MBAD 503 Flashcards

1
Q

Best illustrates the distinction between statistical significance and practical importance

A

Increased life of hard drive from 240,000 to 250,000 hours

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

25% Students in stats class watch 8+ hours of TV a week so I conclude 25% of university students do the same. Which fallacy is this?

A

Uses a sample not representative of all the students

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

NASA Challenger and Columbia disasters suggest that

A

Limited data may still contain important clues

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

Smoking isn’t harmful, my aunt lived to 90, illustrates which fallacy

A

Small sample generalization

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

Bob didn’t wear lucky T shirt to class so he failed his test, illustrates which fallacy

A

Post hoc reasoning

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

T/F. Statistics is the science of believability

A

True

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

Characteristics of the statistically - savvy

A

Technically current
Communicates well
Can deal with imperfect information

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

Which are practical constraints facing a business researcher

A

Time and money are limited
Research on humans is fraught with danger and ethics
The world is no laboratory so some things are impratical

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

Which is not true?

Inconsistent treatment of data by researcher is a symptom of poor survey or research design
Science of stats tells us whether the sample evidence is convincing
The post hoc fallacy says that when B follows A then B is caused by A
Valid statistical inferences may be made when sample sizes are small the the rules are followed for handling them.

A

Inconsistent treatment of data by researcher is a symptom of poor survey or research design

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

Bond rating from firms like B+, AA, etc are examples of which measurement of data?

A

Ordinal

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

Type of charge card is an example of which kind of variable?

A

Nominal

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

Duration of a flight is an example of which kind of variable?

A

Continuous Ratio

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

Number of Nobel prize winning faculty at Oxnard U is an example of which kind of data measurement?

A

Discrete Ratio (involves zero)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Temp in degrees Celsius at 7:00am today is an example of which measurement of data?

A

Continuous Interval

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

T/F. Cluster Sampling is useful when strata characteristics are unknown?

A

True

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

Before deciding to asses heavy fines on noisy airlines, which sampling method would the FAA probably use to measure peak noise of jets departing?

A

Stratified Sample

To record aircraft size, type, carrier for a week and use this to construct a stratified sample

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

Sampling Bias can best be reduced by?

A

Random Sampling

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

If we use a random number generator between 0-99, we would most likely find that

A

Some numbers would occur more than once

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

Which describes the observations in a dataset consisting of the GPAs and credits taken in the current quarter for randomly selected EWU students?

A

The EWU students

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
20
Q

What is a time series variable

A

Net earnings reported by Xenia Corp. for the last 10 quarters

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
21
Q

CDC wants to estimate extra hospital stay that occurs when pts experience post op a-fib. They divide the USA into 9 regions. In each region, hospitals are selected at random which each hospital size group. In each hospital, surgery pts are sampled according to known percentages by age, gender, etc.
Which sampling methods are used?

A

Cluster
Stratified
Simple Random

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
22
Q

T/F. Running times for 500 runners in a race would be a univariate data set.

A

True

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
23
Q

T/F. List of the ages, genders, salaries, years of experience for 50 CEOs is a multivariate data set.

A

True

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
24
Q

Bond ratings for Aardco INC are B+ while bonds of Deva Corp are AA. Which level of measurement would be appropriate for this data?

A

Ordinal

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
25
Q

Auto exhaust emission of CO2 is what kind of data measurement?

A

Ratio

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
26
Q

Number of passengers bumped on a particular flight is what data measurement?

A

Ratio

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
27
Q

What sampling method is quicker and easier?

A

Convenience

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
28
Q

Professor chose 7 students from his stats class of 35 students by picking those with red shirts that day. Which kind of sample is this?

A

Convenience

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
29
Q

30 work orders are selected from a filing cabinet of 500 by choosing every 15th folder. Which sampling method is this?

A

Systematic

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
30
Q

A population has groups with a small amt of variation within them but large variation among or between the groups themselves. The proper sampling technique is?

A

Stratified

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
31
Q

A manager chose 2 people from his team of 8 to give an oral presentation because he thought they were representative of the whole teams views. What sampling technique did he use in choosing these 2 people?

A

Judgement

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
32
Q

A professor wants to know how many MBA students would take a summer elective and took a survey of the class she was teaching. What kind of sample is this?

A

Convenience

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
33
Q

A sampling technique used when groups are defined by their geographical significance is?

A

Cluster

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
34
Q

Which is not an area of application of statistics in business?

A

Questioning executives strategic decisions

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
35
Q

Students evaluation of a professors teaching is an example of which measurement type?

A

Interval

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
36
Q

Tom’s SUV rolled over. SUVs are dangerous. This best illustrates which fallacy type?

A

Small sample generalization

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
37
Q

Your rating of the food served at a restaurant using a three point scale of 0=gross, 1=decent, 2=yummy is what kind of data measurement?

A

Ordinal (ranking)

38
Q

Frequency Polygon

A

Line graph connecting the midpoints of the histogram bin intervals plus extra at the beginning and end.

39
Q

Ogive is?

Useful for?

A

Line graph of the cumulative frequencies. Useful for finding percentiles or for comparing shape with a benchmark.

