Design & Lang. - Outline 3 w/notes

StudyBlue printing of Design & Lang. - Outline 3 w/notes html, body, div, span, applet, object, iframe, h1, h2, h3, h4, h5, h6, p, blockquote, pre, a, abbr, acronym, address, big, cite, code, del, dfn, em, font, img, ins, kbd, q, s, samp, small, strike, strong, sub, sup, tt, var, b, u, i, center, fieldset, form, label, legend, table, caption, tbody, tfoot, thead, tr, th, td { margin: 0; padding: 0; border: 0; outline: 0; font-size: 100%; background: transparent; } body { line-height: 1; } blockquote, q { quotes: none; } blockquote:before, blockquote:after, q:before, q:after { content: ''; content: none; } /* remember to define focus styles! */ :focus { outline: 0; } /* remember to highlight inserts somehow! */ ins { text-decoration: none; } del { text-decoration: line-through; } /* tables still need 'cellspacing="0"' in the markup */ table { border-collapse: collapse; border-spacing: 0; } /* end RESET */ .header { min-width:800px; } .logo { padding:6px 20px 2px 20px; margin:0; font-size:25px; font-weight:bold; color:#808285; position:relative; border-bottom: 1px solid #c5c5c5; } .logo-blue { color:#70adc4; } .logo-desc { font-weight:normal; font-size:19px; color:#cccccc; margin-top:50px; position:absolute; display: none; } .back-button { position:absolute; top:20px; right:20px; font-size:13px; line-height:25px; color:rgb(0,175,225); font-weight:normal; } .back-button a { color:rgb(0,175,225); } .instructions { padding:0; margin:0; width:100%; position:relative; color:rgb(100,100,100); } .step-holder { border-left:1px solid #ededed; margin-left:20px; } .steps { padding:15px 0; float:left; width:24%; border-right:1px solid #ededed; text-align:center; } .steps-01 { } .steps-02 { } .steps-03 { } .steps-04 { } .label { padding:5px 10px; } .print-button { } .print-button a { background-color:rgb(0,175,225); color:white; line-height: 19px; padding:9px 8px 5px 30px; font-size:14px; text-decoration:none; background-image: url(images/printer.png); background-repeat: no-repeat; background-position: 7px 50%; -moz-border-radius: 5px; -webkit-border-radius: 5px; } .print-button a:hover { background-color:black; } .theNote .content { width: 8.0in !important; margin: 5px auto; padding:20px; background-color:white; } .theNote .header { border-bottom: 1px dashed #C8C8C8; font-size: 17px; padding: 0 0 10px; line-height: 19px; color: #00ADE1; min-width:500px; } .theNote .body { font-size: 14px; line-height: 19px; padding: 10px 0; } .theNote{ padding:6px 0; clear:both; background-color: rgb(200,200,200); } .theNote h3{ color: rgb(100,100,100); } .theNote h1, .theNote h3{ background-color:white; padding:2px 20px; width:8.0in !important; margin: 0 auto; font-size: 15px; } .theNote h1{ padding-top: 10px; font-size: 15px; } .theNote h1:first-child{ font-size: 20px; } .theNote h3 { font-size: 14px; font-weight: normal; } #options { border: 3px double #ccc; padding: 5px 12px; margin: 10px 50px 10px 20px; float: left; } #info { border-top: 1px solid #ccc; padding-top: 5px; font-style: italic; } li { margin: 5px 10px 5px 25px; } ul li { list-style: disc; } ol li { list-style: decimal; } img { border: 0; } table { clear: both; width: 100%; border: 1px solid #c5c5c5; border-width: 1px 0; margin: 0; page-break-after: always; } table#page { page-break-after: auto; } td { text-align: center; font-size: 12px; border-bottom: 1px dashed #c5c5c5; height: 1.75in; width: 50%; padding-left: 15px; } .leftside { border-right: 1px solid #cccccc; padding: 0 15px 0 0; } .bottom td { border-bottom: none; } .clearfix { clear:both; line-height:1px; height:1px; } img { max-width:80%; max-height:150px; margin:20px; } @media print {.header { display: none; } .content .header{ display:inherit; } table { border: 1px dashed #bbb; border-width: 1px 0; } .theNote{ background-color:white; } } Research Design & Language - Outline 3 (Mertig) w/notes (Hancock) I. The Language of Social Research A. A Variable Language *Variables - Values will vary across people/cases/subjects...Things that take on different values across what is being studied. *Attributes - Values a variable can take on Examples... Variable Attributes/Values *Sex *Male *Female *Religion *Protestant *Catholic *Jewish...etc. *Political Party *Democrat *Republican *Independent, etc. *Income *From none to billions of dollars *Use of a Product *Yes *No - More specific would be - sometimes, never, often B. Relationships between variables 1. Association or Correlation I was unable to upload the tables drawn in class in these notes... When two variables tend to vary together Positive Association - two variables vary in the same direction (as one goes up, the other goes; or as one goes down, the other goes down) Examples of Positive Association: ↑Education → ↑Income ↑Environmental Concern → ↑Non-Consumptive Recreation (FYI- Bicycling is non-consumptive, hunting is consumptive) ↓Age → ↓Income **If both arrows go up or down, it is a positive association. **If plotted on graph... it looks like a positive slope. Negative Association - Two variables vary in the opposite direction (as one goes up, the other goes down). 