Business statistics
What are the rules when constucting classes for grouped data?
1.Create equal class sizes 2. Use mutually exclusive classes 3.include all data values 4.Avoid open-ended classes
The human resources department at a major high tech company recently conducted an employee satisfaction survey of 100 of its 3,000 employees. Data were collected on such variables as age, gender, marital status, current salary, level of overall satisfaction on a scale from 1 to 5, number of years with the company, and job title. Which of the variables would be considered to be qualitative data? A) Gender, marital status, job satisfaction, and job title B) Age C) Years with the company D) All variables listed are qualitative.
A
Discrete Data
Data that can take on a countable number of possible values.
Continuous Data
Data whose possible values are uncountable and that may assume any value in an interval
The Cranston Company recently met with a group of its customers to ask questions about the service and products provided by the company. The data collected in this process would be an example of data collected through direct observation.
FALSE
Typically, it is possible to include a larger number of questions in a phone survey than in a mail survey since it takes less time to complete the survey over the phone.
FALSE
Statistics
Helps us make sense of numbers. It is a way to get information from data.
Business statistics
Is a process of collecting, organizing, analyzing, and converting data into meaningful information for decision making in a business environment.
symmetrical distribution
The shape of a distribution when its two halves mirror one another.
What is =COUNTIF ?
This neat function will count the number of As, Bs, Cs, Ds, and Fs.
When stratified random sampling is employed, the population is divided into homogeneous subgroups called strata.
TRUE
When students are asked to list their age and the percentage of their college expenses that they pay for themselves, the type of data being collected is quantitative.
TRUE
Relative Frequency
The Proportion of Total Observations that are in a given category.
Ogive
The graphical representation of the Cumulative Relative Frequency
percentage polygon
The height of each midpoint represents relative frequency of the corresponding class.
Some of the most common methods of collecting data include experiments, telephone surveys, mail questionnaires, direct observations, and personal interviews.
TRUE
A professor hands out survey forms during her classes, where the population is all students attending the college. This is an example of: A) a convenience sample. B) a simple random sample. C) a stratified sample. D) a cluster sample.
A
What is meant by the term statistical inference?
A statistical inference is a conclusion reached about a population value (parameter) based upon an analysis of data in a statistical sample from the population. The idea is that we can study the sample data and then draw a conclusion (inference) about what the entire population looks like with respect to the measure of interest. There are two main categories of statistical inference: estimation and hypothesis testing.
Frequency Distribution
A summary of a set of data that displays the number of observations in each of the distribution's distinct categories or classes
Cumulative Frequency Distribution
A summary of a set of data that displays the number of observations with values less than or equal to the upper limit of each of its classes
Cumulative Relative Frequency Distribution
A summary of a set of data that displays the proportion of observations with values less than or equal to the upper limit of each of its classes
contingency table
A table that provides a format to display observations that have more than one value associated with them.
A sampling plan that requires a person to interview 100 people as they exit a department store would most likely be: A) a simple random sample. B) a convenience sample. C) a systematic random sample. D) a stratified sample.
B
If a systematic random sample is to be selected of size 100 from a population with 5,000 items, the first item selected from the ordered population will be: A) randomly selected between 1 and 100. B) randomly selected between 1 and 50. C) any randomly selected value between 1 and 5,000. D) item 50.
B
The company that makes a new weight loss pill claims that people who use this pill according to instructions will lose an average of 20 pounds during a four-month period. They say the claim is based on a study of 300 people. Which of the following statistical methods was most likely used to arrive at the company's conclusion? A) Estimation B) Hypothesis testing C) Histograms D) Bar charts
B
The summaries of data, which may be in forms of tabular, graphical, or numerical, are referred to as: A) inferential statistics. B) descriptive statistics. C) statistical inference. D) report generation.
B
When a survey uses the responses strongly disagree, disagree, neutral, agree, strongly agree, this is an example of: A) nominal data. B) ordinal data. C) interval data. D) ratio data.
