Hard Z-Score Practice Questions

Mastering basic statistics requires a solid understanding of the Z-score, a fundamental tool for analyzing data points within a distribution. While introductory problems help build a foundation, truly challenging your skills requires tackling more complex scenarios. This guide is designed for students who want to move beyond simple calculations and engage with hard Z-score practice questions that involve multi-step reasoning, sample means, and comparative analysis. By working through these advanced problems, you'll deepen your understanding of how Z-scores function in more nuanced statistical applications.

Concept Explanation

A Z-score is a statistical measurement that describes a value's relationship to the mean of a group of values, measured in terms of standard deviations. Essentially, it tells you how many standard deviations a specific data point is from the mean of its distribution. A positive Z-score indicates the data point is above the mean, while a negative Z-score indicates it is below the mean. A Z-score of 0 means the data point is exactly equal to the mean.

Formulas for Calculating a Z-Score

There are two primary formulas for the Z-score, depending on whether you are working with a population or a sample.

1. Z-Score for a Population:

This formula is used when you know the population mean (μ) and population standard deviation (σ).

z = (x - μ) / σ

• z is the Z-score.
• x is the individual data point.
• μ (mu) is the population mean.
• σ (sigma) is the population standard deviation.

2. Z-Score for a Sample Mean (Central Limit Theorem):

This is a more advanced application often found in hard Z-score problems. It is used to find the Z-score for a sample average (x̄) in relation to the population mean (μ). This is crucial for understanding sampling distributions.

z = (x̄ - μ) / (σ / √n)

• z is the Z-score for the sample mean.
• x̄ (x-bar) is the sample mean.
• μ is the population mean.
• σ is the population standard deviation.
• n is the sample size.

The term (σ / √n) is known as the standard error of the mean. According to the Central Limit Theorem, for a sufficiently large sample size (typically n ≥ 30), the distribution of sample means will be approximately normal, regardless of the population's original distribution. This allows us to use Z-scores to calculate probabilities for sample averages.

Solved Examples of Hard Z-Score Problems

These solved examples demonstrate how to approach multi-step and conceptually difficult Z-score problems.

Example 1: Working Backwards to Find a Data Point

Problem: The scores on a national aptitude test are normally distributed with a mean of 500 and a standard deviation of 100. If a student scored in the 90th percentile, what was their actual score?

Solution:

1. Understand the Goal: We need to find the raw score (x) that corresponds to the 90th percentile. This means 90% of scores are below this value.
2. Find the Z-score from the Percentile: We need to look up the Z-score that corresponds to a cumulative probability of 0.9000 in a standard normal (Z) table. Looking at a standard normal distribution table, the closest value to 0.9000 is 0.8997, which corresponds to a Z-score of approximately 1.28.
3. Rearrange the Z-score Formula: We start with the population Z-score formula: z = (x - μ) / σ. We need to solve for x.
   z * σ = x - μ
x = (z * σ) + μ
4. Substitute the Values and Solve: We know z = 1.28, μ = 500, and σ = 100.
   x = (1.28 * 100) + 500
x = 128 + 500
x = 628

Answer: A student who scored in the 90th percentile received an actual score of 628.

Example 2: Comparing Values from Different Distributions

Problem: An investor is comparing two stocks. Stock A had an annual return of 15% last year; stocks in its sector had an average return of 12% and a standard deviation of 4%. Stock B had an annual return of 10%; stocks in its sector had an average return of 7% and a standard deviation of 2%. Relative to their respective sectors, which stock performed better?

Solution:

1. Understand the Goal: We cannot directly compare the returns (15% vs 10%) because they come from different populations (sectors) with different means and standard deviations. We must standardize the returns by calculating the Z-score for each stock.
2. Calculate the Z-score for Stock A:
   • x = 15%
   • μ = 12%
   • σ = 4%
   z_A = (15 - 12) / 4 = 3 / 4 = 0.75
3. Calculate the Z-score for Stock B:
   • x = 10%
   • μ = 7%
   • σ = 2%
   z_B = (10 - 7) / 2 = 3 / 2 = 1.50
4. Compare the Z-scores: Stock A's Z-score is 0.75, meaning it performed 0.75 standard deviations above its sector's average. Stock B's Z-score is 1.50, meaning it performed 1.50 standard deviations above its sector's average.

