HAWKES LEARNING SYSTEMS math courseware specialists Copyright © 2010 by Hawkes Learning Systems/Quant Systems, Inc. All rights reserved. Chapter 2 Data, Reality, and Problem Solving HAWKES LEARNING SYSTEMS Data, Reality, and Problem Solving math courseware specialists Sections 2.1-2.4 The Reality of Conducting a Study Objectives: • Learn the ethical concerns of conducting a study. • Determine the practical concerns of conducting a study. HAWKES LEARNING SYSTEMS Data, Reality, and Problem Solving math courseware specialists Section 2.1 The Lords of Data Measurement: To develop suitable measurements we will be concerned with the following: • What should be measured? • How should the concept be measured? Now we need to know how good the measurements are. Ask yourself the following: • Is the concept under study adequately reflected by the proposed measurements? • Is the data measured accurately? • Is there a sufficient quantity of the data to draw a reasonable conclusion? If you answered yes to all three of these questions, the data possesses good properties. HAWKES LEARNING SYSTEMS Data, Reality, and Problem Solving math courseware specialists Section 2.2 Science and Data The Scientific Method: The scientific method is a collection of methods that have become standard for exploring research problems. The Scientific Method: • Gather information about the phenomenon being studied. • On the basis of that data, formulate a preliminary generalization or hypothesis. • Collect the data to test the hypothesis. • If the data and other subsequent experiments support the hypothesis, it becomes a law. HAWKES LEARNING SYSTEMS Data, Reality, and Problem Solving math courseware specialists Section 2.3 Decision Making and Data Decision Making: We make decisions every day and collecting data is a natural part of our lives. One decision we make every day is: “What will I have for dinner?” • Although we may not apply the scientific method, most people perform experiments and collect data (by eating). This leads to generalizations such as “I like everything except liver, sweet peas, and beets.” • After sufficient experimentation, these generalizations become personal preference laws. Do you have any personal preference laws? HAWKES LEARNING SYSTEMS Data, Reality, and Problem Solving math courseware specialists Section 2.3 Decision Making and Data Decision Making Method: • Clearly define the problem and any influential variables. • Decide upon objectives and decision criteria for choosing a solution. • Create alternative solutions. • Compare alternatives using the criteria established in the second step. • Implement the chosen alternative. • Check the results to make sure the desired results are achieved. HAWKES LEARNING SYSTEMS Data, Reality, and Problem Solving math courseware specialists Section 2.4 Collecting Data Ways to Collect Data: The two ways to collect data are: • Controlled experiments • Observation The data collection method is related to the nature of the problem to be solved and the ethical and practical constraints of collecting data in some particular environment. HAWKES LEARNING SYSTEMS Data, Reality, and Problem Solving math courseware specialists Section 2.4 Collecting Data Controlled Experiments: The purpose of a controlled experiment is to reveal the response of one variable to the changes of another variable. • In a controlled experiment there are two groups: the control group and the experimental group. • During the experiment a treatment is applied to the experimental group. • The exact treatment will depend on the particular experiment. • The treatment changes the level of the explanatory variable in the experiment. The effect of the treatment can be measured by comparing the response variable in the control and experimental groups. HAWKES LEARNING SYSTEMS Data, Reality, and Problem Solving math courseware specialists Section 2.4 Collecting Data Definitions: •The response variable measures the outcome of interest in a study. •An explanatory variable causes or explains changes in the response variable. HAWKES LEARNING SYSTEMS Data, Reality, and Problem Solving math courseware specialists Section 2.4 Collecting Data Calculus before Physics Experiment: Control group Students with the same mathematical ability Experimental group Randomly assigning students to take calculus before physics Treatment Taking calculus before physics Response variable Students’ grades in physics Explanatory variable Whether students take calculus before physics HAWKES LEARNING SYSTEMS Data, Reality, and Problem Solving math courseware specialists