Research Methods Study Guide
Research Methods Study Guide Pols 201
Popular in Research Methods in Political Science
Popular in Political Science
This 48 page Study Guide was uploaded by Lauren Jones on Monday March 7, 2016. The Study Guide belongs to Pols 201 at University of Tennessee - Knoxville taught by Adam Eckerd in Winter 2016. Since its upload, it has received 79 views. For similar materials see Research Methods in Political Science in Political Science at University of Tennessee - Knoxville.
Reviews for Research Methods Study Guide
Report this Material
What is Karma?
Karma is the currency of StudySoup.
You can buy or earn more Karma at anytime and redeem it for class notes, study guides, flashcards, and more!
Date Created: 03/07/16
Why do we do research? Lecture one https://quizlet.com/_234gtc password is week1 This class will tend to lean towards policy, instead towards political science o Course will tend to be applicable to the real world The basic process we will encounter is a distinction from the scientific method Class project! In small groups, that we will pick over the weekend o Located on the blackboard site Participation is key! o Does not take attendance, but just being here is not enough There is class on the 26 , incorrectly marked on the syllabus Memos are due on Tuesdays of that week Open to approaches, not exactly the same things o He will purposefully be unclear Research and data o Data allow a researcher to: Describe data through the use of: Frequency, distributions Graphs Statistics Anecdotes Narratives Interprestations o Come in a variety of forms Data can be Statistics Interpretations Narratives Contextual o Information, anything that is useful in decision making Ideally data is high quality, but there is a probability of low quality of data o There are some preferences of some data or others Would you rather have a narrative or a statistics? Broader base, more people to pull from Narrative o Knowing A lot about few Statistic o Knowing a few about a lot o Numbers are important to inform the stories Interpreations o Understanding issues deeply instead of broadly Why? o To help us make better decisions Research should inform our ability to make decisions Or, there is probability to make ideologically biased choices Evidence goes over ideologically What does the evidence suggest we should do? o If there is no evidence, not achieving o Information should make decisions Describing the world Use information to understand the context we make decisions Explaining How and why something has or will occur Predicting Past is prelude, information is the ability to explain Ability to predict the likeliness of something happ Description Using data in which we make decisions o Be able to take some variable in a context and describe it Data allows us to understand the situation better than we did before we did By breaking something down, you can understand certain degrees of information better o Schooling, smoking are examples Comparisons are possible o For example, the more education = the healthier people are o People who are educated can afford to pay for their own healthcare Things can also be occurring overtime o Research is to figure out why something occurs o Limitations of description Be able to explain we should be able to predict We very often can’t observe things actually happening o We can gather data, but we can’t have any data on something very specific For example, there is not really an observation on jack daniels workers going to congress and why But, we can collect data and try to determine how x causes y What we care about here is the cause and effect o Education and earnings and unemployment have a strong relationship Higher education, more money you make Theory: more education? You should be able to access a higher paying job We can test this! o And evidence supports this hypothesis o We’ve explained income variation with this Be careful! o Correlation is not causation In social science work, we cannot completely isolate variables For example Most bank crises start in September o Might look like something is significant, but is actually just is a coincidence o In research, ascertain which is meaningful and something meaningless For example, there is a correlation between global temperatures and Us postal changes o But of course, this is meaningless o Still meaningful because you can draw other issues But still possible to muddy correlations that can be drawn Inference and Explanation o We want to infer things about population We want to know the characteristics of things Inference o We want to know something of a population, but we can’t do information about everybody So we have a sample, create a statistic, and the estimate Polls are more often right then wrong Steps in research process o Identifying problem What is the underlying problem What are some theories? There are a multitude of right answers but find the best one o Make a hypothesis from it Statement of relationships between to variables You can come up for hypothesis in multiple ways especially in social sciences o How to analyze Unit of analysis The what or who that will be studied Measure how x causes y o Collect data o Specify model o Estimate model o Test model o Use model o Share results Variables Independent and dependent variable o Independent The cause o Dependent is the effect We don’t prove things in social sciences o We can only find strong correlations Data o Can be quantitative or qualitative o Be careful about how you measure something Test relationships Everything presented is a broad overview of this semester https://quizlet.com/126187315/research-measurement-and-the-nature-of-knowing- flash-cards/ week2 Research, Measurement, and the Nature of Knowing :1.19.2016 Levels of Analysis o Pure: Theoretical