First chapter of Statistics.

Question Answer
Define statistics. It involves collecting, classifying, summarizing, organizing, analyzing, and interpreting information or data in order to draw conclusions or answer questions.
Are the conclusions drawn using inferential statistics 100% accurate? Data varies and so conclusions drawn from data vary. Statistical results are usually not 100% certain. Therefore, a measure of the confidence in conclusions is also given with statistical results.
What are the steps in a statistical process? 1. Identify the research objective including the population under consideration. 2. Collect information 3. Organize the data 4. Draw conclusions from the information.
Descriptive statistics consists of what methods? Descriptive statistics consists of methods, (such as constructing tables, graphs, and charts or calculating averages, measures of variation, and percentiles) for organizing and summarizing information.
What is a census? In a census information is gathered from the entire population. This information is then organized using descriptive statistics. In this case, the results are 100% accurate assuming that there were no errors in the collection of data.
Inferential statistics consists of what types of methods? Inferential statistics consists of methods for drawing conclusions and testing conclusions about a population based on information obtained from a sample of the population. A good sample is essential or the results will have no validity.
Define a quantitative variable. A quantitative variable is a variable that takes on numerical values. (Arithmetic operations give meaningful results when performed on quantitative variables.) Example: age, height, number of children Example: age, height, number of children
Define a qualitative variable. A qualitative variable (or categorical variable) is a variable whose values are descriptive. (It gives some attribute of the individual in the population.) Example: eye color
What are two classifications of quantitative variables? A discrete variable and a continuous variable.
What is a discreat variable? A discrete variable is a quantities variable that has either a finite number of possible values or a countably infinite number of possible values. (Often counted)
What is a continuous variable? A continuous variable is a quantitative variable whose values form some interval of numbers. (Often measured)
What is an observational study? In an observational study data is collected without trying to influence the results. (It is an “after-the-fact” study. There is no attempt to control variables.) An observational study cannot be used to show causality.
What is a designed experiment? In a designed experiment, a researcher conducts an experiment to obtain data to answer his question. The key idea is that in a designed experiment the researcher controls factors that will influence the values of the variables.
Can a designed experiment be used to show causality? yes
What is the difference between a sample and a population? A population is all of the individuals under consideration in a study. A sample is just a portion of the population. (A sample is the smaller group taken from the population which is used to collect data when not conducting a census.)
What is a variable in a statistical study? A variable is a characteristic of an individual or object in the population. It varies from one individual to the next.
What is the key characteristic of simple random sampling? A sample of size n from a population of size N is obtained through simple random sampling if every possible sample of size n < N has an equally likely chance of occurring. The sample is chosen using some sort of a randomizing tool.
What is the difference between a simple random sample with replacement and a simple random sample without replacement? In a simple random sampling with replacement, a member of the population can be selected more that once. In a simple random sampling without replacement a member of the population can be selected at most once.
What is a stratified sampling? The population is divided into non-overlapping sub-populations or strata with the members of each stratum sharing the same characteristics relative to the study. The members of the sample are chosen by simple random sampling from each stratum.
What is a systematic sampling? This method is useful if a list of the population (frame) is not easily obtained. This method samples every kth member of the population with the first member of the sample corresponding to a random number in the interval 1 to k.
What is a cluster sampling? In a cluster sampling, the population is divided into groups or clusters. Then a simple random sampling is taken from the clusters and all individuals in the chosen clusters are sampled.
What is a convenience sampling? A convenience sampling is a sample in which the individuals chosen because they were easily obtained. For example: a call in pole. The sample is not based on randomness and so the results are unreliable.
Define sampling error. Sampling error is the error that results from using a sample of the population to estimate information about the entire population. This type of error can be minimized but cannot be eliminated when samples are used.
Define nonsampling error. Nonsampling errors are errors that result from obtaining and recording the information collected in a survey. (These errors could even occur in a census.) A good sample should try to eliminate all nonsampling errors.
What are some of the types of nonsampling error? Sampling bias (the sample does not represent the entire population); Self-selection bias; Non-response bias; Interviewer error; Poorly designed questions; Data entry error.
Define a statistical experiment. A statistical experiment is an activity which can be repeated and in which there are two or more possible outcomes. The results of the experiment cannot be predicted with absolute certainty before the experiment is conducted.
What is a designed experiment? In a designed experiment, a question is answer by performing a controlled experiment. Treatments are applied to the individuals in the study and results are measured. Factors that are not manipulated by treatments are either controlled or randomized.
What are the key points in a designed experiment? In a designed experiment, effects of certain conditions on the individuals or objects in the study are investigated. The factors that affect these results are controlled, manipulated, or randomized.
What are the experimental units (or subjects) in a designed experiment? The experimental units in a designed experiment are the members of the sample upon which a treatment is applied. They are called subjects if the sample consists of people.
In a designed experiment, what is meant by the term “treatment”? A treatment in a designed experiment is one or more factors that are applied to the experimental units in the study. It affects the measured results in the experiment.
What is the response variable in a designed experiment? The response variable is the characteristic (qualitative or quantitative) that is being measured or observed. The values of the response variable are used to determine the results obtained from the study.

Leave a Reply

Your email address will not be published. Required fields are marked *