Exam 1 Flashcards
What is Predictive Analytics? (3)
- analyze past performance
- extrapolates to future
- predicts risks
What is the difference between Mean and Median?
Mean is affected by outliers while Median is not
What is a sample point?
The most basic outcome of an experiment
What is Descriptive Analytics? (3)
- uses data to understand past and present
- summarizes data into meaningful charts and reports
- identify patterns and trends in data
What is Prescriptive analytics? (2)
- uses optimization techniques to identify best alternatives
- often combined with predictive analytics to account for risk
Chebyshev’s Theorem Equation
1 - 1/k^2
What is the purpose of sampling?
we cannot get all the data, all the time, in the real world we get only a small portion of the data
What is the mean?
The average value of a data set
What is the median?
Find the middle number in a data set
What is covariance?
used to determine how much two random variables go together
What is correlation?
used to determine when a change in one variable can result in a change in another
What do correlation and covariance have in common?
they both measure linear relationships between variables
What are the two sampling methods?
Subjective Methods and Probability Sampling
What are the two types of subjective methods for sampling?
judgment sampling and convenience sampling
Judgement Sampling
Expert Judgement is used
Convenience Sampling
Collect sample based on convenience
4 Types of Statistical Sampling
1) Systematic (periodic) sampling
2) Stratified Sampling
3) Cluster Sampling
4) Sampling from a continuous process
Systematic (Periodic) sampling
selects every nth item from a population
Stratified Sampling
population divided into subsets and allocates specific proportion of samples to each subset
Cluster Sampling
divide the population into clusters and sample a set of clusters
Sampling from a continuous process
- fix the time and select n items after that time or selected next item after each
What is a sampling error?
a statistical error that occurs due to the sample not being well represented
T/F: a good example of independent events are rolling a dice or flipping a coin
TRUE
What does a union look like and what does it do?
- looks like a “U”
- OR statement
What does an intersection look like and what does it do?
- looks like an “n”
- AND statement
Type I error is a
false positive
incorrectly reject H0
(person put in jail that is innocent)
Type II error is…
false negative
incorrectly fails to reject H0
(person found not guilty when actually guilty)
How do you write a null hypothesis?
you hypothesize that no change will occur
if the p-value is less than alpha you…
reject the null
if the p-value is greater than or equal to alpha you…
fail to reject the null
the probability of obtaining results as extreme as the observed results of a statistical test is…
the p-value
the significance level (set by the researcher or stated) is…
alpha
The maximum number of logically independent values, which are values that have the freedom to vary, in the sample data is…
df (degrees of freedom)
(N columns - 1) * (N rows - 1)
Hypothesis testing is done under the assumption the null hypothesis is…
TRUE
p-value written as probability statement
P(sample s | H0 True)
Four types of data based on measurement scale
- Categorical (Nominal)
- Ordinal
- Interval
- Ratio
Two Types of Categorical Data
- Nominal
- Ordinal
Two types of numerical data
- Interval
- Ratio
What is Categorical (nominal) data?
data placed in categories according to a specified characteristic
ex: product types, storage locations, gender
What is Ordinal Data?
Data that is ranked or ordered according to some relationship with one another
ex: customer satisfaction levels, risk levels, t-shirt size
What is Interval Data?
Ordinal data but with constant differences between observations & has NO TRUE ZERO POINT
ex: PH scale, time on a 12 hour clock
What is Ratio Data?
continuous values and have natural zero point
ex: monthly sales, height, weight, time spent