Intro to Business Statistics: Introduction to Statistics - Measurement Scales, Nominal Ordinal Interval Ratio

What This Is

Measurement scales are a fundamental concept in statistics that help us understand the type of data we're working with. In business, knowing the measurement scale of our data is crucial for making informed decisions. For example, a retail chain wants to know if average daily sales exceed $10,000 to determine if they should invest in more inventory. To do this, they need to understand the measurement scale of their sales data.

Key Formulas & Symbols

• Nominal Scale: A scale that assigns labels or categories to data without any inherent order or ranking. Example: X = {A, B, C, D} where X is a variable representing a category (e.g., product type).
• Ordinal Scale: A scale that assigns labels or categories to data with an inherent order or ranking, but no equal intervals between them. Example: X = {Low, Medium, High} where X is a variable representing a level of satisfaction.
• Interval Scale: A scale that assigns labels or categories to data with equal intervals between them, but no true zero point. Example: X = {0, 10, 20, 30} where X is a variable representing temperature in degrees Celsius.
• Ratio Scale: A scale that assigns labels or categories to data with equal intervals between them and a true zero point. Example: X = {0, 10, 20, 30} where X is a variable representing weight in kilograms.
• Z-Score: A measure of how many standard deviations an observation is from the mean. Z = (x? – ?) / (?/?n) where x? = sample mean,-= population mean,-= population standard deviation, n = sample size.
• T-Score: A measure of how many standard errors an observation is from the mean. T = (x? – ?) / (s/?n) where x? = sample mean,-= population mean, s = sample standard deviation, n = sample size.
• Degrees of Freedom (df): The number of observations in a sample minus the number of parameters estimated. df = n - 1 where n is the sample size.

Step-by-Step Procedure

1. State Hypotheses: Clearly define the null and alternative hypotheses.
2. Choose Test: Select the appropriate statistical test based on the measurement scale of the data and the research question.
3. Compute Test Statistic: Calculate the test statistic using the chosen formula.
4. Find p-Value or Critical Value: Determine the p-value or critical value using a statistical table or calculator.
5. Compare to ?: Compare the p-value or critical value to the significance level (? = 0.05).
6. Conclude: Make a decision based on the comparison and interpret the results.

Common Mistakes

• Mistake: Using Z when-is unknown.
• Correction: Use T instead, as it is more robust to non-normality and can handle unknown population standard deviation.
• Mistake: Misinterpreting p-value as probability H? is true.
• Correction: The p-value is the probability of observing the data (or more extreme) if H? is true, not the probability that H? is true.
• Mistake: Failing to check assumptions.
• Correction: Always check for normality, equal variances, and independence before conducting a statistical test.

Quick Practice Problems

1. A marketing firm wants to know if the average age of their customers is greater than 35. They collect a sample of 25 customers with a mean age of 40 and a standard deviation of 5. What is the Z-score? Answer: Z = (40 - 35) / (5/?25) = 2.5. The calculation involves converting the sample mean and standard deviation to a Z-score to determine how many standard deviations away from the population mean the sample mean is.
2. A quality control team wants to know if the average defect rate in a manufacturing process is less than 5%. They collect a sample of 50 units with a mean defect rate of 3% and a standard deviation of 2%. What is the T-score? Answer: T = (3 - 5) / (2/?50) = -2.5. The calculation involves converting the sample mean and standard deviation to a T-score to determine how many standard errors away from the population mean the sample mean is.
3. A retail chain wants to know if the average daily sales exceed $10,000. They collect a sample of 20 days with a mean sales of $12,000 and a standard deviation of $2,000. What is the p-value? Answer: p-value = 0.01. The calculation involves using a statistical table or calculator to determine the p-value associated with the T-score.

Last-Minute Cram Sheet

• Nominal Scale: Assigns labels or categories without order or ranking.
• Ordinal Scale: Assigns labels or categories with an inherent order or ranking.
• Interval Scale: Assigns labels or categories with equal intervals, but no true zero point.
• Ratio Scale: Assigns labels or categories with equal intervals and a true zero point.
• Z-Score: Measures how many standard deviations an observation is from the mean.
• T-Score: Measures how many standard errors an observation is from the mean.
• Degrees of Freedom (df): The number of observations in a sample minus the number of parameters estimated.
• ? = 0.05: The default significance level for most statistical tests.
• p-value is NOT the probability that H? is true – it’s the probability of observing the data (or more extreme) if H? is true.
• Use T instead of Z when-is unknown.
• Always check assumptions before conducting a statistical test.