Title | ECO 045 Exam 1 Study Guide |
---|---|
Author | Kelly Jacobs |
Course | Statistical Methods |
Institution | Lehigh University |
Pages | 8 |
File Size | 424.1 KB |
File Type | |
Total Downloads | 66 |
Total Views | 930 |
Download ECO 045 Exam 1 Study Guide PDF
Chapter 1 Descriptive statistics- describes large amounts of data concisely Inferential statistics- drawing conclusions about an entire population from a small sample Categorical- can be grouped by specific categories, labels, and names Quantitative- uses numeric values ↳ Discrete - only certain values (ex. family size) ↳ Continuous - gets increasingly more precise (ex. height) Nominal- qualitative data Ordinal- order is meaningful (ex. rating 1-5) Interval scale- distance between values is meaningful and measurable (ex. 32°F is not half as cold as 64°F) Ratio scale- distance can be used to compare (ex. 50K salary is 2x as much money as 25K)
Mean- average value Median- middle value Mode- most frequently occurring value Frequency distribution- shows frequency of observations ↳ Relative frequency- fraction or proportion of the total number, should all add up to 1 ↳ Relative % frequency - relative frequency as a % (multiply x 100) ↳ Cumulative frequency- number of items with values less than or equal to the upper limit of each class
Frequency
Relative Frequency
Relative % Frequency
Cumulative % Frequency
Bear
17
.18
18%
18%
Card
8
.09
9%
27%
Chocolate
42
.46
46%
73%
Wine
25
.27
27%
100%
Total
92
1
100%
Chapter 2 Categorical Data ↳ Frequency distribution ↳ Relative frequency distribution ↳ % frequency distribution ↳ Bar chart ↳ Pie Chart Pareto diagram- when bar chart bars are arranged in descending order of height left to right Qualitative Data ↳ Frequency distribution ↳ Relative frequency distribution ↳ % frequency distribution ↳ Cumulative distribution ↳ Histogram When creating a distribution, determine: 1. # of non-overlapping categories 2. Width of each class 3. Class limits
width =
largest data value − smallest # of classes
Open end class- requires only upper or lower class limit (ex. grades 60 or less)
Kurtosis- length of tails Spread- minimum value minus maximum value Cross tabulation - summarizes data for two variables, can be used with both qualitative and quantitative data
Side by side bars
Stacked bars
Trend Lines
Scatterplots and Correlations
Chapter 3 Population parameters - measures computed data from a population Sample statistic- measures computed data from a sample
Mean Variance Standard Deviation
Sample
Population
x
μ
S
2
S
σ
2
σ
Trimmed mean- remove smallest and largest values Weighted mean- more value/weight given to some values (ex. 3 vs 4 credit classes and GPA)
Geometric mean- used to analyze growth rates to determine mean rate of change
√(x1)(x2)...(xn) n
Quartiles- puts percentiles into four groups of 25% Deciles- puts percentiles into ten groups of 10% Percentile calculation-
p
i = ( 100 )n + 1
= number of values i = value at p percentile n
IQR- middle 50% Variance- s2
=
Σ(x−x) 2 or n−1
Standard deviation-
σ2 =
Σ(x−μ) 2 N
√s2
Coefficient of variance-
( sx x 100)%
or
( μσ x 100)%
Normal Distribution ↳ Mean = median = mode ↳ Skewness = 0 Z-score - number of standard deviations from the mean
x−μ σ or
x−x s
Empirical Rule- version of Chebyshev’s Theorem for Normal distribution ↳ 68.26% within 1 SD ↳ 95.44% within 2 SD ↳ 99.72% within 3 SD Outlier- more than 3 SD off from the mean Covariance- linear association between two variables ↳ between -1 and 1 ↳ more extreme = stronger
sxy =
Σ (xi −x)(yi −y) or n−1
σ xy =
Σ (xi−μ x)(y i−μ y ) n−1
Chapter 4 Experiment- chance process (ex. flip a coin) Event- outcome of a chance process (ex. coin lands on heads) Sample space- all possible outcomes of a chance process Probability- numerical likelihood 0-1 Types of Experiments ↳ Classical - each outcome is equally possible, probability is number of successes divided by total outcomes ∞
↳ Relative frequency- limit of relative frequency as # of trials gets larger
∫
0
s n
↳ Subjective - degree of confidence or rational belief
Types of Events ↳ Simple (ex. rolling two dice that add up to 2) vs compoundevents (ex. rolling two dice that add up to 7) ↳ Mutually exclusive- if one event happens, another can’t, P(A∩B) = 0 ↳ Statistically independent- one event has no effect on the other, P(A) = P(A|B) ↳ Complementary - both events cannot happen but one will, P(A∩B) = 0 and P(A ⋃B) = 1
Symbol
Meaning
P(A)
Probability A will happen
P(Ā)
Probability A will not happen
P(A|B)
Probability A will happen given B happens
P(A’)
Probability the complement of A will happen
P(A∩B)
Probability A and B will both happen
P(A ⋃B)
Probability A or B will happen
P(A ⋃B) = P(A) + P(B) - P(A∩B) P(A∩B) = P(B) * P(A|B) or P(A) * P(B) when A and B are statistically independent
P(A|B) =
P (A∩B) P (B )...