40
Q

Stem and Leaf plot

A

Exploratory data analysis tool

Frequency tally

41
Q

Stacked Dot Plot

A

Compares two or more groups, like home prices in 4 different regions

42
Q

Sturges’ Rule

A

Bin Width = (Xmax- Xmin)/k

43
Q

Relative frequencies calculation of data in a table

A

Absolute frequency per bin / total number of data values

44
Q

Cumulative Relative Frequencies

A

Accumulate relative frequency values as bin limits increase.

45
Q

Histogram

A

Graphical representation of a frequency distribution
Appearance is identical if vertical axis shows frequency, relative frequency, or percent
Shows SHAPE of a population.

46
Q

Frequency Polygon

A

Line graph connecting midpoints of histogram bin intervals at the beginning and end

47
Q

Log Scale is used for

A

Time series data that could grow at a compound rate, common when period of time is long or for data that grows rapidly.

48
Q

Which is vertical and which is horizontal, bar and column?

A

Bar is horizontal, column is vertical

49
Q

Pareto chart

A

Column chart of categorical data in descending order of frequency

50
Q

Stacked column chart

A

Bar height is sum of several subtotals

51
Q

Scatter Plot

A

Pairs of observations, starting point for bivariate analysis. Investigate the relationship between 2 variables.

52
Q

Pivot Table

A

Interactive analysis of a data matrix

53
Q

Row and column data types of a pivot table

Variables must be what kind?

A

Categorical or discrete numerical

Numerical

54
Q

Nonzero Origin

A

Exaggerates the trend

55
Q

Elastic graph proportions

A

Exaggerates trend, to avoid, keep aspect ratio below 2.0

56
Q

Difference between bar and column charts

A

Bar is qualitative data and column is numerical

57
Q

Which is least likely to be used in choosing bin frequency?

Sturges’ Rule
Aesthetic Judgement
Nice limits
Always starting at zero

A

Always starting at zero

58
Q

Are line charts used for cross sectional data?

A

No

59
Q

A column chart would not be suitable to display which data?

A

500 company CEO salaries (too many numbers)

Better would be a histogram

60
Q

What kind of data is allowable for a pie chart?

A

Categorical / nominal

61
Q

Sturges’ rule

A

1+3.322 log (number of entries)

62
Q

Attributes of Sturges’ Rule

A

Just a guideline
Purpose is to determine bins to use
Double sample size, then add one bin class

63
Q

Pie Charts are popular in business because (3 reasons)

A

Convey a false sense of science
Can be labeled with data to facilitate interpretation
Can display major changes in parts of a whole

64
Q

Empirical Rule

A

Gaussian distribution (bell shaped)

65
Q

How to estimate sigma (range)?

A

(Xmax-Xmin)/6

66
Q

How to find quartiles?

A

Find the median then the median of the bottom half and the top half.

67
Q

Box Plot

A

Exploratory data analysis based on the 5 data summary, Xmax, Xmin, Q1, Q2, Q3

68
Q

Midhinge

A

Average of first and third quartiles

69
Q

Covariance

A

Measures the degree which values of x and y change together. If they’re unrelated the covariance is zero.

70
Q

Coefficient of Variation

A

Standard deviation / mean

71
Q

Which way skewed if mean > median?

A

Skewed Right

72
Q

Correlation coefficient

A

The standardized value of the covariance

73
Q

T/F The skewness coefficient is zero in a sample from any normal distribution

A

False

74
Q

T/F Coefficient of variation cannot be used when the mean is zero

A

True, because CV = SD/mean

75
Q

T/F Standard Deviation is in same units as the mean?

A

True

76
Q

Geometric mean is?

A

Nth root of data points multiplied together where N is the number of data points

77
Q

Disadvantage of the Range is?

A

Only extreme values are used in its calculation

78
Q

Mode is least appropriate for?

A

Continuous data

79
Q

Which types of statistics offer robust (resistant to outliers) measures of center?

A

Median, Midhinge, Trimmed mean

80
Q

Empirical rule says that….

A

about 32% of the data are beyond one SD from the mean

81
Q

What percentages will lie within the first 3 standard deviations?

A

68%, 95%, 99%

82
Q

Quick formula for estimating the SD?

A

Range / 6 OR (Xmax-Xmin)/6

83
Q

Inner fence calculation

A
Q1-1.5(Q3-Q1) = lower inner fence
Q3+1.5(Q3-Q1) = upper inner fence
84
Q

Outer fence calculation

A
Q1-3.0(Q3-Q1) = lower outer fence
Q3+3.0(Q3-Q1) = upper outer fence
85
Q

Geometric Distribution

A

How many Bernoulli trials would it take to get a the first positive result

86
Q

Hypergeometric Distribution

A

Like Bernoulli but WITHOUT replacement

87
Q

Poisson Distribution

A

Number of occurrences within a specific unit of measure (like time)

88
Q

Bernoulli Experiment

A

Random experiment with only 2 outcomes

89
Q

Uniform Distribution

A

Every outcome has the same change, like rolling a dice

90
Q

Expected Value

A

Each result multiplied by it’s probability and then all added together, does not have to be an actual option or possible result

91
Q

Binomial Distribution SD equation

A

Sq.root(nπ(1-π))