# Finding Appropriate Sample Sizes

Are there any steps I can take to ensure that I have an appropriate sample size? How can I make sure that even with appropriate numbers that the distribution of the sample is representative? Are there tests that I can run that will assist with this and or any strategies for ensuring my sample coverage and variability?

© BrainMass Inc. brainmass.com October 17, 2018, 11:25 am ad1c9bdddfhttps://brainmass.com/psychology/abnormal-psychology/finding-appropriate-sample-sizes-538401

#### Solution Preview

Hi, my name is Jamie and I'd like to help you with this question. I am finishing my PhD in Psychology and I have a lot of experience with research methods.

First of all, you want to make sure that your sample is a good representation of the overall population you are interested in studying. The sample is the group of individuals actually participating in the study. It is necessary to ensure that your sample is a good representation of your population of interest, so that you can draw inferences and make valid and reliable conclusions.

To obtain a solid sample from the population you want to study, it might be a good idea to obtain the data from questionnaires, self-reports, peer feedback, etc. Obtaining rating scales, behavior reports or other types of assessment questionnaires is going to be very helpful for you. To conduct a study on human subjects, your proposal must pass what is called the IRB: Institutional Review Board. Most colleges and universities have their own IRBs, so check with your professor or Principal Investigator for more information. I am including the note on the IRB here, as it is one of the most important steps in obtaining the proper sample for your study.

One of the most important ways to assure your sample is representative of the population you are studying is to employ random sampling. This means that members from a specific ...

#### Solution Summary

The expert finds the appropriate sample sizes for the strategies ensuring a sample coverage and variability.

Normal Distributions, Central Limit Theorem and Age Distribution

Questions:

Work each question, using Excel where appropriate.

Remember, each gestation period is its own normal distribution. Thus, you will need to change the "mean" and "standard deviation" to reflect the question you are answering.

2. What percent of the babies born with each gestation period have a low birth weight (under 5.5 pounds)?

a. under 28 weeks

b. 32 to 35 weeks

c. 37 to 39 weeks

d. 42 weeks and over

Answer:

3. Describe the weights of the top 10% of the babies born with each gestation period.

a. 37 to 39 weeks

b. 42 weeks and over

Answer:

4. For each gestation period, what is the probability that a baby will weigh between 6 and 9 pounds at birth?

a. 32 to 35 weeks

b. 37 to 39 weeks

c. 42 weeks and over

Answer:

5. A birth weight of less than 3.3 pounds is classified by the NCHS as a "very low birth weight." What is the probability that a baby has a very low birth weight for each gestation period?

a. under 28 weeks

b. 32 to 35 weeks

c. 37 to 39 weeks

Answer:

Questions:

Remember, each gestation period is its own normal distribution. Thus, you will need to change the "mean" and "standard deviation" to reflect the question you are answering.

1. Enter the age distribution of the United States into a technology tool. Use the the tool to find the mean age in the United States.

Answer:

2. Enter the set of sample means into a technology tool. Find the mean of the set of sample means. How does it compare with the mean age in the United States? Does this agree with the results by central Limit theorem?

Answer:

3. Are the ages of people in the United States normally distributed? Explain your reasoning.

Answer:

4. Sketch a relative frequency histogram for hte 36 sampl means. Use 9 classes. Is the histogram approximately bell shaped and symmetic? Does this agree with the results predicted by the Central Limite Theorem?

Answer:

5. Use technology tool to find the standard deviation of the set of 36 samoke means. How does it compare with the standard deviation of the ages? Does this agree with the result predicted by the Central Limit Theorem?

Answer:

Questions:

1. Using Excel, find the z-score that corresponds to the following Confidence Levels:

a. 80%

b. 85%

c. 92%

d. 97%

2. Using Excel, find the t-score that corresponds to the following Confidence Levels and Sample Sizes:

a. 95% with n = 25

b. 96% with n = 15

c. 97% with n = 21

d. 91% with n = 10

3. Suppose we wish to estimate the population mean using a confidence interval. When is it appropriate to use a z-score? When is it appropriate to use a t-score?

Bob loves making candy, especially varieties of caramel, including plain, chocolate dipped caramels and chocolate dipped caramels with pecans. Bob has received lots of compliments from his friends and neighbors, and several have encouraged him to start his own candy making business.

After several days of research, Bob finds that the national average amount of money spent annually per person on this type of specialty candy is $75. Bob believes that the citizens in his area spend more than that per year. Knowing whether or not this is true could help Bob make a wise decision regarding his future business plans.

Bob wants to use statistics to support his claim, and to help him obtain a small business loan. Bob also wants to find an estimate of the true amount of money local citizens do spend on this type of specialty candy.

Bob randomly selects several people from his local phone book and asks the person that answers how much money they typically spend per year on candy like he will make. He obtains the following results (in dollars): 75, 74, 80, 68, 79, 85, 77, 82, 79, 67, 90, 72, 76, 75, 69, 85, 78, 79, 82, 66, 75, 85, 90, 76, 85, 67, 89, 82, 69, 79, 82, 80, 84, 79, 78, 81, 77, 84, 80, 76.

Based upon these results, Bob is hoping his area has a good customer base for his new business. Bob also hopes the bank is impressed with his use of statistics and will grant him the loan he needs to start it!

Questions:

1. Find the sample mean and sample standard deviation of the amount citizens spend per year.

2. When finding a confidence interval for the true mean spent of ALL citizens, should we use a z-score or

a t-score? Why?

3. Find the z/t-values (as appropriate) for a 95% confidence interval and a 92% confidence interval.

4. Find a 95% and a 92% confidence interval for the true mean amount that citizens spend per year.

5. What do you think the lowest possible mean amount spent per year is? Why?

6. Do you think Bob has a good customer base for his new business? Explain.

Please see the 4 tabs on this spreadsheet. Specifically, Birth Weights,Age Dist, Conf Intervals & Candy Business

View Full Posting Details