B
When an accounting auditor randomly selects 20 accounts from all the accounts to check for accuracy, she has selected: A) a personal observation. B) a sample from the population. C) a census. D) a convenience sample.
B
What type of Bar chart is this? The length or height of each bar represents the frequency or percentage of observations or some other measure associated with the category .
Bar chart
A value computed from a population is called: A) a statistic. B) a real number. C) a parameter. D) a point estimate.
C
The human resources department at a major high tech company recently conducted an employee satisfaction survey of 100 of its 3,000 employees. Data were collected on such variables as age, gender, marital status, current salary, level of overall satisfaction on a scale from 1 to 5, number of years with the company, and job title. Considering the age variable where employees were asked to list their age at their last birthday, which of the following best describes the level of data measurement for that variable? A) Interval level B) Nominal level C) Ratio level D) Cross-sectional data
C
The human resources department at a major high tech company recently conducted an employee satisfaction survey of 100 of its 3,000 employees. Data were collected on such variables as age, gender, marital status, current salary, level of overall satisfaction on a scale from 1 to 5, number of years with the company, and job title. Which of the variables would be classified as nominal level data? A) Age and years with the company B) Overall satisfaction C) Gender, marital status, and job title D) Age and gender
C
When an administrator at a local hospital prepares a series of charts and graphs pertaining to the patients that have stayed at the hospital during the past month, she is using which general category of statistical analysis? A) Quantitative statistics B) Inferential statistics C) Descriptive statistics D) Random sampling
C
A tire manufacturing company is interested in obtaining data on stopping distances for each of the three main tread types made by the company. The data collection method that would be most likely used in this case would be: A) telephone survey. B) written questionnaire. C) demographic surveying. D) experiments.
D
If a stratified random sample is to be conducted, which of the following is true? A) The population will be broken down into subgroups called strata. B) Each subgroup should contain items that are homogeneous with respect to the characteristic of interest. C) If effective, the total required sample size should be less than that which would be needed if a simple random sample were selected. D) All of the above.
D
In a survey, what is meant by demographic questions and why might we want to include demographic questions in survey?
Demographic questions are questions that pertain to the respondent such as age, gender, education level, etc. The purpose of demographic questions is to be able to group responses to the central survey questions by category of the demographic questions. For instance, we might group responses to a question about product satisfaction by male/female to see whether males and females have different views about the product.
Pie chart
Each segment represents the relative frequency of that category.
Assuming that you are planning to collect data using an experiment, it will be very important to establish an appropriate survey design.
FALSE
Data collected on the Internet can generally be considered accurate since the data must go through a screening process before they can be placed on the Internet.
FALSE
Descriptive statistics allow a decision maker to reach a conclusion about a population based on a subset from the population.
FALSE
In this course, the term business statistics refers to the set of tools and techniques that are used to convert information into meaningful data
FALSE
Questions on a written survey dealing with the characteristics of the respondent (age, income, etc.) are referred to as categorical questions.
FALSE
Recently, an analyst in a company's marketing department surveyed customers regarding how often they buy a particular product. One customer indicated that she purchased the product 17 times in the last six months, but the analyst recorded the response as 71 times. This is an example of observer bias.
FALSE
Stratified random sampling is the same thing as simple random sampling.
FALSE
When a group of university students takes a poll of their fellow students on whether they support a proposed fee increase, the sampling method they would use when students walking near the library are surveyed would be called a random sample.
FALSE
A light bulb manufacturer wants to advertise the average life of its light bulbs so it tests a subset of light bulbs. This is an example of inferential statistics.
TRUE
A sales manager has five salespeople. The following are the number of units sold by the five salespeople during the past week: {5, 13, 6, 2, 4}. Based on the data, the mean number of units sold was 6 units.
TRUE
An accountant has recently prepared a report for a client that contains a variety of graphs and charts. In doing so, she has used descriptive statistical methods.
TRUE
Another term for the arithmetic average is the mean.
TRUE
Companies frequently use charts and graphs in their regular communications with stockholders and investors; this shows the use of descriptive statistics.
