SCMA 350 Exam 1

business analytics

use of data and information to gain insight and knowledge and aid business decision maker

mean

summing up all variable values/number of entries

median

use instead of mean when extreme values exist

mode

most frequently observed value

percentile

at least “p” percent of the observations are less than or equal to the value of the “pth” percentile and (100-p)% > to this value

quartiles

1st, 2nd, 3rd quartile: 25th, 50th, and 75th percentile

range

difference between maximum and minimum values observed

interquartile range

middle 50% of the data = Q3-Q1

reference lines

can show average, median, and quartiles, constant line: very helpful when distinguishing between categories comparing using target value (numerical)

covariance

measure of how much two random variables change together, indicates positive or negative direction

skewness

relative to extreme values among observations

positive skew

most values smaller and extreme values skew right (goes downward)

negative skew

most values higher and extreme values skew left (going upward)

histogram

we use this to represent the shape of distribution

box and whisker plot

we use this to represent variability

numerical variables

can display all of the numerical measures described above: quartiles, standard deviation, covariance

categorical variables

we can use different segmentation and comparison across the category to examine relationships: days of week, quality ratings, segments of business

crosstabulation

displays the relationship between two variables in a table: frequency, proportions/marginals, comparisons using numerical variable, visualizations

stacked bar chart

unique way (similar to pie chart) to display crosstabulation across multiple categories

variables

service or product characteristics that can be measured, such as weight, length, volume, or time

attributes

service or product characteristics that can be quickly counted for acceptable performance

decrease variation

larger sample sizes tend to _

common causes

are random, unidentifiable sources of variation that are unavoidable with the current process

assignable causes

any variation causing factors that we can identify and eliminate

statistical control

a process is in _ ___ when the location, spread, or shape of its distribution does not change over time

r chart

monitors process variability

x chart

checks the process output to determine: on average, consistent with target variable, current performance, consistent with past performance

p-chart

a chart used for controlling the proportion of defective services or products generated by the process

c-chart

a chart used for controlling the number of defects when more than one defect can be present in a service or product

alternative hypothesis

finding the defendent guilty based on evidence

null hypothesis

we do not find enough evidence to find the defendant guilty

p-value

the smaller, the stronger evidence against the null hypothesis

z-test

comparing two subgroups where variance of both subgroups is known

t-test

comparing two subgroups where variance of subgroups is unknown

ANOVA

comparing three or more subgroups

normal distribution (try ln if not), equal variances (levene’s test)

assumptions of anova include

kruskal-wallis test

comparing three or more subgroups