Section 2.4 Collecting Data Flowchart for the Calculus before Physics Experiment: Treatment Group Treatment (Take Calculus before Physics) Observe Randomly Select Students Compare Performance Control Group Observe HAWKES LEARNING SYSTEMS Data, Reality, and Problem Solving math courseware specialists Section 2.4 Collecting Data Does an SAT Course Improve an SAT Score? Response variable High school students that have taken the SAT exactly one time The high school students are given an SAT preparation course. The same high school students take the SAT again SAT scores Explanatory variable SAT preparation course Control group Treatment Experimental group HAWKES LEARNING SYSTEMS Data, Reality, and Problem Solving math courseware specialists Section 2.4 Collecting Data Flowchart for the SAT Experiment: Before The control group: Is high school students that have taken the SAT exactly one time. The value of the response variable is the students’ scores on their first SAT. Treatment The same high school students are given an SAT preparation course. After Now, the students are the treatment group and they take the SAT again. The value of the response variable is the score on the second SAT. Compare Compare students performance on the SAT before and after the course HAWKES LEARNING SYSTEMS Data, Reality, and Problem Solving math courseware specialists Section 2.4 Collecting Data Definitions: • Sometimes in clinical trials people are given placebos. Placebos are “fake” treatments. • Double blind studies are used to counteract the placebo effect. In these studies neither the subjects know if they are members of the control or experimental group, nor do the evaluators know whether their subjects are members of the control or experimental group. HAWKES LEARNING SYSTEMS Data, Reality, and Problem Solving math courseware specialists Section 2.4 Collecting Data Observational Data: Observational data comes by measuring “what is.” For example, observational data is: • What is happening in the marketplace at the time. • The measure of how things are in a specific geographic area at a given point in time. Virtually all data we routinely encounter is observational. HAWKES LEARNING SYSTEMS Data, Reality, and Problem Solving math courseware specialists Section 2.4 Collecting Data Examples of Observational Data: • Stock, commodity, bond, option, and currency market data. • Almost all federal data, including census, economic, and educational data. • Sports data. Can you think of an example of observational data? HAWKES LEARNING SYSTEMS Data, Reality, and Problem Solving math courseware specialists Section 2.4 Collecting Data Example: 8,442 men and 4,321 women applied to graduate school at Berkeley. Subsequently, 3,714 men and 1,512 women accepted. Thus 44% of the men and 35% of the women were accepted. Was the graduate school discriminating against women? College Acceptance Rates Men Women Total Number Percent Total Number Percent Major of Applicants Admitted of Applicants Admitted I 800 65 120 85 II 550 62 32 70 III 400 40 410 36 IV 350 36 347 37 V 200 24 387 27 VI 300 8 352 10 To the left is the admissions data from Berkeley. Does this data show discrimination? HAWKES LEARNING SYSTEMS Data, Reality, and Problem Solving math courseware specialists Section 2.4 Collecting Data Solution: College Acceptance Rates Men Women Total Number Percent Total Number Percent Major of Applicants Admitted of Applicants Admitted I 800 65 120 85 II 550 62 32 70 III 400 40 410 36 IV 350 36 347 37 V 200 24 387 27 VI 300 8 352 10 • In all but one of the majors, women were admitted more frequently than men. Not only were women not being discriminated against, but there appears to be potential discrimination against men in Major I. • The majors that had very low acceptance rates had relatively very few men and a large number of women applying. •The variable, major field of study, was confounding the variable gender in the original analysis and biasing the original conclusion. HAWKES LEARNING SYSTEMS math courseware specialists Copyright © 2010 Hawkes Learning Ch 2. Data, Reality, &byProblem Solving Data, Reality, and Problem Solving Systems/Quant Systems, Inc. Data Classifications Section 2.4 2.5 Collecting Data All rights reserved. Example: Determine whether each of the following studies is observational or experimental. • A medical researcher wants to examine the effects of exercise on cardiovascular health. Solution: Experimental • A recording company is interested in knowing the percentage of teenagers that download music off of the internet. Solution: Observational • A