TRUE
Experimental design is a plan for performing an experiment where the effects of one or more factors on the variable of interest are measured.
TRUE
Hypothesis testing and estimation are two statistical tools that are used to draw inferences about a large data set based on a subset of the data.
TRUE
If a population is very large, it may be better to select a sample from the population than to try to obtain a census in an effort to reduce measurement error.
TRUE
Population parameters are descriptive numerical measures, such as an average, that describe the entire population.
TRUE
Recording vehicle type as sedan, minivan, pick-up truck, etc. is an example of qualitative data.
TRUE
The editor of a local newspaper is interested in determining the percentage of subscribers who read the paper's editorials. The statistical technique that he would use is called estimation.
TRUE
The primary purpose of performing a pre-test when developing a telephone or mail survey is to make sure that the respondents can understand the questions and are able to provide meaningful responses.
TRUE
General Electric Corporation tracks employee turnover annually. It currently has a data set that contains turnover for the past 20 years. What type of data does it have? A) Time-series data B) Cross-sectional data C) Nominal data D) Ordinal data
A
The human resources department at a major high tech company recently conducted an employee satisfaction survey of 100 of its 3,000 employees. Data were collected on such variables as age, gender, marital status, current salary, level of overall satisfaction on a scale from 1 to 5, number of years with the company, and job title. Which of the following best describes the overall data set that was generated from the study? A) Cross-sectional data B) Time-series data C) Nominal data D) Quantitative data
A
The mayor of a large U.S. city is interested in addressing complaints from many property owners regarding recent property assessments. Many people feel that they are being overtaxed and that their assessments are too high. To study this issue, the mayor plans to hire consultants to randomly select homes in the city and have these homes independently assessed for value. However, she is concerned that the cost of sampling will be very high since the city is spread out over a wide geographical area. To potentially reduce the cost of sampling, which of the following statistical sampling techniques should be applied? A) Cluster sampling B) Ratio sampling C) Simple random sampling D) Stratified random sampling
A
The use of charts and graphs is an example of: A) descriptive statistics. B) inferential statistics. C) estimation. D) hypothesis testing.
A
When a marketing manager surveys a few of the customers for the purpose of drawing a conclusion about the entire list of customers, she is applying: A) inferential statistics. B) descriptive statistics. C) quantitative models. D) numerical measures.
A
Stacked bar charts
A bar chart that groups several values in a single column within the same category in a vertical direction.
clustered bar chart
A bar chart that groups several values side by side within the same category in a vertical direction.
Pareto chart
A bar chart that shows in a decreasing order the frequency of the categories that cause quality control problems.
Histogram
A bar graph showing the number of observations in each class as the height of each bar.
Bar Charts
A graphical representation of a categorical data set in which a rectangle or bar is drawn over each category or class
Is there ever a reason why we might prefer to work with a sample rather than with an entire population? Discuss.
A sample is a subset of a population and might not be a perfect representation of the population. As a result, it is possible that when our objective is to know characteristics of the population, the values we get from the sample might be misleading. Thus, in the general case, we would prefer to have access to all the data in the population. However, there are reasons why we might be better off with a sample in some instances. For example, if the population is very large, the time and cost of collecting data from the entire population might make the project unfeasible. In addition, when a great number of measurements are required for a large population, measurement and/or coding errors could be introduced that would give us incorrect information about the population. In addition, if the measurement process requires that we destroy, or otherwise modify, the population values, it would not make sense to deal with the entire population. In these cases, a sample might well be preferable to a census of the population.
Which of the following statements is true? A) Random samples are easier to select than nonstatistical samples. B) Nonstatistical samples can provide useful data. C) Stratified random sampling involves breaking the population down into geographic subgroups. D) Systematic sampling is an example of nonstatistical sampling.
B
Discuss the differences and similarities between statistical estimation and statistical hypothesis testing.
