Business Statistics Chapter 1 Notes

Chapter 1: Data and Statistics

  • This chapter serves as an introduction to BUQU 1230: Business Statistics, as taught by Guoren Zhang of the Kwantlen Polytechnic University School of Business.

  • The primary topics covered include:

    • Applications of statistics in the fields of business and economics.

    • The fundamental definition and structure of data.

    • Descriptive statistics (tabular, graphical, and numerical).

    • The concepts and processes of statistical inference.

    • The role of Microsoft Excel in professional statistical analysis.

Applications in Business and Economics

  • Accounting:

    • Public accounting firms utilize statistical sampling procedures during audits for their clients. This allows auditors to evaluate accounts without examining every single transaction.

  • Economics:

    • Economists rely on statistical information to generate forecasts regarding the future of the overall economy or specific facets of it.

  • Production:

    • Statistical quality control charts are employed to observe and monitor the output of various production processes to ensure consistency and quality.

  • Marketing:

    • Retailers utilize electronic point-of-sale scanners at checkout counters to gather data. This information is used for diverse marketing research applications and consumer behavior analysis.

Data and Data Sets

  • Data:

    • Defined as the facts and figures that are collected, summarized, analyzed, and interpreted.

  • Data Set:

    • This term refers to the entire collection of data obtained for a specific study.

Elements, Variables, and Observations

  • Elements:

    • These are the specific entities on which data are collected.

  • Variable:

    • A variable is a particular characteristic of interest associated with the elements being studied.

  • Observation:

    • An observation is the set of measurements collected for a single element.

  • Data Volume:

    • In a complete data set, the total number of data values is calculated by multiplying the number of elements by the number of variables.

    • A data set containing nn elements will necessarily contain nn observations.

  • Example Comparison (Slide 7):

    • For companies Dataram, EnergySouth, Keystone, LandCare, and Psychemedics:

      • Element Names: The names of the individual companies (e.g., Dataram).

