week 4 Flashcards
what does the general process of sampling refer to
the manner by which you get ppl to participate in your study
two broad categories of sampling
- probability: each member of a population has a probability of being selected, hopes to draw general conclusions (ex simple random, stratified sample, cluster)
- nonprobability: sampling out of convenience (ex purposive, quota, and snowball)
when a sample reflects attributes of the whole target population it is _____ and it is ___ when it does not
representative, biased
different types of internal validity (8 total)
- content: contents on a test make sense based on what is measured
- face: if it is valid to those that are taking it
- criterion: if its relatable to previous research outcome/criterion
- predictive: accurately forcast future behaviour
- concurrent: if measure is meaningfully related to another
- construct: if it measures a construct/operational definition
- convergent: should relate to past tests that are related to construct
- discriminant: does not relate to scores not related to construct
locus of control
- personal beliefs abt causes of what happens to us
- internal: they control what happens
- external: outside forces control outcomes
nominal scale
- classify people into one group or another
ordinal scales
- sets of ranking, show relative standing of objects/ppl
interval scales
- rank order w equal intervals between ordered events
- preferred bc of more sophisticated stat analysis and wider range of them
ratio scales
- similar in equal interval and concepts of order from ordinal and interval scales, but add a true point zero
- point zero=absence of attribute measured
Descriptive vs inferential stats
descriptive: summarize data collected
inferential: draw conclusions from data
mean location formula
mean location= n+1/2
- n=total number of scores in sample
____ stats measures mean, median, and mode
descriptive
mean, median, mode, and range def
mean: average
median: middle of numbers
mode: most frequent number occurring
range: difference between highest and lowest number
interquartile range
- find quartiles 1, 2 and 3
- Q3-Q1=IQR
- useful when you have outliers in your dataset
variance
- shows how distributed data is from the mean
standard deviation
- estimates the average amount by which scores in sample deviate from the mean score
what is the square root of the variance
standard deviation
variance vs SD
- variance: data represents entire population
- SD: data represents a sample of scores from population
what does a histogram show
- number of times each score occurs or how often scores within a range occur
how to make histogram
- find frequency distribution (table that records # of times an event occurs)
- graph it
normal curve
- aka =normal distribution
- bulges near middle and is relatively flat at either end
- hypothetical distribution if everyone was tested on same measure
- at the centre is often mean median and mode
t or f: majority of events will fall within the first few standard deviations
true
what is the purpose of null hypothesis testing
to determine the rate of which results found were due to chance
null hypothesis vs alt hypothesis
- Null: aka nothing, H0, no difference between variables
- alt: what you are hoping to find, Ha, difference between variables is found
alpha
- (a) = 0.05
- probability of obtaining particular results if no difference is true
publication bias
- notion that only statistically significant results get published
file drawer effect
- studies finding no difference are less likely to be published
NHST
null hypothesis significance testing
effect size
- provides estimate of magnitude of difference among sets of scores, taking amount of variability in scores into account
__________ is a range of values expected to include population value with a degree of confidence
confidence interval