2Probability and Statistics Chapter 1 Notes I. Section 1-1A. Definition of Statistics1. Statistics is the science of collecting, organizing, analyzing, and interpreting data in order to make decisions.a. Data – Information coming from observations, counts, measurements, or responses.1) There are 2 types of data sets.a) Population – the collection of all outcomes, responses, measurements, or counts that are of interest.1. In other words, the set of all possible measurements, counts or observations that are of interest in a particular study.
3Probability and Statistics Chapter 1 Notes I. Section 1-1b) Sample – A subset of the population.1. Since it is usually impractical or even impossible in terms of time or money to obtain every possible response, we must often rely on information obtained from a sample.1. Random Sample: -- A sample in which every member of the population has an equal chance of belonging.2) A central theme, in the study of statistics, is that of using information obtained from a sample tomake decisions or inferences concerning an entire population from which the sample has beendrawn.1. We will study techniques which will enable us to do this with a high level of reliability.
4Probability and Statistics Chapter 1 Notes I. Section 1-13) There are 2 types of numerical descriptionsa) Parameter – A numerical description of a population characteristic.b) Statistic – A numerical description of a sample characteristic.B. Branches of Statistics1. Descriptive Statisticsa. The branch of statistics that involves the organization, summarization, and display of data.2. Inferential Statistics.a. The branch of statistics that involves using a sample to draw conclusions about a population.1) A basic tool in the study of inferential statistics is probability.
5Probability and Statistics Chapter 1 NotesII. Section 1-2A. Types of Data1. Qualitative Dataa. Attributes, labels or nonnumerical entries.2. Quantitative Dataa. Numerical measurements or counts.B. Levels of Measurement1. Nominal Dataa. Consists of names, categories, qualities, or labels.Example: type of car you drive.b. Can put data into categories, but we are unable to determine if one piece of data is better or higher than another.c. When numbers are used as labels, such as on an athletic jersey, they are classified as nominal data.
6Probability and Statistics Chapter 1 NotesII. Section 1-21) It is of no use whatsoever to know the average of all jersey numbers of the King’s Fork field hockey team.2. Ordinal Dataa. Designations or numerical rankings which can be arranged in ascending or descending order.1) TV ratings for #1 show, #2 show, etc.b. We can compare rankings as to which is higher, however it does not make sense to subtract one rank value from another.1) Differences in rankings are not meaningful computations.a) If there are three candidates for a job, they can be ranked 1, 2, and 3, but there is no way to tell how far ahead of the second candidate the first candidate is.
7Probability and Statistics Chapter 1 NotesII. Section 1-23. Interval Dataa. Can be subtracted to find the difference between two values, put in order, and put into categories.b. Data is numerical; 0 can be used to indicate a position in time or space, however, the zero at this level does not correspond to “none” of the specific variable being measured.1) The position on the thermometer of zero degrees does not indicate that is absolutely no heat present.c. Differences between data values are meaningful but it does not make sense to compare one data value as being twice (or any multiple of) another.1) A temperature of 2 degrees is not twice as warm as a temperature of 1 degree.
8Probability and Statistics Chapter 1 NotesII. Section 1-24. Ratio Dataa. The highest level of measurement.1) The number of gallons of gasoline you put into your car today.b. There is a zero on this scale which is interpreted as “none” of the variable in question.1) It is possible to put zero gallons of gas into your tank today.2) This is called an “inherent” zero.c. It is meaningful to say one measure is two times, or three times, as much as another.1) You may have put twice as much gas in your car today than you did last week.
9Probability and Statistics Chapter 1 NotesII. Section 1-25. How to tell Interval data from Ratio data.a. Does the expression “twice as much” have any meaning in the context of the data?1) $2 is twice as much as $1, so these data points are at the ratio level.2) A temperature of 2 degrees is NOT twice as warm as degree is, so these data points are at the interval level.
10Probability and Statistics Chapter 1 NotesIII. Section 1-3A. Design of a Statistical Study1. Identify the variable(s) of interest (the focus) and the population of the study.2. Develop a detailed plan for collecting data.3. Collect the data.4. Describe the data, using descriptive statistics techniques.5. Interpret the data and make decisions about the population using inferential statistics.6. Identify any possible errors.B. Data Collection1. Do an Observational Studya. Observe and measure characteristics of interest of part of a population, but do NOT change existing conditions.
11Probability and Statistics Chapter 1 NotesIII. Section 1-3B. Data Collection2. Do an Experimenta. Apply a treatment to part of a population and observe responses or results.b. Observe another part of the population as a control group.1) May use a placebo in place of the treatment being tested.