Try to understand the way the world works in a general way Help scholars understand the causal links between variables and social outcomes at a general level We are not specifically interested in the specifics, but the general We are trying to understand what characteristics of individuals lead people to vote in certain ways. o Policy (exploratory) Look at social outcomes in one specific context for the purposes of making a decision in that context We want to know specifically We want to know things about a specific situation o Applied Consider social outcomes more specifically in varying contexts- bridge the gap between very specific policy research and general theory This is the gap between policy and pure We know that there are broad trends o We also know that a lot gets lost with one specific instance o Applied is using a mix of broad human behavior and specific context of a circumstance to better understand the way the world works o Action (descriptive) How can we help people understand that? Doing research for the point of helping the public understand and policy and politics affect their lives Theory and Practice o There is no distinction Theory is informed by observing practice We develop theory by gathering evidence from practice Observation about knowing how the world works In developing theory by understanding the world better, we form practice The Nature of Knowing o Philosophical section o Essentially the scientific method o Still following the same general ideas, Ontology Our starting point The question is “what it is we think we can know” o What is the nature of reality? o What should we spend our time trying to know? o Before you start doing research must understand If there is an objective reality or not? There is a tangible world that we can understand Causes and effects exist Overtime, as we learn more about the way the world works We get closer to understanding the Truth. o Truth There is a physical way the world works, including human behavior Scientist view This is the more dominating view Social Constructed reality? There may or may not be an objective truth, but because we are social beings, we have come to some set of agreements about how the world works. o Little t truth What we know is what we agree upon What makes physical reality is what we agree upon Humanist View o There is an important distinction here. Epistemology How can we know what we know? o How do we acquire knowledge? If our ontological perspective says there is an objective reality, we can know this by observing this objective reality Empirical testing Observation o Scientist Theory Interpretative logic o Humanist View Axiology Do we selectively know, generally know, or does context matter? o If you are an objective realist you believe you study the world as it is There is no alternative interpretation o If you are interpretists You believe value underlie everything. Methodology A term that is used most of the time o Not “research method” Given what is possible to know, how can we actually learn it? What is our framework? o Positivist Observation and theory, the scientist They believe in observing the world o Post-positivist/interpretive Dialogue, textual analysis, critique Rhetoric How do we convey what we know? o Modes of communication or argumentation? Data, analysis Language of science, how we do analysis, how do we come to conclusions from that analysis Empowerment Dialogue Recognizing the way that people collectively view the world and try to change that Praxis This is one of the most important things we should take away from research o How do we use what we know? How do we apply that knowledge to understand our world Scientists say explaining or predicting is the best way to make a knowable world Post positivists Gain mutual understanding, and create conversations in which we can understand context and develop solutions Logic What is our structure for drawing conclusions? o Inductive You have a general principle about the world, and from that you draw a specific answer for a specific instance. o Deductive logic You have a specific piece of information, you can take it on a broader skills o There are flaws in thinking in both ways Deductively If something happens in one spot doesn’t means it’ll happen everywhere Inductively Just because a general statement is made doesn’t mean it is specifically fitting. These two aforementioned methods are more for positivists o Abductive When a bias is or is not confirmed Easy to do this This is how people think If you adhere to more of the socially constructed view o Be consistent in your ontological perspective The Scientific Method o Identify a problem or question Define the problem Use literature to find the problem Develop a hypothesis o Collect Data Determine which unit to analyze Developing a data collecting plan Collecting and prepping data Where and how we collect the data, and then actually do it Observe the world in the same way WE can’t sit and watch things o Data Analysis Specify a model Estimate the model Reject or fail to reject hypothesis Find if the hypothesis is good or not, basing this evidence Collect Data Everything is driven by the hypothesis development We are not going to prove or disprove the hypothesis, you will never prove something o Share results and make some conclusions Positivism o The world is real Empirical focus, Learning by observing Not how we think how the world should be Understanding the causes and effects o When doing research you shouldn’t talk about how the world should be, but how it is Independent variable, dependent variable distinction Research should be objective Objective? Means that you should avoid having strong opinions on a topic, because you tend to get on an abdjuctive tract Value Free? Don’t apply your specific values