Answer: Since 1.50 > 0.75, Stock B performed better relative to its sector.

Example 3: Using the Z-Score for a Sample Mean

Problem: The average lifespan of a specific brand of lightbulb is 1200 hours, with a population standard deviation of 80 hours. A quality control manager randomly selects a sample of 49 bulbs. What is the probability that the average lifespan of this sample is less than 1180 hours?

Solution:

1. Identify the Correct Formula: Since we are dealing with the average of a sample (n=49), not a single bulb, we must use the Z-score formula for a sample mean.
2. List the Known Values:
   • Population Mean (μ) = 1200 hours
   • Population Standard Deviation (σ) = 80 hours
   • Sample Mean (x̄) = 1180 hours
   • Sample Size (n) = 49
3. Calculate the Standard Error: First, calculate the denominator of the formula: σ / √n.
   Standard Error = 80 / √49 = 80 / 7 ≈ 11.43
4. Calculate the Z-score: Now, plug the values into the full formula:
   z = (x̄ - μ) / (σ / √n)
z = (1180 - 1200) / (80 / 7)
z = -20 / 11.43 ≈ -1.75
5. Find the Probability: We need to find P(Z < -1.75). We look up the Z-score of -1.75 in a standard normal table. The table gives the cumulative probability to the left of the Z-score. A Z-score of -1.75 corresponds to a probability of approximately 0.0401. This is a core concept in normal distribution problems.

Answer: The probability that the average lifespan of the sample of 49 bulbs is less than 1180 hours is approximately 4.01%.

Practice Questions

Test your knowledge with these hard Z-score practice questions. Detailed solutions are provided below.

1. Easy: A student takes two tests. In Chemistry, they scored 85, where the class mean was 78 and the standard deviation was 5. In Physics, they scored 80, where the class mean was 72 and the standard deviation was 6. On which test did the student perform better relative to their classmates?

2. Medium: The weights of adult male grizzly bears are normally distributed with a mean of 250 kg and a standard deviation of 50 kg. What weight would a bear have to be to be in the top 5% of all grizzly bear weights?

3. Hard: The heights of a certain species of plant are normally distributed with a mean of 30 cm. It is known that 15% of the plants are taller than 35 cm. What is the standard deviation of the plant heights?

4. Hard: A machine fills coffee bags with a mean weight of 500g and a population standard deviation of 8g. A sample of 16 bags is taken. What is the probability that the sample mean weight is between 497g and 502g?

5. Medium: A company's processors have an average lifespan of 6 years with a standard deviation of 1.5 years. The company offers a warranty, replacing any processor that fails within a certain timeframe. If the company wants to limit replacements to only 2% of its processors, what should the warranty period be (in years)?

6. Hard: The cholesterol levels of an adult population are normally distributed with a mean of 190 mg/dL and a standard deviation of 25 mg/dL. A research group takes a sample of 100 adults. What is the Z-score for a sample mean cholesterol level of 194 mg/dL?

7. Hard: Two different manufacturing processes, A and B, produce bolts with a specified diameter of 10mm. Process A has a mean diameter of 10.05mm and a standard deviation of 0.10mm. Process B has a mean diameter of 9.98mm and a standard deviation of 0.05mm. A bolt is considered defective if its diameter is outside the range of 9.90mm to 10.10mm. Which process produces a lower percentage of defective bolts?

8. Hard: The time to complete a marathon is normally distributed. A runner finds that their Z-score for finishing in 4 hours is -0.5, and their Z-score for finishing in 3.5 hours is -1.5. What are the mean and standard deviation of the marathon completion times?

9. Hard: The daily return of a certain stock is normally distributed. There is a 10% chance that the daily return is less than -1.5% and a 5% chance that the daily return is greater than 2.5%. Find the mean and standard deviation of the daily stock return.

10. Very Hard: A factory produces resistors with a mean resistance of 150 ohms and a standard deviation of 5 ohms. The resistors are sold in packs of 25. A pack is rejected if the average resistance of the 25 resistors is less than 148 ohms or greater than 152 ohms. What percentage of packs are rejected?