      • Variables: Stock Exchange, Annual Sales (MM), and Earnings per Share ().\n - **Data Set**: The collective table of all listed values for these companies.\n\n# Scales of Measurement\n\n- The scale dictates which data summarization techniques and statistical analyses are appropriate for the data set.\n- **Nominal Scale**:\n - Data are labels or names used to identify an attribute of the element.\n - These may use non-numeric labels or numeric codes.\n - Example: Classifying university students by their enrolled school (e.g., Business, Humanities, Education). A numeric code might use 1forBusiness,for Business,2 for Humanities, etc.\n- **Ordinal Scale**:\n - This scale possesses the properties of nominal data, but the order or rank of the data holds meaningful significance.\n - These may use non-numeric labels or numeric codes.\n - Example: Classifying university students by class standing (e.g., Freshman, Sophomore, Junior, Senior). A numeric code might assign 1toFreshman,to Freshman,2 to Sophomore, etc.\n- **Interval Scale**:\n - Interval data are always numeric.\n - This scale has the properties of ordinal data, and the interval between observations is expressed in terms of a fixed unit of measure.\n - Example: GRE scores. If Melissa has a score of 1205andKevinhasascoreofand Kevin has a score of1090,Melissascoredexactly, Melissa scored exactly115 points higher than Kevin.\n- **Ratio Scale**:\n - This scale has all the properties of interval data, and the ratio between two values is mathematically meaningful.\n - Variables such as distance, height, weight, and time use this scale.\n - A ratio scale must contain a zero value that indicates that nothing exists for the variable at that specific zero point.\n - Example: College credit hours. If Melissa has earned 36credithoursandKevinhasearnedcredit hours and Kevin has earned72, it is meaningful to state that Kevin has earned twice as many credits as Melissa.\n\n# Categorical and Quantitative Data\n\n- Data is broadly classified into two categories, which determines the appropriate statistical analysis. Generally, quantitative data allows for more analytical alternatives.\n- **Categorical Data**:\n - These are labels or names used to identify an attribute of each element.\n - It is often referred to as **qualitative data**.\n - It employs either the nominal or ordinal scale of measurement.\n - It can be either numeric (for coding) or non-numeric.\n - Statistical analysis options for categorical data are relatively limited.\n- **Quantitative Data**:\n - These data indicate "how many" or "how much."\n - **Discrete**: Used when measuring "how many" (countable items).\n - **Continuous**: Used when measuring "how much" (unbroken scales).\n - Quantitative data are always numeric.\n - Ordinary arithmetic operations (addition, subtraction, etc.) are meaningful for this data type.\n\n# Time Series Data\n\n- Time series data are observations collected over several consecutive time periods.\n- Example: A data set detailing the specific number of building permits issued in Surrey, BC, for each of the last 36 months.\n\n# Descriptive Statistics\n\n- Descriptive statistics consist of tabular, graphical, and numerical methods used to effectively summarize and present data.\n- **Example Study: Hudson Auto Repair**:\n - A manager surveyed 50 customer invoices for engine tune-ups to understand the cost of parts (rounded to the nearest dollar).\n - Sample data points provided include values such as: 91, 78, 93, 57, 75, 52, 99, 80, 97, 62, 71, 69, 72, 89, 66, 75, 79, 75, 72, 76, 104, 74, 62, 68, 97, 105, 77, 65, 80, 109, 85, 97, 88, 68, 83, 68, 71, 69, 67, 74, 62, 82, 98, 101, 79, 105, 79, 69, 62, 73.\n- **Tabular Summary (Frequency and Percent Frequency)**:\n - Parts Cost (50-59):Frequency=): Frequency =2,PercentFrequency=, Percent Frequency =4\%((\frac{2}{50} \times 100).\n - Parts Cost (60-69):Frequency=): Frequency =13,PercentFrequency=, Percent Frequency =26\%.\n - Parts Cost (70-79):Frequency=): Frequency =16,PercentFrequency=, Percent Frequency =32\%.\n - Parts Cost (80-89):Frequency=): Frequency =7,PercentFrequency=, Percent Frequency =14\%.\n - Parts Cost (90-99):Frequency=): Frequency =7,PercentFrequency=, Percent Frequency =14\%.\n - Parts Cost (100-109):Frequency=): Frequency =5,PercentFrequency=, Percent Frequency =10\%.\n - **Total**: Frequency = 50,PercentFrequency=, Percent Frequency =100\%.\n- **Graphical Summary**:\n - A **Histogram** is used to show the distribution of the parts costs, with the y-axis representing frequency and the x-axis representing cost intervals.\n- **Numerical Descriptive Statistics**:\n - The most common numeric statistic is the **average (or mean)**.\n - For Hudson Auto, the average cost of parts based on the sample of 50tune−upsiscalculatedastune-ups is calculated as\$79(thesumofallcostvaluesdividedby(the sum of all cost values divided by50).\n\n# Statistical Inference\n\n- **Population**: The complete set of all elements of interest in a particular study.\n- **Sample**: A subset of the population used for analysis.\n- **Census**: The process of collecting data for an entire population.\n- **Sample Survey**: The process of collecting data specifically for a sample.\n- **Statistical Inference**: The process of using data obtained from a sample to make estimates and test hypotheses regarding the characteristics of the larger population.\n- **Inference Process (Hudson Auto Example)**:\n 1. **Population**: Consists of all tune-ups. The true average cost of parts for all possible tune-ups is unknown.\n 2. **Sample**: A sample of 50 engine tune-ups is selected and examined.\n 3. **Sample Data**: Provides a sample average parts cost of \$79$$ per tune-up.

    1. Inference: The sample average is used to estimate the unknown population average.

Statistical Analysis Using Microsoft Excel

  • Due to the large volume of data typically involved in statistical analysis, computer software is essential.

  • Modern spreadsheet packages like Microsoft Excel are used because they are capable of efficient data management, detailed analysis, and visual presentation.

  • Microsoft Excel is currently the most widely available spreadsheet software within business organizations.