about how the world should be, not understand what it is you want. o Important distinction Don’t “think” or “believe” something In the Memo Should be replicable Someone should be able to do your study over Post-Positivism o The World is socially constructed from shared or individual meanings Always changing of time Once we change time, we will change the variable. You can’t always replicate social sciences because we always will change as people. Not constant Three Paradigms o WE will mostly deal with positivism Interpretists Empower the powerless Make better decisions Positivists Better understanding the truth of the world Post modernisms Everything we do is wrong. Quantitative or Qualitative o Positivist research is done with numbers Numbers can lie Either type of data can if within positivist or post positivist frameworks o Make your data to what is helpful Positivist Methods o Mathematical Modeling Game theory o Logic Modeling Causal diagrams o Qualitative techniques Content analysis Read through documents and coat them into numbers Surveys Case Studies o In political science you will get mostly statistics Post-positivist approaches o Not as scientific methody Interpretative Researcher will read transcripts, drawing a conclusion about how the world is understood Narrative Pretty much anything you talk about can be drilled down to a story o Find the story that people find for a story of a situation o Most politics interests follow the similar stories We are not trying to say what is right, but what the narrative is Emancipatory Examine power relationships for people who don’t have power o Feminist, Marxist, Ethnic Approaches Understand why the world is the way it is from the perspectives that it is already in. The point is to find a balance of power Post Positivist methods o Case studies Look at small sub set of the world Gain deep understanding of one case o Grounded theory Gather data while continually comparing and categorizing to derive o Ethnography The anthropologists The way a community views the world is studied o Narrative Postmodernism o By deconstructing the situation we can point out the actors Critique the story, understand, what motivations there are, what lessons there are Comes from literary critique Causality o Particularly important about policy Scientists care about this The intent of policy is to tweak some variable in order to cause a change in some outcome Idea that is a fairly simple straightforward logic Find an intent, tweak and invent an answer Dependent and Independent variables o Dependent, what we expect to occur o Independent variables, what we want to use to make a change to what to occur Independent variables will always precede an dependent variable in a logic model If, then. Logic Model o Inputs Government gets some sort of inputs, we are going to do something o Activities When we do something o Results in a direct output After this we will have A short term outcome A longterm outcome o And the impact o The key part of the theory is what happens next What Theory is? o Nothing complicated An answer to the world Gravity, Rational Choice, Public Service Motivation What Theory isn’t? o Not a specific answer to a specific question It is a general answer to a general question o Not scientific law There is some probability of a theory being incorrect There is some probability of a theory being incorrect o There may be times when theory doesn’t apply In social sciences It is more complex to get something so definitive. o Getting better than a coin flip is great How do we know? o We don’t know anything Until we have reached a theory that explains everything, we don’t know anything WE are going to make claims o That a theory is correct or incorrect o That something can hold or won’t hold Ideally, fully sufficient evidence can support a claim Often, people can quickly find a way to make a claim wrong Then go back through a cycle of evidence until there is a consensus reached o We learn in college is largely that consensus We often have shifts in views about what that view is overtime Evidence o Just about any information can be evidence Observations, religious beliefs The context will dictate the extent to which the evidence is valid We try to gather valid evidence and see if it is valid Validity o We don’t have evidence that is valid or invalid But we have a range of validity Face validity o Is something is plausible o Is the argument that someone is making plausible Content validity o Is it relevant Pragmatic o Is it realistic Evidence in political Science o Dealing with concepts that are hard to agree upon, define, and measure Program effectiveness Fairness Will differ based on your perspective Happiniess Justice When we do political and policy research, most important and difficult to define. 1.21.2016 https://quizlet.com/_236mmr Evidence in Political Science Evidence in Political Science o We are often dealing with concepts that are difficult to define and measure o They are very often abstract Program effectiveness Fairness Happiness Justice Happiness? o Defining it can provide an issue. o We ask specifically about specific policies Concepts o Three classes of concepts Directly observable Economic policies that are intended to see if people buy homes, you can see and assess Indirectly observable Exams are measures for school systems Theoretical concepts Concepts that can be represented with something observable o Intelligence o Job satisfaction The concept can be represented with something observable We need to develop an operational definition of the concept in order to measure it Operationalization of constructs Definition of things that they are measuring Indicator o The measurement of a concept is an indicator It represents, but does not directly measure the concept We might