Baylor University QBA 2302 Exam 1

interquartile range

Q3-Q1, used to determine which points are outliers

statistic

a numerical measure of all elements within a sample

convenience sample

a sample that is easy to obtain. DISADV: not SRS and not representative, ie surveys on thee internet

what is a representative sample

a sample that represents the population well

what is a srs

a sample where every single element in a population has the exact same chance of being chosen. DISADV: sometimes SRS might meet criterion ie. 40% male and 60% female and thus not always a rep sample

what is a population

a set of ALL individuals or items being studied, when defining a population include the word ALL

sample

a subset of individuals from a population, use the word SOME. big data=big sample

stratified sampling

a variation of random sampling; the population is divided into subgroups and weighted based on demographic characteristics of the national population ADV: a rep sampling, ie NYC is made of 5 boroughs

is a representative sample biased

can be called unbiased

systematic sampling

choosing every kth personm

what are the two types of quantitative variables

discrete and continuous

what is the formula and notation for SAMPLE variance

s2

what is a discrete variable

set is finite and limited number of outcomes, "counting data"

what is the best data collection method

simple random sample

biased sample

some portions have a greater chance of being chosen,

cluster sampling

split the population into different mutally exclusive and collectivly exhaustive groups and then take a random sample from only SOME of the groups.. ADV: a good way to keep from a biased sample when pop is geographically large DISADV: not representative or SRS

descriptive statistics

summarizes a data set, ie mean median mode range, GRAPHS

bar graphs

summarizes qualitative data, bars are touching

pie chart

summarizes qualitative data, do not use when there are many slivers

Box plot

summarizes quantative data

histogram

summarizes quantitative data, like a bar graph but bars arent touching

stem and leaf plot

summarizes quantitative data, use if you dont have a lot of numbers, we can see which numbers show up frequently

standard deviation

the square root of the variance, for nation just square root o2 or s2, an outlier can throw off

what is statistics for

to understand and analyze data in the real world

continuous data

too many outcomes to list out, measurable

what is unamodel, bimodel, multimodel

unamodel: one peak or mode bimodel: two peaks same hieght multimodel: more than 2 of same height peaks

inferential stats

use a summary measure from a data set to make an inference for an entire population, NOT graphs, it is making an inference will include a thus statement

what is a variable

varies from element to element, where we obtain data, qualitative or quanitative

non-response bias

when individuals selected to be in the sample do not respond

what is distribution

where points tend to fall on a number line

what is the variance

• Most frequently used measure of variability • Mean of the squares of deviation scores • basically an average distance of data points away from the mean always positive

semiquartile

IQR/2

what does empirically based mean

based on data and everything is empirically based

voluntary response

bias because self selected

leading questions

bias because wording favors a response ie, satisfied, very satisfied

what is the tendency of j shape

higher numbers get more frequent

what is a measure of variation

how spread out the numbers are ie, range , variance

what is the mode

inconsistant, may be several modes or no modes, not mathematically tactable, ONLY measure of central tendency that can be used with qualitative data

what is a bias sample

leaves out certain portions which reflects in inaccurate view

what is left skewed and right skewed

left skewed: higher numbers are more frequent right skewed: lower numbers are more frequent

dot plot

like a stem and leaf plot but has dots

percentiles

measure of variation, quartiles of 25

social desirability

most like to be seen in good light so may not be honest particularly if survey results are not confidental

what is the range

not mathematically tractable, not consistent, and bad if there are outliers

what is a parameter

numerical measure of all elements in a population, actually impossible to find

what is the formula and notation for POPULATION variance

o2

what is an element

one thing in a population, in real life we cannot track down data from all elements in an entire population

we use statistics to estimate....

parameters