How to identify variables and sample size

Introduction to Linear Regression Analysis

• Linear regression analysis helps answer business questions through predictive modeling.

• Define data element characteristics crucial for research findings review.

Data Element Characteristics

• Independent Variable (X):

  • Refers to the variable that is used to predict another variable.

  • In this case, the independent variable is Click Through Rate (CTR).

• Dependent Variable (Y):

  • Refers to the variable that is predicted or expected to change based on other variables.

  • In this case, the dependent variable is Weekly Sales.

• Sample Size:

  • The total number of observations available for analysis.

  • Defined as 52 for this analysis, representing 52 weeks of data collection.

• Level of Measurement:

  • Identifies the nature of the data and how it can be analyzed.

  • In this case, the level of measurement for both variables is Ratio.

Understanding the Variables

• Click Through Rate (CTR):

  • Measures the frequency at which customers click on an online advertisement that leads them to the point of sale.

  • It serves as the independent variable predicting sales performance.

• Weekly Sales:

  • Represents the revenue generated in a single week from sales activities.

  • This serves as the dependent variable being predicted.

Predictive Relationship

• Key question: What are we trying to predict?

  • As business decision-makers, the goal is to predict Weekly Sales based on other influencing variables.

Variable Identification in Graphs

• The X-axis in a scatter plot graphs the independent variable (Click Through Rate).

• The Y-axis in a scatter plot graphs the dependent variable (Weekly Sales).

Consistency in Data Naming

• Importance of using the variable names as per spreadsheet headers.

• Maintain consistency between variables used in the analysis and those represented in graphics.

Sample Size Clarification

• Sample size is strictly based on observations.

• 52 observations, not defined by time frame (e.g., weeks) or frequency of measurement.

Conclusion on Variables and Measurement

• Clarity on variable definitions, sample size, and level of measurement is essential for accurate linear regression analysis.

• Familiarity with measurement levels ensures data is used and interpreted correctly.