measure a variety of things o There are always errors in measuring Indicator= concept+ error A valid indicator Accurately measures the concept o You are never going to have a complete indicator o You will never have a complete measure Shooting for objective here Is measured with little error. o Please note that you can never eliminate all biases o Height Proving that there Is no perfect measurement You’d have to actually measure people throughout the day o Measurement with error Inches Just a standardized way of doing things o The reason something is measured by something doesn’t always make it the right way What are the problems with these arguments? o One thing to understand about research is that there are a lot of challenges All of these arguments have correlation causation issues. Corporations move jobs off-shore because corporate taxes are too high o Corporations don’t actually pay a lot of taxes, but they most likely move off-shore because of wage costs o This statement is almost completely unverifiable o You could jack up taxes on corporations and see if they will leave This most likely wouldn’t happen, for obvious reasons Renewable energy is impractical because it is too expensive o Not great technology yet, so yes, things are still expensive A lot of money up front, but you will ideally save money later o Also an argument that destroying the earth is also incredibly expensive This cost is externalized The economy has declined because union membership has fallen o Of course, they are many factors that go along with economy falling o “the economy” is a very loaded word Hard to define what exactly is a strength in the economy People who graduate from college are less likely to go to jail o People who are going to college are the kinds of people are who are not going to jail in the first place o Doesn’t actually solve the problem Research starts with an observation. o When talking about doing research Basically going through the process of the scientific method Collect data Come up with an answer Where does research start from? An observation of something we can’t explain or we want to know more about o Beer is expensive in TN Why is it so expensive At this point, you aren’t even looking at policy o But instead, what is happening and why Why? o Most simply, because of the high taxes on beers (high gravity beers) The research problem? The interesting question here is: o Why are taxes on beer so high? This is what we want to know more about. The scientific Method o Identify a problem or question Define the problem Beer is taxed too much Use literature to understand the issue Literature is previous studies to make more understanding o Also, look at other researchers Look for explanations o Sin Tax Develop a hypothesis The Sin Tax example o When taxes are high, people drink less beer o If taxes are high, fewer can afford or buy it Supply and Demand here The other industries in the state o Rent seeking Industries will lobby the government to benefit the industry Here this an assertion of YES, people drink less when taxes are high o Collect Data Determine unit of analysis The easiest way to do this is to determine your independent and dependent variable. o Independent- how high taxes are o Dependent- how much people drink A unit of analysis here is places Data collection plan You can look here at counties o Gather information about their tax rates Go to all the establishments that sell, and get their receipts Can calculate the per capita that people can buy Collect and prepare data o You must compare it with something to make a difference Get information about every county in the state What would very in the state is local state taxes You aren’t going to learn a whole lot from that You might want to look at other states as well You want to look for populations that are similar o Be careful of beer sales on per county o Make sure it is per capita Going back to hypothesis o You should expect as taxes get higher, you should see the per capita rate to go down Have a negative correlation All a regression is is an equation of a line. o If you run the analysis and you should expect to see a negative slope If you do, you have some evidence to support it That means, you have evidence that support, NOT PROVING Share results and make conclusions/ conjectures We don’t want to complicate it! o Analysis is pretty simple If you understand what a line is, it can work https://quizlet.com/_236nrk imsleepy The lit review is not o A summary of what’s been done before Do not cover everything Use literature that helps you build your case and defend your argument o Give a snippet of what is pertinent to doing? Not a comprehensive document of all research on a given topic Not everything that touches o Not a bullet list of key variables Bring a story together of variables Set up of why we have a certain set of expectations Lit review should o What is already known about the specific topic Opening paragraphs are all the same Gives the background of what the topic is and who we should understand it How do you specify the relationships between Look at the research hypothesis others have used o Look at key theories have informed understanding of the topic Not to rehash Read articles clearly o Be critical The point of building knowledge Here’s something they missed o Point of reviw is to justify and fully formulate the research question o Make the case that this research question is important, interesting, and you should care. If people care, the lit review is important You will turn research question into a hypotheses o Instead of a question, make a statement. Hypotheses. o Statement of some expected relationship X on y o If you can articulate statement clearly, you are on track o At the end of the lit review Make sure the hypothesis