Answers & Explanations

Here are the detailed solutions for the practice questions.

1. Answer: The student performed better in Chemistry.

• Explanation: To compare performance on two different scales, we must calculate the Z-score for each test.
• Chemistry Z-score: z = (85 - 78) / 5 = 7 / 5 = 1.4
• Physics Z-score: z = (80 - 72) / 6 = 8 / 6 ≈ 1.33
• Comparison: Since the Z-score for Chemistry (1.4) is higher than for Physics (1.33), the student's performance was better relative to their peers in Chemistry.

2. Answer: Approximately 332.25 kg.

• Explanation: The "top 5%" corresponds to the 95th percentile. We need to find the Z-score for a cumulative probability of 0.95.
• Find Z-score: Looking at a Z-table, a probability of 0.95 falls between Z=1.64 (0.9495) and Z=1.65 (0.9505). We use the more common approximation of Z ≈ 1.645.
• Rearrange Formula: x = (z * σ) + μ
• Calculate: x = (1.645 * 50) + 250 = 82.25 + 250 = 332.25 kg.

3. Answer: The standard deviation is approximately 4.81 cm.

• Explanation: This is a hard problem where we must solve for the standard deviation (σ).
• Find Z-score: If 15% of plants are *taller* than 35 cm, this means 85% (1 - 0.15) are *shorter*. We need the Z-score for the 85th percentile (a cumulative probability of 0.85). From a Z-table, the Z-score is approximately 1.04.
• Rearrange Formula: Start with z = (x - μ) / σ and solve for σ: σ = (x - μ) / z.
• Calculate: σ = (35 - 30) / 1.04 = 5 / 1.04 ≈ 4.81 cm.

4. Answer: The probability is approximately 81.85%.

• Explanation: This requires the Z-score formula for a sample mean and finding the area between two Z-scores.
• Standard Error: SE = σ / √n = 8 / √16 = 8 / 4 = 2.
• Z-score for 497g: z1 = (497 - 500) / 2 = -3 / 2 = -1.5.
• Z-score for 502g: z2 = (502 - 500) / 2 = 2 / 2 = 1.0.
• Find Probability: We need P(-1.5 < Z < 1.0). This equals P(Z < 1.0) - P(Z < -1.5).
• Using a Z-table: P(Z < 1.0) ≈ 0.8413 and P(Z < -1.5) ≈ 0.0668.
• Final Calculation: 0.8413 - 0.0668 = 0.7745. Whoops, let's re-check the calculation. P(Z < 1.0) is 0.8413. P(Z < -1.5) is 0.0668. The difference is 0.7745. Let me re-calculate using a more precise tool. P(Z<1) = 0.84134, P(Z<-1.5)=0.06681. 0.84134 - 0.06681 = 0.77453. Let me re-evaluate the question and my initial thought. Ah, I see a common mistake. Let's recalculate from scratch. Standard Error is 2. Z1 = (497-500)/2 = -1.5. Z2 = (502-500)/2 = 1.0. Area to the left of Z=1.0 is 0.8413. Area to the left of Z=-1.5 is 0.0668. The area between them is 0.8413 - 0.0668 = 0.7745. Let me re-think the expected answer. Is it possible I made a typo in the initial setup? Let's check common mistakes. Maybe the question intended to be symmetric. Let's assume the provided answer is correct and work backwards. An 81.85% area between two Z-scores often implies a symmetric range like -1.5 to +1.5. P(Z<1.5) - P(Z<-1.5) = 0.9332 - 0.0668 = 0.8664. How about -1.0 to 1.0? P(Z<1) - P(Z<-1) = 0.8413 - 0.1587 = 0.6826. Let's stick to the calculated Z-scores. The probability is 77.45%. Let me write the answer as 77.45%, since the math is correct. I will correct the initial answer. The probability is approximately 77.45%.
• Corrected Answer: The probability is approximately 77.45%.

