Descriptive
Inferential
A
Priori
Relative
Frequency
Subjective
Approach
Distribution
Wrong Use of
Statistics Six Common Errors
1)
Ambiguity of Definition
2)
Pictorial representation misleading
3)
Sample Bias
4)
Omission
5)
Logical Error
6)
Technical Error
How to Spot Statistical
Errors
Who is
providing the evidence?
Where
did the data come from
Does it
pass the common sense test?
Has one
of the 6 common Errors been committed?
1)
Rounding
2)
Reordering
3)
Interchange
4)
Summarize
5)
Minimize
6)
Clarify
7)
Verbalize
Rules for Accounting Data
Presentation
1)
Rounding
5)
Minimize
6)
Clarify
7)
Verbalize
Helpful
Not
Helpful
Management
Problems in Data Analysis
1)
The Statistical Gap
2)
Lack of Confidence
3)
Over-complication by the experts
Example of problems faced
1)
Reduce the Data
2)
Re-Present the Data
3)
Build a Model
4)
Exceptions
5)
Comparisons
Measures of Location
(also Called Measures of Central Tendency)
Symmetrical
Distortion
U
shaped Distortion
Reverse
J Distortion
Other
Uses for Measures of Location
Distortion
Measures of Scatter
(also Called Measures of Dispersion)
Range
Interqartile
Range
Mean
Absolute Deviation (MAD)
Variance
Standard
Deviation
Advantages
and Disadvantages of Various Scatter Measurements
Coefficient
of Variation
Skew
Kurtosis
Twyman’s
Law
Part of
the Pattern
Isolated
Events
Indices
(Index)
Simple
Index
How
To
Simple
Aggregate Index
Weighted
Aggregate index
Laspeyres
Index
Paasche
Index
Fixed
weight Index
Opinion poll,
Quality control,
Checking invoices
Simple Random Sampling
Variations
of Simple Random Sampling
Sampling
Frame
Non-response
Bias
Inaccurate measurement
Interviewer bias
Interviewee bias
Instrument bias
1) Mutually exclusive
2) Conditional probability
3) Independent event
4) Multiplication law of
probability for independent events:
5) Combinations
Observed distribution
Standard distribution
Normal
Characteristics
Situation
in which the Binomial Occurs
Deriving
the Binomial Distribution
Using
Binomial tables
Parameters
Deciding
whether Data Fit a Binomial
Characteristics
Situation
in which the Normal Occurs
Deriving
the Normal Distribution
Using
Normal Curve tables
Parameters
Deciding
whether Data Fit a Normal Distribution
Approximating
the Binomial with the Normal
Estimation
Significance
Testing
Applications
of Statistical Inference
Sampling
Distribution of the Mean
Sampling
distribution of the mean from a normal distribution
Sampling
distribution of the mean of non-normal distribution
Formulate
the hypothesis
Collect
a sample of evidence
Decide
on a significance level
Calculate
the probability of the sample evidence occurring
Compare
the probability with the significance level
Significant Tests and
Confidence Levels
Difference in Means of Two
Samples
Difference between Paired
Samples
Reservations
about the Use of Significance Tests
Situations in which the Poisson Occurs
Deciding whether Data Fit a Poisson
Using the Poisson to Approximate the Binomial
Situations in which the t-Distribution
Occurs
Deriving of the t-Distribution
Deciding whether Data have a t-Distribution
Characteristics
Situations
in which the Chi-squared Occurs
Using
Chi-squared Tables
Using
Chi-squared to test differences in Proportions
Characteristics
Situations
in which the F- Distribution Occurs
Using
F- Distribution Tables
Forecasting
Explaining
The
Equation of a Straight Line
Residuals
Four steps in
regression and correlation
Some Reservations about
Regression and Correlation
Similarities and Differences between Simple and
Multiple Regression Dummy Variables
Non-Linear Regression Analysis
Statistical Basis of
Regression and Correlation
Testing that the Residuals Are Random
Deciding which Variables to Retain (in
Multiple Regression)
A Review of
Forecasting Techniques
Short-term
Forecasting
Medium-term
Forecasting
Long-term
Forecasting
Qualitative
Forecasting Techniques
Where Time Series Methods are
Successful
Series with Trend
and Seasonality
Series with Trend,
Seasonality and Cycles
Review of Time Series
Techniques
The manager’s Role in
Forecasting
Guidelines for an
Organization’s Forecasting System
Step1. Analyze the decision-making Systems to be Served by
the Forecast
Step 2 Define what Forecasts Are Needed
Step 3 Develop a Conceptual Model of the Forecasting
Method
Step 4 Ascertain the Data Available (and not Available)
Step 5 Develop the Method by which Forecasts Are to Be
Made
Step 6 Test the Method’s Accuracy
Step 7 Incorporate Judgments into Forecasts
Examples
Using HP10B Calculator for Mean and SD
Average Quantities as the weights Indices
Mutually
Exclusive events (adding)
Conditional
Exclusive events (multiplication)
Poison to Approximate the
Binomial
Regression Analysis to find
Exponential Equation Link sales and time
Measure closeness of fit Annova
Decomposition Method Quarterly