12Probability and Statistics Chapter 1 NotesIII. Section 1-3B. Data Collection3. Use a simulationa. Use a mathematical or physical model to reproduce the conditions of a situation or process.1) Simulations allow us to study situations that are impractical or even dangerous to create in real life.a) Testing the effects of alcohol on a pilot’s ability to fly is best done in a flight simulator2) Simulations often save time and/or money.4. Use a survey (census)a. A survey is an investigation of one or more characteristics of a population.1) Usually carried out on people by asking them to respond to questions.
13Probability and Statistics Chapter 1 NotesIII. Section 1-3B. Data Collectionb. It’s important to word the questions so that they do not lead to biased results.C. Experimental Design1. Experiments must be carefully designed in order to produce meaningful, unbiased, results.a. The Hawthorne effect occurs in an experiment when subjects change their behavior simply because they know they are participating in an experiment.2. Three key elements of a well-designed experiment are control, randomization, and replication.
14Probability and Statistics Chapter 1 NotesIII. Section 1-3C. Experimental Designa. Control1) It is important to control as many influential factors as possible in a study.2) When an experimenter cannot tell the difference between the effects of different factors in an experiment, a confounding variable has occurred.3) Placebo effect occurs when a subject reacts favorably to a placebo when in fact they have been given no medical treatment at all.a) Blinding is a technique used in which the subject does not know whether he or she is receiving a real treatment or a placebo.
15Probability and Statistics Chapter 1 NotesIII. Section 1-3C. Experimental Designb) Double-blind experiments occur when neither the subjects nor the experimenter know which individual subjects are receiving a treatment or a placebo.1. The experimenter only finds out which subjects are which after all the data have been collected.b. Randomization is a process of randomly assigning subjects to different treatment groups.1) Randomized block design – Divide subjects with similar characteristics into blocks, and then randomly split each block up into different treatment groups.
16Probability and Statistics Chapter 1 NotesIII. Section 1-3C. Experimental Design2) Matched-pairs design – Subjects are paired up according to a similarity.a) One subject in each pair is randomly selected to receive one treatment, while the other one gets another, different treatment.c. Replication is the repetition of an experiment using a large group of subjects.1) The larger the sample size, the better.D. Sampling Techniques1. Census – a count or measure of an entire population.a. Provides complete information, but is often too costly or difficult to perform.
17Probability and Statistics Chapter 1 NotesIII. Section 1-3D. Sampling Techniques2. Sampling – a count or measure of part of a population.a. Researcher must ensure that the sample is representative of the population.1) This is necessary to ensure that inferences about a population are valid.a) Sampling error – the difference between the results of a sample and those of the population.b. Random sample – a sample in which every member of the population has an equal chance of being selected.1) Methods of sampling randomly
18Probability and Statistics Chapter 1 NotesIII. Section 1-3D. Sampling Techniquesa) Simple Random Sample – assign each member of the population a number and then randomly select the numbers that you will survey.1. Random number table (Appendix B of the book)a. Randomly pick a starting pointb. Count off digits in groups that match how many digits your population has.c. Record the numbers, ignoring those that are larger than the population size.
19Probability and Statistics Chapter 1 NotesIII. Section 1-3D. Sampling Techniques2. Calculatora. Press Math, select PRB, press 5(randInt)b. Enter the number that you started with when assigning labels to your population, then a comma, then the last number you assigned, comma, and the sample size you wish to use.1) The calculator will generate the requested quantity of random numbers.3. If you do not want to have any member of the population included in the sample twice, the sampling process is said to be without replacement.
20Probability and Statistics Chapter 1 NotesIII. Section 1-3D. Sampling Techniques4. If you don’t care if a member of the population is included twice, the sampling process is said to be with replacement.b) Stratified Sample1. Separate population into two or more subsets, called strata, using some similar characteristic.a. Randomly select members of each strata to make up your sample.c) Cluster Sample1. When the population is already divided into subsets that are very similar to each other, you could randomly select a number of entire groups (not all the groups) and do your data collection on those groups.
21Probability and Statistics Chapter 1 NotesIII. Section 1-3D. Sampling Techniquesa. We call these groups clusters.d) Systematic Sample1) Each member of the population is assigned a number.a. Put the members of the population in order somehow.b. Randomly select a starting point.c. Randomly select an interval.d. Survey every nth member of the population from your starting point.
22Probability and Statistics Chapter 1 NotesIII. Section 1-3D. Sampling Techniquese) Convenience Sample1) NOT RECOMMENDED!!a. Simply select those members of the population who are readily available.
23QUIZ on Chapter 1 Sections 1 and 2 during next class block Friday (ODD) and Monday (EVEN)TEST on Chapter 1 next weekTuesday (ODD) and Wednesday (EVEN)