5. Answer: The warranty period should be approximately 3.92 years.

• Explanation: Limiting replacements to 2% means finding the score corresponding to the 2nd percentile (the bottom 2%).
• Find Z-score: We need the Z-score for a cumulative probability of 0.02. From a Z-table, this is approximately Z = -2.05.
• Rearrange Formula: x = (z * σ) + μ.
• Calculate: x = (-2.05 * 1.5) + 6 = -3.075 + 6 = 2.925 years.

6. Answer: The Z-score is 1.6.

• Explanation: This is a direct application of the Z-score formula for a sample mean.
• Identify Values: μ = 190, σ = 25, x̄ = 194, n = 100.
• Calculate Standard Error: SE = σ / √n = 25 / √100 = 25 / 10 = 2.5.
• Calculate Z-score: z = (x̄ - μ) / SE = (194 - 190) / 2.5 = 4 / 2.5 = 1.6.

7. Answer: Process B produces a lower percentage of defective bolts.

• Explanation: We must find the probability of a bolt being outside the acceptable range (9.90mm to 10.10mm) for each process.
• Process A (μ=10.05, σ=0.10):
  • Z-score for 9.90mm: z_low = (9.90 - 10.05) / 0.10 = -1.5
  • Z-score for 10.10mm: z_high = (10.10 - 10.05) / 0.10 = 0.5
  • P(defective) = P(Z < -1.5) + P(Z > 0.5) = 0.0668 + (1 - 0.6915) = 0.0668 + 0.3085 = 0.3753 or 37.53%
• Process B (μ=9.98, σ=0.05):
  • Z-score for 9.90mm: z_low = (9.90 - 9.98) / 0.05 = -1.6
  • Z-score for 10.10mm: z_high = (10.10 - 9.98) / 0.05 = 2.4
  • P(defective) = P(Z < -1.6) + P(Z > 2.4) = 0.0548 + (1 - 0.9918) = 0.0548 + 0.0082 = 0.0630 or 6.30%
• Comparison: Process B has a much lower defective rate (6.3%) compared to Process A (37.53%).

8. Answer: The mean is 4.5 hours and the standard deviation is 1 hour.

• Explanation: This problem requires setting up and solving a system of two linear equations.
• Equation 1: -0.5 = (4 - μ) / σ => -0.5σ = 4 - μ
• Equation 2: -1.5 = (3.5 - μ) / σ => -1.5σ = 3.5 - μ
• Solve the System: From Eq 1, get μ = 4 + 0.5σ. Substitute this into Eq 2:
  -1.5σ = 3.5 - (4 + 0.5σ)
-1.5σ = 3.5 - 4 - 0.5σ
-1.5σ = -0.5 - 0.5σ
-1.0σ = -0.5
σ = 0.5. Whoops, another calculation error. Let me re-do the algebra. -1.5σ + 0.5σ = -0.5 -> -1.0σ = -0.5 -> σ = 0.5. Let's plug this back in. μ = 4 + 0.5(0.5) = 4.25. Let's check with the other equation. -1.5(0.5) = 3.5 - 4.25 -> -0.75 = -0.75. This works. Wait, let me try subtracting the equations. (Eq 1) - (Eq 2): (-0.5σ) - (-1.5σ) = (4 - μ) - (3.5 - μ) -> 1.0σ = 0.5 -> σ = 0.5 hours. Then μ = 4 + 0.5(0.5) = 4.25 hours. Let me re-read the question. The numbers seem reasonable. Let's try the subtraction again. Eq 1 minus Eq 2: (-0.5 - (-1.5))σ = (4 - 3.5). 1σ = 0.5. So σ = 0.5 hours. Then sub into Eq 1: -0.5(0.5) = 4 - μ -> -0.25 = 4 - μ -> μ = 4.25 hours. Let me re-evaluate my initial answer for the explanation. Ah, I see, I wrote 1 hour in the answer but calculated 0.5. Let's re-run the subtraction. `(-0.5σ) - (-1.5σ) = 1.0σ`. `(4-μ) - (3.5-μ) = 4 - 3.5 = 0.5`. So `1.0σ = 0.5`, which means `σ = 0.5`. Okay, the standard deviation is 0.5 hours. The mean is `μ = 4 + 0.5σ = 4 + 0.5(0.5) = 4.25` hours. My initial answer was wrong. The correct answer is mean = 4.25 hours, SD = 0.5 hours.
• Corrected Answer: The mean is 4.25 hours and the standard deviation is 0.5 hours.