2. Causal Relationships (Stronger Relationship) Independent Variable →Dependent Variable (Cause) or Influences (Effect) Result of influence DIRECT: X → Y INDIRECT: X → Z → Y C. Hypotheses *Should be stated PRIOR to analyzing data *Can be represented by a causal diagram Example: Education → Income *Are to be tested using Research Methods *We can NEVER absolutely prove or accept a hypothesis (because it is possible at a later date to disprove) Statements about expected relationships between variables (Mainly for Quantitative) We REJECT or FAIL TO REJECT NULL hypothesis (HO) versus (No Effect Hypothesis) --No effect --Symbolized by H0 --We try to reject the null hypothesis Usually, we are trying to reject the null hypothesis. ALTERNATIVE hypothesis (H1) (Research Hypothesis) --Symbolized by H1 (or Ha) --Rejecting the null provides "support" for H1 The "Alternative" or "Research" Hypothesis is the thing we're trying to find. Example: We just designed a solar powered car that we wish to market. Diffusion Theory: First people to buy a solar-powered car tend to be more educated. Alternatively Hypothesis (or H1): People with higher levels of education will be more likely to buy the car. Causal Diagram: ↑Education → ↑Buy Solar-Powered Car Ind. Variable → Dep. Variable Null Hypothesis (or H0): People with higher levels of education will be as likely to buy the car as people with lower levels of education. **Using a null leaves open the possibility to disprove** D. The Nature of Causality In science, it is next to impossible to establish pure necessity, sufficiency or causal. We use "weaker' versions of causality. Usually we get variations of 60%/40% or 80%/20%. 1. Probabilistic and Deterministic Probabilistic: Not perfect - probably - chances are... Deterministic: Determined - Happens for a reason that we can find out **Nomothetic versus Idiographic Nomothetic: Interested in the most important causes Idiographic: Interested in ALL of the causes...no matter how minor. If interested in all possible reasons, it loses the ability to explain in general. 2. Criteria for Positing Causality One variable causes the other... If you want to argue that some variable (x) causes/influences another (y), then the following criteria must be established (3 in book, one from Dr. Mertig)=4 Total: a. Logic (from Dr. Mertig) Does the relationship make sense? X → Y For example: Shoe Size → Intelligence - is NOT logical! b. Time Order (**Hint: Check alterability of variables) X must preceed Y in time. The future cannot cause the past...not always easy to determine. Example: Political Identification → Political Party Which comes first? Political Identification or Political Party? Check for alterability of variables...For example, age, sex, race can not be dependent. They must come first...you don't have control of the change. c. Association X must be associated with Y empirically. Empirical means you can get evidence. How can this evidence be made? *Studies showing relationship/prior literature *Perform tests (surveys) *The Strong the association, the more likely we'll believe it. Consistency! d. Non-spuriousness (We want this!) Other variables must NOT be able to explain away the observed association between X and Y. To check: 1. Think it through...what are the possibilities? 2. Make sure you include them in your study 3. Test it with your data X → Y ??? Silly example : In Sweden, there is a strong correlation between the number of babies born in an area and the number of storks in that area. OR There is a third variable...the type of area (rural) causes the relationship between number of babies and number of storks to be spurious. ==Relationship between X and Y is spurious. X → Y ??? Another Silly Example : There is a strong correlation between the sale of ice cream and the number of drownings. OR There is a third variable...the outside temperature (heat) causes the relationship between increased ice cream sales and number of drownings. ==Relationship between X and Y is spurious. 