NRF/BIG research provided results of a consumer holiday
spending survey (USA Today, December 20, 2005). The
following data provide the dollar amount of holiday spending
for a sample of 25 consumers.
12 85 74 59 34
45 89 26 61 35
Test Statistics for Scenarios
September 28, 2016
Sleep scenario, unknown
A random sample of 44 government employees were assigned to a 6-hour work day for a period of 8 weeks.
Over this time, a sleep monitor was used to record the amount of
Done to remvoe scale effects
Done to make each variable start with the same number
Usually performed before principal component analysis
Usually needed before a tecnique can be used
Done by dividing by the standard d
Lecture 13: More Test Statistics
September 30, 2016
Moonwalking with Einstein
Some individuals have the ability to recall accurately vast amounts of autobiographical information without
mnemonic tricks. This ability is called HSAM, for Highl
Lecture 14 Part II: Proportions as PDF
October 2, 2016
The test statistics and confidence intervals to this point have dealt with continuous data.
Discrete data: Isolated points on a number line.
breakdown of stude
2 Sept 2016
Standard Normal Distribution
What is E(Z)?
What is Var(Z)?
Use the rules for linear combination:
Var ( Z ) b 2 2
E ( Z ) a b
Z ~ N (0,1)
Average lifespan of 40 months, standard deviation
of 6.3 m
August 26, 2016
The Design: Experiments, Observational Studys, Surveys
Experiment-allows the researcher to manipulate one or more of the factors.
Response Variable- variable of interest.
Explanatory Variables (Factors)- v
What is the lot size and income associated with the below splits?
Lot size = 23,000
Lot size = 21,000
Lot size = 19,000
Lot size = 17,000
The value of K i
For the following dendogram, how many clusters can the data be reduced to
with a cutoff distance of 3.4?
Give any one other term used for each of the following terms:
Based on the below decile chart, how much more likely is the top decile to
identify the important class, as compared to the average prevalence
2.5 times as likely
Twice as likely
1.5 times as likely
Just as likely
none of the above
Data mining methods grew out of which 3 fields?
None of the above
Please put the recursive partitioning steps in order
Maximize purity in initial split through
Normal Approximation for Sample Proportions
The sampling distribution of
is approximately normal with mean p and
if the following conditions are satisfied:
1. A random sample is selected from the population. Even if the sample is
Discrete Prob. Dist.
Discrete and Continuous
Discrete Probability Distributions
Expected Values and Variance
Binomial Probability Distribution
Poisson Probability Distribution
Continuous Prob. Dist.
Uniform Probability Distribution
The above is true if the sample size is large enough, usually n greater than
30 is sufficient.
We have shown that both the sampling distribution of the sample
proportion, and the sampling distribution of the sample mean are both
Measures of location
Mean, Median, Mode
Percentiles, Quartiles, Rank
Measures of Variability
Range, Interquartile Range
Variance, Standard Deviation
Measures of Distribution
z - Scores
Using Economic Fluctuations to Understand the Recent Recession
What Caused the 2007 Recession?
1) Collapse of the housing bubble
The sharp drop in housing sales and prices led to rising
foreclosures, lower consumer spending and large-scale layoffs in
October 7, 2016
Testing independence of Categorical Variables
Is an undergraduate students choice of presidential candidate independent of year of study?
X=choice of presidential candidate (Clinton or Trump) Y =year(Freshman
August 28, 2016
Our research question
Does studying lead to better test scores on a exam?
Target Population: WSU-V students, N = 3410 (based on unofficial enrollment update)
Random Variable : X = Examscores
Variables differ between
Apply Tools: The following steps describe how to use Excels
chart tools to construct a histogram for the audit time data using
the frequency distribution appearing in cells C1:D6.
Select cells C2:D6
Click the Insert tab on the Ribbon
19.Fortune provides a list of Americas largest corporations
based on annual revenue. Shown below are the 50 largest
corporations, with annual revenue expressed in billions of
dollars (CNN Money website, January 15, 2010).
Construct a cumulative frequency distribution and a
cumulative relative frequency distribution.
Construct a histogram and an ogive for the data in exercise
Consider the following data.
1 1 1 1 1 1
0. 1. 7. 0. 2. 3.
A cumulative relative frequency distribution.
What do these distributions tell you about the annual
revenue of the largest corporations in America?
Show a histogram. Comment on the shape of the
What is the largest corporation in
The majority (60%) earn less that $5 million; 78% earn less than $10 million; five golfers (10%)
earn between $20 million and $30 million; only Tiger Woods and Phil Mickelson earn more than
The Nielsen Home Technology Report provide
The Dow Jones Industrial Average (DJIA) underwent one of
its infrequent reshufflings of companies when General
Motors and Citigroup were replaced by Cisco Systems and
Travelers (The Wall Street Journal, June 8, 2009). At the
time, the prices per shar
Excel Assignment 1
Due Date: October 12, in class
Name: Rania Hassan .
(a) Open the excel file named Excel_Assignment 1 from Blackboard. The worksheet Descriptive
Statistics) contains information about selected schools (unive