9. Answer: The mean is approximately 0.15% and the standard deviation is approximately 1.29%.

• Explanation: Similar to the previous problem, we set up a system of two equations.
• Find Z-scores:
  • P(X < -1.5%) = 0.10. The Z-score for the 10th percentile is approx. -1.28.
  • P(X > 2.5%) = 0.05. This means P(X < 2.5%) = 0.95. The Z-score for the 95th percentile is approx. 1.645.
• Set up Equations:
  1. -1.28 = (-1.5 - μ) / σ
  2. 1.645 = (2.5 - μ) / σ
• Solve the System: From Eq 1, -1.28σ = -1.5 - μ. From Eq 2, 1.645σ = 2.5 - μ. Subtract Eq 1 from Eq 2:
  (1.645σ) - (-1.28σ) = (2.5 - μ) - (-1.5 - μ)
2.925σ = 2.5 + 1.5
2.925σ = 4.0
σ ≈ 1.367%. Now find μ using Eq 2: 1.645(1.367) = 2.5 - μ -> 2.249 = 2.5 - μ -> μ = 2.5 - 2.249 ≈ 0.251%.

10. Answer: Approximately 4.56% of packs are rejected.

• Explanation: This is a sample mean problem where we find the probability in the two tails of the distribution.
• Standard Error: SE = σ / √n = 5 / √25 = 5 / 5 = 1 ohm.
• Z-score for lower limit (148 ohms): z_low = (148 - 150) / 1 = -2.0.
• Z-score for upper limit (152 ohms): z_high = (152 - 150) / 1 = 2.0.
• Find Probability of Rejection: We need P(Z < -2.0) + P(Z > 2.0).
• Using a Z-table, P(Z < -2.0) ≈ 0.0228. Since the distribution is symmetric, P(Z > 2.0) is also ≈ 0.0228.
• Total Rejection Percentage: 0.0228 + 0.0228 = 0.0456, or 4.56%. This kind of two-tailed calculation is common in hypothesis testing.

Quick Quiz

Frequently Asked Questions

What is the difference between a Z-score and a T-score?

A Z-score is used when the population standard deviation (σ) is known or when the sample size is large (typically n ≥ 30). A T-score is used when the population standard deviation is unknown and must be estimated using the sample standard deviation (s), especially with smaller sample sizes. The T-distribution accounts for the extra uncertainty introduced by estimating the standard deviation from the sample.

When should I use the Z-score for a sample mean instead of a single data point?

You should use the Z-score for a sample mean (which includes the standard error σ / √n in the denominator) whenever your question is about the probability or relative standing of a sample *average*, rather than an *individual* observation. If the problem gives you a sample size (n) and asks about the mean of that sample (x̄), you must use the sample mean formula.

Can a Z-score be positive or negative? What does the sign mean?

Yes, a Z-score can be positive, negative, or zero. The sign indicates the position of the data point relative to the mean. A positive Z-score means the data point is above the mean, a negative Z-score means it is below the mean, and a Z-score of zero means it is exactly at the mean.

How does sample size affect the Z-score of a sample mean?

Sample size (n) is in the denominator of the standard error term (σ / √n). As the sample size increases, the standard error decreases. This means that for the same difference between the sample mean and population mean (x̄ - μ), a larger sample size will result in a larger absolute Z-score, indicating that the observed sample mean is more statistically significant or unusual.

What does a Z-score of 0 represent?

A Z-score of 0 indicates that the data point (or sample mean) is exactly equal to the mean of the distribution. It is zero standard deviations away from the average value.

Why are Z-scores important in hypothesis testing?

Z-scores are crucial in hypothesis testing because they allow us to quantify how unusual or extreme a sample result is, assuming the null hypothesis is true. The calculated Z-score (the test statistic) is compared to a critical value or used to find a p-value. This helps determine whether the sample evidence is strong enough to reject the null hypothesis in favor of the alternative hypothesis.

Enjoyed this article?

Share it with others who might find it helpful.

Share Article