is obvious Null and Alternative Hypothesis o Null A statement of no effect, status quo State one of them as the thing we care about knowing more (this is the alternative) o We never “prove” anything You find a consistent evidence with the argument. o We don’t test if it is likely, we test if no relationship is unlikely WE assume this relationship doesn’t exist We want to assume there is no relationship, look for evidence that says that’s probably incorrect. o Intending to make statement How do they do this? You never know if you have a good or bad representation of a huge population. Research Design o Whenever you go through the process of going through the literature and defining the process, the research design should flow from the hypotheses Exploratory Relationship Causal Encouraged o How a change in one causes the change in another. o The way you state your hypothesis is tied up Should dictate what you do for the rest of the memos Should flow relatively after Validity o In the study Internal Did the IV actually lead to changes in DV What happened after didn’t affect beforehand. Framing makes it different. o External Can results hold true in different but similar cases Which is the right theory doesn’t matter o Hold water, some don’t Approaches Take on theory and tell what we should know about that argument, what is the previous argument, or fix it Try to figure out how these all work together Page 26 in the book, one through five o Good advice here How to abstract and make sense of it all Pick one writing style o Doing Research 2.2.16 The Research Process o Identify the problem or question o Develop a theoretical framework that provides one or more possible answer The research question o The most important step in the process Defining the problem is challenging and often unique to an individual Often impleies value judgements about what is or what not o What is the effect of x on y o This is unique to the individual Objective research The whole idea of objectivity is biased What is and isn’t important is a value laden decisions o Flint There was a political decision made to assume everything was fine o We decide what is important when we have a catalyst to decide this General research question, what is the effect of x on y Generally the way we frame o Specific enough to be manageable, that we can do an actual research project on Types of Questions, not an exhaustive theory o Reasons questions Explaining the reasons why others did something Did ___ do ___ because ____ Understand the reason of what is going on in people’s minds o Event Questions Explain a chain of causal events Why did the challenger explode? o The sequence of events o Evaluate the place back through down o Outcome Questions Explain why something happened the way it did instead of the other way? Two cities, two entirely different Inherently a comparison Where to find research questions o Convince enough people that there is enough emphasis on your question Social problem Creativity Interesting The researchers job is to explain why something is important o Once articulating a research questions, get into theories Looking into what is known about human decision making So what is theory o An explanation of human behavior How Humans act, what we deal with There are a variety of theories that explain behavior Normative and positive theory Normative theory o The world should work this way Most of the time people are discussing this Some argument about the way the world should be o This is not what we talk about for research Positive Theory o The world does work this way Based on empirical observation This is how we actually contribute to knowledge Talk about how the world actually works We need to understand how the world is before we even begin to think about the wy it should be? Components of a theory o A theory helps us predict or explain phenomena by linking constructs to propositions Construct is a term we use to describe actual things or ideas o See how well incumbents do in election Examples o Very specific supply and demand When environmental qualities deteriorate, people move away. When you have environmental problems, the price gets worse o Assumptions Where theory is useful Those that an economist would make here Willingness and demand have to get together Environment condition is there first, and then poor folk moved in o Explain/predict what happened Don’t predict well, but better idea than no idea at all If we want to do that… Theory must be o Falsifiable or testable If it can’t be tested it can’t be verified o Parsimonious Make it logically sound o Pragmatic or Useful It is easy to figure out what occurs, but how it occurs, why Why should I care? o Theory gives structure to things we observe Why do we want to understand our world better? Because we want our make our world better o Regardless of ideological predispositions b/c we want to make the world a better place Theory is abstract o We need to be able to be capable and able to understand abstract thought Give a person or machine a specific situation, it can make a specific decision It is only useful that one time. o Policy is the practical application of theory The reason we do research is because the more we become better on theory, our policies get better o We are already doing theory! Now we just need more structure Theories should be o Valid, must conform to reality o Simple, must simplify the world to make sense of it o Testable, we need some way to determine accuracy o Explain why we have seen what happens o Predictive predict what happens, not exactly If we implement something this is what is likely to happen o Relevant Must have some value to practice o Reliable Don’t expect accuracy o Observable It should be actually testable General theoretical argument, we want to