Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
68 Cards in this Set
- Front
- Back
Observational study
|
merely observe things about sample
|
|
Randomized experiment
|
randomly assign people to one of two groups
|
|
Random assignments
|
made by doing something akin to flipping a coint ot determine group membership
|
|
When deciding if a study is reliable, what 7 things should be considered?
|
Funding source
The researchers themselves Individuals/objects studied, how they were selected Nature of measurements/questions asked Setting of study Differences in groups Extent/size of effects |
|
Open Question
Closed Question |
Open: respondents allowed to answer in their own words.
Closed: respondents given list of alternatives. |
|
Categorical variables
|
those we can place into a category but may not have any logical ordering
|
|
Ordinal variable
|
some sort of order imposed on categorical variables
|
|
Nominal variables
|
categorical variables that don't have any natural ordering
|
|
Measuerment variables/quantitative variables
|
those which we can record a numerical value and then order respondents according to those values
|
|
Interval variable
|
measurement variable in which it makes sense to talk about differences, but not ratios. Temperature
|
|
Ratio variable
|
measurement varaible with a meaningful value of zero. Pulse rate doubling.
|
|
Discrete variable
|
one for which you could actually count the possible responses
|
|
Continuous variable
|
Anthing within a given interval
|
|
Valid measurement
|
One that actually measures what it claims to measure
|
|
Reliable measurement
|
one that will give you or anyone else approximately the same result time after time when taken on the same object or individual
|
|
Biased measurement
|
A measurement that is systemaatically off the mark in the same direction
|
|
Variability
|
likely to differ from one time to next, or from one individual to the next because of unpredictable errors or discrepancies
|
|
Measurement error
|
Amount by which each measurement differs from the true value
|
|
Explanatory variable
|
What is being manipulated
|
|
Outcome/response variable
|
The outcome of the manipulation
|
|
Margin of error
|
Measure of accuracy; 1/ squ(n), where n is the number of people in the sample.
|
|
Simple random sample
|
Everyone in population has the same chance of being selected
|
|
Stratified random sample
|
Divide population into groups, then taking simple random sample from each. Used instead of simple sample when we need to get a group reading, when it's more accurate, when strata are geographically separated, when different intervieweres are used.
|
|
Cluster sampling
|
often confused with stratified sampling, but totally different; clusters are assigned, but instead of a sampling within each group, a random sample of clusters is picked to be measured as a whole.
|
|
Systematic sampling
|
Divide list into as many consecutive segments as needed, randomly choose a starting point in first segment, then sample at that same point in each segment.
|
|
Multistage sampling plan
|
Using a combination of sampling methods
|
|
Explanatory variable
|
attempts to explain or is purported to cause differences in response variable
|
|
Treatment
|
one or a combination of categories of the explanatory variables assigned by the experimenter
|
|
Randomized experiment
|
create differences in the explanatory variable and then examine the results
|
|
Observational study
|
observe differences in the explanatory variable and then notice whether these are related to differences in the response variable
|
|
Confouding variable
|
individuals who differ in in explanatory variable likely to differ in confounding variable; confounding variable affects the response variable
|
|
Interactions
|
occur qhen the effect of one explanatory variable on the response variable depends on what's happening with another explanatory variable
|
|
Randomization
|
relted to the idea of random selection
|
|
Control groups
|
Don't receive treatment, handled identically
|
|
Double blind
|
Neither particpants nor researcher taking measurements know who had which treatment
|
|
Single blind
|
only one of the two, participant or researcher, knows who got treatment
|
|
Matched pair designs
|
Experimental designs that use either two matched individuals or the same individual to receive each of the two treatments
|
|
Randomized black design (block design)
|
Extension of matched pair design to three or more treatments
|
|
Random assigment to treatments reduces...
|
unknown systematic baises
|
|
Matched pairs, repeated measures, and blocks are used to reduce..
|
known sources of natural variability in response
|
|
Potential complications for experiments
|
1) Confouunding variables
2) interacating variables 3) Placebo, Hawthrone, and experimenter effects 4) Ecological validity and generalizability |
|
Solution to confounding variables
|
randomization
|
|
Solution to interactinv variables
|
researchesrs measure and report variables that may interact with main explanatory variables
|
|
Placebo, hawthorne, and experimenter effects solution
|
double-blind and control group
|
|
Solution to ecological validty and generalizability
|
(Variables being removed from natural setting)
No ideal solutions; design experiments that can be performed in natural setting with random sample |
|
case-control studies
|
a type of observational study; cases who have a particular attribvute are compared with controls who don't have that attribute
|
|
Retrospective and prospective studies
|
observational; retrospective look backward, prospectrive follows participants into the future and events are recorded. prospective preferred.
|
|
Complications for observational studies
|
Confounding variables and implications of causation
Extending the results inappropriately Using the past as a source of data |
|
Mode
|
most common value
|
|
Median
|
center
|
|
Mean
|
average
|
|
Range
|
distance between least and most
|
|
Unimodal histogram or stemplot
|
one prominant peak
|
|
Bimodal histogram or stemplot
|
two prominent peaks
|
|
Skewed to the right
|
higher values more spread out and lower (skewed part is low part)
|
|
Skewed to the left
|
Lower values are more spread out
|
|
Five number summary
|
Lowest and highest values, median, lower and upper quartiles
|
|
Quartiles
|
median of the two halves of the ordered list
|
|
Variance
|
Standard deviation is the square root of the variance
|
|
Frequency curve
|
smooth picture of population
|
|
Normal distribution of freuqnecty curve
|
bell shaped
|
|
Standardized score
|
represents the number of standard deviations of the observed value or score falls from the mean
|
|
Standard score is also known as
|
z score
|
|
Standard normal curve
|
Normal curve with a mean of 0 and a standard deviation of 1
|
|
Standardized score
|
(Observed value - mean)/standard deviation
|
|
To find percential
|
get standardized score, then look up percentaile in table
|
|
To find observed value from percentile
|
look iup percentile in table, find standaridzed score. COmpute the oberseved value: mean + (standardized score x standard deviation)
|
|
Empirical rule
|
68% fall within 1 standard deviation
95% fall within 2 standard deviation 99.7 fall within 3 standard deviation |