3. Pure Causality - This is not what is normally intended or claimed in science. a. Necessary condition If A is a necessary condition for B, then B will never occur without A.. Must have B for A to occur - Pregnancy, for example. b. Sufficient condition If A is a sufficient condition for B, any time A occurs, B will occur... If you have A, you'll have B. You can have B without A. c. Necessary AND sufficient conditions Given A and B, if you can establish that A is both a necessary and sufficient condition for B to occur...Example: Must have exposure to drugs to become addicted. If A is a necessary AND sufficient condition for B, B will occur if and only if A occurs. This is Pure Causality. d. The Nature of Causality... In science, it is next to impossible to establish pure necessity, sufficient or causal. We use "weaker" versions of causality... DIRECT Causal Relationship: X → Y Education → Income Sex → Attitude toward Animal Rights **Cause is too strong wording. Appropriate Wording: Variations (or changes) in X influence (or leads to) variations in Y. INDIRECT Causal Relationship; X → Z → Y Education → Job Opportunities → Income ***There is an indirect relationship between X and Y or Education and Income. II. Research Design A. What is research design? The strategy by which you will answer your research question. The strategy is the path/methods used to get from ideas to results . ~Some designs are purely exploratory ~Typically, design needs to be very explicit ~Usually, there is not just one way to design a project ~Some research questions lend themselves better to certain designs ~Need to consider all aspects of design when preparing design (don't figure out as you go along...have an overall plan in advance). Strategy for answering research question(s). Research Design does at least two key things: 1) Helps clarify WHAT it is you want to find out What do you want to find out? 2) Provides the best WAY to find out What is the best way to find out? a. Given your constraints - Maybe not enough time or money or may not be ethical. B. Decisions to make in research design a. WHO? - Who or What will you study? UNIT OF ANALYSIS - Who or what you wish to draw conclusions about... Who/what you examine to get a summary of all such units and explain differences between them 1. Individuals - Not a person...people 2. Groups/Organizations - Groups = informal; Organizations = formal 3. Social Artifacts - Products of human behavior (newspapers, books, cars, buildings...) 4. Interactions - Riots, protests, marriages, divorces... Avoid the Ecological Fallacy: Drawing false conslucions about individuals based solely on observation of groups. b. WHAT? (what aspects of the units of analysis will you study?) 1. Characteristics - "states of being" - age, race, height, membership in a group, year in school, etc. 2. Orientations - Attitudes, beliefs, opinions, policies, or thoughts about phenomena 3. Actions - Behaviors (e.g., littering, fighting, voting) c. WHEN? - When will your study be conducted? 1. Cross-sectional - At one point in time - taking a slice/snapshot of society (most common form for social research). If done well, you can make inferences about things that happen over time. To do this, you can ask questions of age or things in a person's past...this is HOW it can be done well. 2. Longitudinal - At more than one point in time a. Trend study - Study a population over time. The actual sample taken from the population will likely vary. This is the most basic form of longitudinal study (i.e., Gallup, GSS) b. Cohort study - Follow a specific subset of the population over time (based on some common experience). The actual sample will vary; however, they will have a common experience such as "baby boomers", Iraq War veterans. This is a more narrow focus, and defined population than a trend study. c. Panel study - This is the most expensive and the best method to study change over time. In this type of longitudinal study, the exact same people are followed over time. 3. Historical - Information can be obtained from past documents, TV, tapes, photos, and other materials. d. WHERE? - Where will your study be conducted? 