test it o And then make contributions Research hourglass Idea is that the more people that do specific studies, the more we understand the world Theory and models o How theory informs a model All that a theoretical framework is is an answer to a question To develop a theoretical argument for an answer to a question o What provides the best answer to the question o Once this is done Find a model and hypothesis A theory is a general thing, explain o A model is specific, concrete, test and explore If theory says construct x causes y, we can test variable x vs y Models o Mental, logical, statistical We will do empirical Models are abstractions of reality based on theory Representation of specific phenomena o Research can be wrong, but useful o There can always be problems with theoretical arguments, especially in social sciences Theories, hyoptheses and models o Theories explain the general relationships o Models Define a research context and test hypotheses to infer o Hypotheses Predict specific outcomes between very specific in variables in the model Finding theories, models, and hypotheses o Use the literature Start exploring theoretical literature that is applicable Look at what other people have studied What were the arguments they have made o Are their distinct situations Use previous theory to derive framework Look for theories that are applicable Think general first o How have everyone do general searching See what’s there o When you’ve found what makes sense, hone in on what is working Looking for past research in your topic area o Look at the way professionals do this The most credible Why it is that way is because its peer reviewed Talk to other scholars Think tanks, newspapers, credible But be careful! Policy design Output is an independent variable o And outcome is typically a dependent variable If we do some government action, it will get some kind of output Evaluation design o Evaluation is common in policy research Offers clear insight for research design Only control building the bridge Causal change theory o We have an expectation that we will produce some desired outcomes Tweak an independent variable to see dependent variable We can’t observe the behavioral change We are going to infer Causal inference o Causality by nothing differences in outcomes Control other things, make inferences based on that Causal inference in open systems o We are inferring cause, but we don’t have a controlled study Evaluation design o Experimental not possibly for policy circumstances We do quasi experimental design Based on comparison groups o 2 like groups Vary the policy response provide the program in one place, infer validity of causal logic based on the outcome of the measures Randomized Controlled Trials o Choose participants from oe population, randomly into a control group Being random in first in collecting the sample, assigning people to either group Two layers of randomness o RCTs Are expensive, unrealistic Doing trials in education, crime, gets expensive Any measurement could be a bad measurement One Group o Look at one population of people Implement a policy Measure whatever our outcome is Interrupted Time Series o Simple Time Series o Regression discontinuity Predict what would happen, but then make a change on how they would be after If we see consistent improvement, effective Pre test, post test comparison group o One as a control group, one as the policy recipient There is no effort to randomize If possible o Do a full RCT Complicated to do Probably do a one sample design, or a two sample comparison o Measure key outcomes We should be able to communicate our results in a meaningful way An Example! o Step through the logic Reduce taxes (action Taxes on beer are lower (output) Demand for beer increases (short term outcome) Entrepreneurs enter the market (intermediate Industrial jobs created (impact/long term outcome) Look at all these things to measure o When you set up your design, measures go hand in hand Set up here as pretest and post test o We will have variable tax rates In the other group, I don’t change the tax rate Look at counties and citie o Testing hypotheses This is evaluation design We will get a probability of rates of change, then we will say policy is effective Asses the difference o See if the population difference To ascertain the effectiveness See if the policy has made a change o Think in terms in samples One year is a sample of a population of years. Measuring samples, you care for the long term average o See how representative 2015 is for the population o Calculate this with the standard deviation of the distribution of differences Interpretation o Rates of change in the two groups of counties Be the same, or the rate of change will be less If the true population was zero What do you have o Increase rate of brewery growth, in a county about 30% Theoretically Is likely a relationship between beer consumption taxes and start ups o GAO and CBO is a good source for federal government things 26 Project find out o Each memo builds on the other o Going through literature review we will discuss next week What approaches we should take How to read it, how to interpret it Keep current on the syllabus o Keep on the one on blackboard First Memo o Five pages or so Key areas Each one of these topics, should be plenty of stuff Find the ones are cited the most Go through and read them Find the most relevant stuff Articulate your argument o The trickiest part of doing research A literature review is not a summary But our argument Looking for ability to take what’s been done and looking to make your own argument o We should end up with “Our research question is…” Second Memo o A research design You will take the research question and start out memo 2 by staring with hypothesis Say which is