chain of grocery stores wants to know how much the average family spends on produce each month. Solution: Observational HAWKES LEARNING SYSTEMS Data, Reality, and Problem Solving math courseware specialists Sections 2.5-2.6 Levels of Measurement Objectives: • Classify data as discrete or continuous. • Determine if data are qualitative or quantitative. • Identify the level of measurement. HAWKES LEARNING SYSTEMS Data, Reality, and Problem Solving math courseware specialists Section 2.5 Data Classifications Data Classifications: Data or variables can be categorized in several ways: • Discrete or continuous • Level of measurement • Quantitative or qualitative HAWKES LEARNING SYSTEMS Data, Reality, and Problem Solving math courseware specialists Section 2.5 Data Classifications Discrete Data: Discrete data is a restricted set of values. Examples of discrete data: • The number of people in a classroom • A variable that only has the values 1, 1.5, 2, 2.5 • A variable that contains integer values Can you think of some data that is discrete? HAWKES LEARNING SYSTEMS Data, Reality, and Problem Solving math courseware specialists Section 2.5 Data Classifications Continuous Data: Continuous data can take on any value in an interval. Examples of continuous data: • Height • Age • A variable that has any value between 0 and 2 Can you think of some data that is continuous? HAWKES LEARNING SYSTEMS Data, Reality, and Problem Solving math courseware specialists Section 2.5 Data Classifications Level of Measurement: The quality of data is referred to as its level of measurement. Terms used to describe the level of measurement: • Nominal • Ordinal • Interval • Ratio HAWKES LEARNING SYSTEMS Data, Reality, and Problem Solving math courseware specialists Section 2.5 Data Classifications Nominal Data: Nominal measures offer names or labels for certain characteristics. Examples of nominal measures: • Gender • Hair color • Jersey number of a basketball player Can you think of a measure that is nominal? HAWKES LEARNING SYSTEMS Data, Reality, and Problem Solving math courseware specialists Section 2.5 Data Classifications Ordinal Data: Ordinal data represents data in an associated order. Examples of ordinal data: • Ranking of sports teams • Year in college • Letter grades Can you think of data that is ordinal? HAWKES LEARNING SYSTEMS Data, Reality, and Problem Solving math courseware specialists Section 2.5 Data Classifications Interval Data: If the data can be ordered and the arithmetic difference is meaningful, the data is interval. Examples of interval data: • Temperature • Dates • Level of difficulty rated from 1 to 5 Can you think of data that is interval? HAWKES LEARNING SYSTEMS Data, Reality, and Problem Solving math courseware specialists Section 2.5 Data Classifications Ratio Data: Ratio data has a meaningful zero point and the ratio of two data points is meaningful. Examples of ratio data: • Money • Height • Age Can you think of data that is ratio? HAWKES LEARNING SYSTEMS Data, Reality, and Problem Solving math courseware specialists Section 2.5 Data Classifications Example: Determine the level of measurement. • Today’s high temperature (in Fahrenheit) for varying cities across the U.S. Solution: Interval • The colors contained in a box of crayons. Solution: Nominal • The boiling point (in Kelvin’s) for varying chemical compounds. Solution: Ratio • The individual page numbers at the bottom of each page in the statistics book. Solution: Ordinal HAWKES LEARNING SYSTEMS Data, Reality, and Problem Solving math courseware specialists Section 2.5 Data Classifications Qualitative and Quantitative Data: • Qualitative data is measured on a nominal or ordinal scale. • Quantitative data is measured on an interval or ratio scale. Qualitative Quantitative Descriptions and labels Counts and measurements HAWKES LEARNING SYSTEMS Data, Reality, and Problem Solving math courseware specialists Section 2.5 Data Classifications Example: Classify each of the following as qualitative or quantitative data. • The weights of members of the football team. Solution: Quantitative • The flavors of Ben and Jerry’s Ice Cream. Solution: Qualitative • The jersey numbers of a women’s basketball team. Solution: Qualitative • Student ID numbers. Solution: Qualitative HAWKES LEARNING SYSTEMS math courseware specialists Copyright © 2010 by Hawkes Learning Data, Reality, and Problem Solving Systems/Quant Systems, Inc. Section 2.5 All Data Classifications rights reserved. Levels of Measurement: Ratio Interval Ordinal Order Nominal Names 0 is a placeholder 0 means the absence of something