1. Natural setting - Where behavior occurs naturally (we did not set it up) 2. Artificial setting - You set up, design, and bring in people (i.e., experiments) e. HOW? - How will study be conducted? What Mode( s) of observation will you use? *Survey *Experiment *Available Data *Content Analysis *Field Observation *Indepth Interviews Triangulation - Combining more than one method (2 or more methods) Mixed Method - This is another term for Triangulation...combining more than one method. C. The Big Picture - Refer to "The Big Picture" diagram listed on D2L. D. Discussion example Discussion Example used to illustrate various points... Theory: Going to college cause people to become smarter. Hypothesis: Going to college causes people to have a higher vocabulary. Null Hypothesis: People who have not gone to college have the same level of vocabulary. Causal Diagram... Went to College → Increased Vocabulary Independent Var. → Dependent Variable Possible attributes? Yes or No **Criteria for causality? ~Logic - Is it logical? Yes, because of exposure to more words in college ~Time Order - May be a problem in this scenario. Must test at high school level, wait 10 years, then re-test and choose whether they went to college...possible method. ~Association - Can be tested ~Non-Spuriousness - Possible other variable? Yes, social class, parenting time...others... a. Research Question: Does the size of a class influence how well students learn in that class? *Importance Why is this important? For BASIC research - to find out more about how people learn better... For APPLIED research - to convince others that this is important. *Overall goal - The general goal is usually explanatory. Other possible goals...exploratory, descriptive, predictive, engineering. Predictive example: Smaller class sizes could result in better learning... Engineering example: Pres. Clinton had a goal to have smaller class sizes and set up federal laws in order to "engineer" the class size. *Hypothesis - H1: Alternative Hypothesis H1 (alternative hypothesis) - The alternative hypothesis is alternative of the null...not alternative to the original question. "Students who are educated in smaller classes learn more than do students who are educated in larger classes." H0 (NULL hypothesis) - Null hypothesis is done first... "Students learn as well in small classes as they do in larger classes." OR "There is NO relationship between class size and learning." *Causal Diagram CLASS SIZE → LEARNING ↑CLASS SIZE → ↓LEARNING *The above example demonstrates the follosing: ↑Independent Variable → ↓Dependent Variable *Causal criteria **Logic - This variable was added by Mertig in addition to criteria listed in text. Does is make sense? **Time Order - Independent comes before the dependent variable? People must be in class first. **Association - Are the variables related? **Non-spuriousness? - Must establish that is no third variable causing relationship. To determine non-spuriousness, you must look for a possible third variable and make a determination. *Concepts - What do we mean? *Variables and measurement - How it's measured... CLASS SIZE... LEARNING... The below demonstrates difficulties in measurement and how what we choose to measure is itself making a classification... CLASS SIZE..... LEARNING..... # in class on average? Retention of info (on a test)? # enrolled? Grade? # of seats available? Perception of amount learned? Students' perception of class size... Later success in life? *Units of analysis/units of observation Compare: Hypothesis a: "Students in smaller classes learn more information than do students in larger classes." Hypothesis a: Unit of Analysis is Students. Hypothesis b: "Smaller classes lead to better learning than do larger classes." Hypothesis b: Unit of Analysis is Class. Unit of Observation = Class for Size and Students for Learning. *WHAT is being looked at? **Characteristics? of classes and students **Orientations? of students (perceptions of class size & less learning) **Actions? *Time dimension cross-sectional, longitudinal, historical *Setting Natural? Classroom Artificial? Set it up *Sampling considerations ~Where? Grade school? High school? College? ~What classes? All? Within a specific major? Within a specific topics...just Intro classes? ~How will classes and/or students be selected? (How many and how?) *Mode of observation **Survey? Ask questions **Experiment? Set it up **Field Observation? Go to different size classes **Available data? Registrar/Canned data **Triangulation? Use more than one methodology *Data processing and so on... How to analyze - data analysis Items reviewed from Assignment I: Stardard format for research article (typical).... ~Abstract *** ~Introduction *** ~Literature Review (hypothesis may be at the end of this section) *** ~Methods (aka: data, survey, experiment) - How was data collected to answer hypothesis? *** ~Results (aka: findings) This is usually the hardest section to understand. *** ~Discussioin/Conclusion (sometimes these are blended together) Usually easier to read...interpreting in "common" language. This is where another will provide limitations (problems w/research). ~References ~Notes (Sometimes Acknowledgements) *** ~These are the most important sections to know...