chose, not by random number generator
Pros: None
Cons: biased
convenience sample example
To represent all the students attending a school, the principal surveys the students in one math class.
voluntary response bias
bias introduced to a sample when individuals can choose on their own whether to participate in the sample (tends to be people with strong opinions)
Selection bias
A polling error in which the sample is not representative of the population being studied, so that some opinions are over- or underrepresented
undercoverage bias
occurs when some members of the population are inadequately represented in the sample
non-response bias
Bias introduced into survey results because individuals refuse to participate.
Response bias
anything in a survey design that influences responses.
Ex: the people who are asking, the environment
Wording bias
a type of response bias where the question is posed to achieve a desired result
Measurement bias
a form of inaccurate measurement in which the data consistently overestimate or underestimate the true value of an event. On the person doing the measurement.
observational study
Observes individuals and measures variables of interest but does not attempt to influence the responses. There's no treatment imposed.
observational study example
Compare the grades on the next unit math test of 25 students who use calculators and 25 students who do not use calculators. The students decide which group they're in.
retrospective study
A study using information on events that have taken place in the past
retrospective study example
investigating the link between childhood exposure to lead paint and current rates of cognitive impairment in adults by reviewing medical records of individuals born in a specific time period to identify past lead exposure levels and then comparing those levels to their current cognitive function test results
prospective study
an observational study in which subjects are followed to observe future outcomes
prospective study example
female nurses who smoke and those who do not smoke) and compares them for a particular outcome (such as lung cancer)
Explanatory variable(factor/independent)
helps explain/predict response
response variable (dependent variable)
measures an outcome of a study
confounding variable
a factor other than the factor being studied that might influence a study's results (influences explanatory and response variables)
Experiment
A research method in which an investigator manipulates one or more factors to observe the effect on some behavior or mental process (treatment imposed, shows casuation)
Treatment
What is done (or NOT done) to the experimental units,
- levels x levels
Experimental units
who/what the treatment is imposed on (if humans we call them subjects)
factors
the explanatory variables in an experiment. (EX: type of drink, caffeine, etc)
Levels
different values of the factor
Control group
In an experiment, the group that is not exposed to the treatment or gets a placebo; serves as a comparison for evaluating the effect of the treatment.
Placebo
any treatment given as a control, appears real but has no benefit
placebo effect
experimental results caused by expectations alone; when a fake treatment works
blinding
when subjects (single-blind) and/or experimenters (double-blind) who interact with subjects are unaware of what treatment was assigned
Everyone _____ blinded.
cannot be. Someone has to know
Key Principles of a well-designed experiment
1. Comparison: 2 or more treatments
2. Random Assignment
3. Control: Keep all other variables besides the treatments constant; minimize confounding
4. Replication: Using enough experimental units to distinguish differences
Control is _____.
Not required for an experiment
Block
a group of experimental units that have a similar characteristic
How to describe an experiment
1. State subjects/experimental units if not yet listed
2. Justify blocks/pairs similar if needed - choose one
3. Randomly assign to treatments (elaborate if asked) stating how many go to each
4. Repeat if needed for other blocks
5. State what you are comparing in(response variable) context.
Randomized block
units are blocked into groups and then randomly assigned to treatments within each block
Matched pair
A block design of size 2 (pairs), there are two possible formats:
1. Subjects are paired first and then randomly assigned to the two treatments
2. Each subject receives two treatments in a random order.
Different Samples...
yield different results due to natural variation
Larger sample sizes...
reduce the variability of estimates
Margin of error
creates an interval of plausible values
plausible
(adj.) appearing true, reasonable, or fair
Statistically significant
refers to a result that is statistically unlikely to have occurred by chance
-if proportion of dots < 5%, then statistically significant
-if proportion of dots > 5%, then not statistically significant
Random sampling allows us to...
make generalizations about the population from which we sampled
Random assignment
Allows us to say a treatment causes changes in the response variable
Randomly selected and random assignment
Inferences about pop: yes
Inferences about cause and effect: yes
NOT randomly selected & IS randomly assigned
Inferences about pop: no
Inferences about cause and effect: yes
Randomly selected and NOT randomly assigned
Inferences about pop: yes
Inferences about cause and effect: no
NOT randomly selected and NOT randomly assigned
Inferences about pop: no
Inferences about cause and effect: no