statistics Flashcards
census sampling advantgaes and disadvantages
ad:
-should give you complete accurate results
-basis of various surveys
dis:
-can not be used when testing involves destruction
-large volume of data to process
-costs and time consuming
sample sampling advantgaes and disadvantages
ad:
-cheaper, quicker
-less data to process
dis:
-may not be accurate
-too small/ not large enough to represent small sub-groups
what is random sampling
each thing has an equal chance of being selected
each element in a sample frame is assigned a numer
random sampling ad and dis
ad:
-numers truly random and free of bias
-easy to use
-each numb has a known qual chance of being selected
dis:
-not suitable when pop size is large
-may not be similiar to the orginial pop
what is convenience sampling
respondents are chosen based upon their aviliability
convenience sampling ad and dis
ad:
-approach avoids difficulties ofsimple random sampling
-if sample is large enough it can still provide useful info
dis:
-sample will nto be random
-can intrudoce bias
-results may not be generalizable to pop
what is systematic sampling
required elements are chosen at regular intervals in ordered list
eg. take every Kth elements where
K= pop size/ samp size
ad and dis of systematic sampling
ad:
-simple to use
-suitable for large samples
dis:
-only random if the ordered list is truly random
-can introduce bias
what is stratified sampling
pop divided into groups (strata) and a simple random sample carried out i each group
used when sample is large and pop naturally divides into groups
ad and dis of stratified sampling
ad:
-it can give more accurate estimatesthan simple random sampling where there are clear strata present
-reflects the pop structure
dis:
-within the strate, the problems are the same as for any simple rando sample
-if the strata are not clearly defined they may overlap
what is quota sampling
the populatin is divided into groups in terms of gender social class etc. a quota of people in each group is set to try and reflect the groups proportion in the whole population
researchers carry out convenience sampling but only stop after all the pre-set quotas are covered
ad and dis quota sampling
ad:
-enables fieldwork to be done quickly because a representitive sample can be achieved with a small sample size
-costs kept to a min
-administering the test is easy
dis:
-not possible to estimate the sampling errors (process is not random one)
-interviewers have to choose the respondents and may not be able to judge the characteristics easily
-can introduce interviewers bias in who is included
range
max-min (width of data set)
interquartile
upper quartile- lower quartile
standard deviation
mean distance each point from mean
variance
square of standard deviation
what happens when you add a constant K to every data
change mean, meadian and mode by K
not change STDEV or IQR
multiplying every data valuesby poistive constant K will
multiply mean, median and mode by K
multiply STDEV and IQR by K
describe histograms
- frequency represented by area of each box= class width X frequency density
class width=. X
frequency density= Y
describe cumulative frequency graphs
numer of values that are less than or equal to give point in data set y axis= cumulative frequency
x axis= data values
median= medium value in y axis
lower quartile = max value in y axis/ 4
upper quartle= max value in y axis/ 4 X 3
describe box and whiskers
lines on each end are min and max value
middle line in box is the median and edges of box lines are lower quartile and upper quartile
what is the pearsons product moment correlation used for
to represent the strength and direction of linear correlation
-1<= r <= 1
r=1; strong positive linear correlation
r=0; no correlation
r=-1; strong negative linear correlation
regression line
line of bestfit
how do you know if data value X is an outlier
if:
X < Q1 - 1.5(Q3 - Q1)