Both estimation and hypothesis testing fall under the main category of statistical procedures called inferential statistics. In both cases, we are attempting to better understand the population of interest by examining the data in a sample from the population. With estimation, we begin with a goal of estimating a population value such as a population mean. We don't have a preconception about what that value is. Instead, we look at a corresponding value for the sample (i.e., sample mean) and use that as our "best" guide to what the population value is. With hypothesis testing, we begin with a claim or idea (hypothesis) about what the population value is and then we use the corresponding sample value to either support or refute the claim or idea.
What are the major categories of statistical tools that will be covered in this course?
Business statistics can be divided into two main categories: descriptive statistics and inferential statistics. Probability is a link between the two and is a major part of the statistical inference section.
A consumer products company is considering introducing a new product nationally. To help make the decision, it first conducts a test market by selling the product for a few months in one city. This is an example of: A) descriptive statistics. B) charts and graphs. C) estimation. D) hypothesis testing.
C
A food warehouse manager plans to conduct a check on damaged packages. The warehouse covers a large area and products are spread out over the entire building. Assuming that no products are more likely to have damaged packages than any other, what statistical sampling method would be used to reduce the time and effort required to do the study? A) Convenience sampling B) Stratified random sampling C) Cluster random sampling D) Systematic random sampling
C
Based on a survey of 400 students in a university in which 20 percent indicated that they were business majors. The university student newspaper reported that "20 percent of all the students at the university are business majors." This report is an example of: A) a sample. B) a population. C) statistical inference. D) descriptive statistics.
C
In Excel, what procedure is used to select random numbers? A) The random numbers function B) Click on the Data tab, then click on Data Analysis, then click on Sampling C) Click on the Data tab, then click on Data Analysis, then click on Random Number Generation D) Random numbers are not available in Excel.
C
In conducting a personal interview, what problem can result if the interviewer is allowed to arbitrarily decide who should be interviewed? A) Nonresponses B) Missing data C) Bias D) Poor response rate
C
In developing and conducting a survey, what is the purpose of the pre-test phase? A) To make sure that the cost of developing the survey instrument is not too great B) To generate initial data for analysis C) To catch any problems with the questionnaire before it is fully administered D) To make sure that the respondents like the issues being addressed by the survey
C
Recently, a major tire manufacturer stated in its advertising that its tires with a new tire tread design will last more than 50,000 miles on average. A consumer agency collected a subset of these tires and tested them in very controlled conditions. Based on this test, the agency concluded that the manufacturer was justified in making this claim. The process described is an example of: A) descriptive statistics. B) hypothesis testing. C) statistical inference. D) B and C
D
Some stores and restaurants have "tell us what you think" cards available for customers. Assuming that angry customers are more likely to take the time to fill these out, this is an example of: A) simple random sampling. B) stratified sampling. C) cluster sampling. D) nonstatistical sampling.
D
The Biltmore Hotel manager is getting ready to make a presentation that she hopes will justify adding additional staff. As part of the presentation, she has constructed charts and graphs. The general type of statistical analysis she is using is: A) hypothesis testing. B) estimation. C) inferential statistics. D) descriptive statistics.
D
Explain the difference between a Stratified Random Sample and Cluster Random Sample.
First, both sampling techniques are examples of statistical sampling procedures. However, they are very different in purpose AZ Then the total sample size selected from all strata will hopefully be less than the required sample size that would be needed if stratification were not used. In cluster sampling, the population is divided into geographical subgroups. The hope is that each subgroup is a mirror image of the population as a whole. Then a few of the clusters are randomly selected and all sampling of individual items is taken from only the selected clusters. The objective is to reduce the cost of sampling by reducing the physical area that must be covered in the sample.
Scatter plots
Provide a picture of the relationship between two data points that are paired together.
Stem and leaf display
Splits the data values into stems (the larger place values) and leaves (the smallest place values.
A common underpinning of all statistical sampling techniques is the concept of random selection.
TRUE
A company that is interested in determining which of three prices to charge for its products has test marketed the product in three cities, each time using a different price for the product. The number of products sold in the first week is recorded. In this case, the data are considered to have been collected using an experiment.
TRUE