independent and dependent How would you collect data and measure Third Memo o This is where you get specific Look for data sources to find it Well thought out plan to actually get data if you can’t find data o tell how you would go about it Fourth Memo o Talk to somebody who is relevant Go through how to conduct the interview Then, make a transcript Systems Map o Systems thinking and the interconnectedness of everything Start thinking about the biggest picture Think about all the social processes o All the ways that your dependent variable is affected by a million other things Draw a systems map Try to connect the dots o Positive negative or reinforcing loops For this, that will not be turned in online, but on paper o 1-2 pages Peer assessment o Way of acknowledging who is carrying the load Recommendation o The groups that do the best, set some time aside to do it Instead of chunking i Collaborate as much as possible o Start Broad If you have the hypothesis ready in memo one You can come up with two variables that you have to measure o Methodology o A general approach to learning about that which we can know In general a balance of goals A theory that is very generalizabile and reliable o Validity and relevance Aggregate is something that gives you less personal attributes Very little about the broader relationship o Methodological approaches Do we look on a broad scale, do we look at a smaller scale Inference and probability o We sill study a subset of a population to learn about something larger in the population Could get a sample Average of the averages give you a good parameter We don’t know what the population parameter o When they did the poll, they have no idea what the result is going to be. Samples and populations o No capacity to measure an entire population Impractical to think that we can calculate o Charachteristic we have calculated from some sample We use Roman letters do denote things about this sample How much money we make Parameters are characteristics of a population o We use greek letters to denote them o Parameters are usually hypothetical American, sample, greek, population Calculate the sample statstic, use it to estimate o We will calculate the mean of a sample, as x bar Iuse x bar to estimate mu Use s to estimate o Mean Figure out how good of an estimate you have o You will have some number below three Probability and the Central Limit Theorem o Our sample statistic is unlikely to ever match the population parameter If we took a mean of the means we would be close to the population average Probaility o The relative likelihood of occurrence of any given outcome or event o The difference between sample statistics Is sampling error The whole point is to estimate with as little sampling error as possible. How to minimize sampling error o To be a valid representation of population, must be selected Every item in the population has an equal chance of being selected Make it as random as possible o Sampling error can be positive or negative Mean K of the sample means o Much better estimate than any particular sample is. More samples taken The larger your sample size is in one sample, the better the population parameter Guy who figured this out o Worked at Guinness brewery The closer they get to that number, the better the estimate We know sample isn’t exact replication o We want to use this to represent and say something about the population Assess how well We can get an exact number that says we would have seen o We can’t afford it if it doesn’t pay for itself Constantly trying to gauge the benefit of a larger sample size o There is till gonna be 50 people who just don’t fill it out Parameter estimates o We don’t know how good it is o Does the sample mean Hypothesis o Research hypothesis states the theoretically expected outcome Null hypothesis states the inverse of the research hypotheses o Hypothesis testing Collect relevant or reject or fail to reject to nul hypothesis and discuss implications and limitations Significance o Two types of significance Statistical significance Only meaningful if we are using a sample to infer to a population o If you have population there is no need to asses significance, any change is meaningful 40 minutes better, than 30 Higher the level, more comfortable I will feel o Figure out how many days worth you need Stistcal tells you an estimate Practical Does any change actually make any real world difference Samples o When to use a population We will use the hypothesis in assessing some level of uncertainty Within or beyond a particular stage o Testing if wheter or not something is ineffective s Not testing on the entire population Your population is humanity The meaning of the null hypothesis o Any observed difference is the result of sampling error alone We want to know If it is likely, if it is how unlikely that would occur. The meaning of the null hypothesis Any observed difference is the result of sampling error alone o The observed difference is random, not meaningful Distribution o The variable tells us what values the variable takes and how often each value occurs We have some number of total observations, n o Population or sample, doesn’t matter o Each observation has some value or score for each o The distribution tells us the frequency with which each particular variable is found There is going to be variability There will be some distribution o There is some amount of time that is the lowest, and highest o Everyone in between Frequency distribution o Watch and wait, tabulate N=51, after gauges Response to
Are you sure you want to buy this material for
You're already Subscribed!
Looks like you've already subscribed to StudySoup, you won't need to purchase another subscription to get this material. To access this material simply click 'View Full Document'