Chapter 1_ Research methods notes

Chapter 1_ Research methods notes - Ghagfert Part 2...

Info icon This preview shows pages 1–10. Sign up to view the full content.

View Full Document Right Arrow Icon
Image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Image of page 2
Image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Image of page 4
Image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Image of page 6
Image of page 7

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Image of page 8
Image of page 9

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Image of page 10
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: Ghagfert Part 2 Research Methods *Psychology is a science— science requires direct observation and measurement to support theories and replicate experiments -This part of chapter one focuses on methods of empirical or scientific investigation {several methods are employed} *Why review this??? To improve understanding of the rest of the text, to improve critical thinking. and to introduce and prepare you for future study and work in psychology [ALL psychology majors must take a semester—long Research Methods course} EmEiricis-m: How to Know Things - Originally. there morocco kinds of Greek doctors: Dogmatists and Empiricists 1. Dogmatists attempted to treat illnesses by developing theories about the body's functions. figmafiem — the tendency for people to cling to their assumptions 2. Empiricists attempted to treat illnesses by understanding the illness through the observation of sick people. Erngiricism - the belief that accurate'knowledge of the wortd- requires observation of it. Empiricists ask the question "Where‘s the evidence?" r Only in the last 300 years have people trusted observation over elders, laying the foundation for modern science. Empiricism is not infallible. however i Understanding natural phenomena through empiricism requires a Scientific method a a way to gather taste that will lead to the formulation and validation of a the-cesifidso defined as a set of ' rules and tediniques for observation that allow observers to avoid the illusions. mistakes. and erroneous conclusions that simple observation can produce * Three things make human behavior especially difficult to study - gmglgfity: the brain is hearty infinitelycomlplex as a stnicture and it- is responsiblefor producing thoughts, feelings, and actions that are the core of psychology's concerns - variflhirflr no two people ever do, say. think. or feel exactly the same thing under exactly the-same conditions - ivim.‘ people ohen react differently when they are being watched compared to when theyare not. and each individual may have a unique reaction to being observed Scientific Method Terminology vt variable is an aspect of a situation that can very or change. It is a characteristic of a substance, quantity, or entity that is measureable. Measurable conditions, events, characteristics, or behaviors observed or controlled in a study IMN variables specify how the variables are measured or manipulated in a study. They involve a description of an abstract property in terms of a concrete condition that can be measured *Facts are established by collecting thug. whichare careful observations or ownericelr measurementsot a. phenomenot'i. Data include the aggregated measurements of all variables in a study. Data are “obiective’l because researchers try to eliminate distortions based on personal beliefs, emotions, or interpretation while collecting them vi. M is a tentative idea that might explain a set of observations”. 'an educated guess about variables or It'te'relatignehip"hetwelar'r variables in a study. Hypotheses are very specific and testable predictions nit. theory is an interlocking set of concepts or principles [system of interrelated ideas} that ere-a1: set of obsewations'or research findings. Hypotheses focus on relationships between variabies ' a study. while a theory focuses on underlying reasons why these relationships occur. More comprehensive than a hypothesis. Entire theories cannot be tested with one study. but rather mu st :-: proven or disproven via many studies. Good theories. once developed, lead to many testable predictions {hypotheses} «Replication involves repeating the method of a study and collecting comparable data as were found in the original study. Replication is necessary to improve confidence in the original results and lend tu rther sup port to theories 5 s of i tifi fig 1: Observing Events -Sciontism want to know the facts as free from any particular notions of their significance as possible. iFacts are established by collecting data. Properly collected data can be replicated. Data are “objective” because researchers try to eliminate distortions based on personal beliefs. emotions. and interpretations. f~ic interpretations are made at this stage Step 2: Formulating Questions -lvlost of science is about answering questions raised by observations. These questions are formed in the same way most peopie would ask questions based on their observations Step 3: Forming a Hypothesis oTo try to answer a question, scientists make an educated guess about the answer in the form of a hypothesis. This third step is where variables are first delineated. This provides a scientifically testable way to answer the questions Ste 4: Testin the othesis 'The researcher must now go about collecting new data to test the hypothesis. But first, one must create operational definitions oi variables, so that the hypothesis may be scientifically tested. After, a number of varying techniques are applied in hypothesis—testing. a. discussion of these techniques comprises the bulk of this iecture on pan 2 of chapter 1 grep 5: Formulating a Theom *This step uses evidence from step 4 to formulate and support a theory. Once a theory has been formulated, it plays a key role in the process of formulating hypotheses. Each prediction of the theory is, in fact, a new hypothesis to he tested. Stag 6: Testing a Theory oFinally. the theory is tested via the formulation and testing of hypotheses. Researchers evaluate a theory by testing its hypotheses. 'EaCh time a lheory makes a correct prediction: the theory is supported. Each time it fails to make a correct prediction, the theory is weakened. If enough of its predictions are unsupported: the theory must be rejected and the data explained in some other way. on good theory is feisirfebr'e. meaning that is makes predictions it cannot “squirm out of.” Step T: Figpgrling Ftesults -This involves sharing the results of your hypotheses and theory testing in scientific presentations at conferences or via a scientific report floumal article or book). This is argu ably the most important step in the scientific method. ? _ : sacs builds upon itself. If the earliest scientific advances of the Enlightenment period had not :een shared, the world we live in would be drasticany different today (transportation. medicine, education. parenting. communication, etc]. Without the recording, reporting, and sharing of scientific knowledge, the knowledge may be lost and new or more advanced discoveries based upon it may never be made Sampling * Different scientific studies employ different sampling techniques * Case Study — a scientific study that involves a single participant, examining his or her psychological characteristics in detail. it is worth studying an exceptional or unusual individual because it might provide insight about a psychological phenomenon. One must be cautious about generalizing from a single case because any particular person may be unusual for many reasons and, therefore, may not be at all representative of people in general. * tvlost often, psychologists are interested in explaining why unexoeptional [i.e.. "ordinary-“J people do what they do- usually psychologists observe many people and average the observations to gain an understanding of typical behavior - The Law of Large Numbers — law of statistics stating that as sample size increases, the attributes of the sample more closely reflect the attributes of the population from which the sample was drawn - Population — the entire set of relevant people or animals that might be measured + Sample — a group that is drawn forrrr a larger population and that is measured or observed in a study Averaging o The average of a sample cannot tell you anything about an individual in that sample; instead, the average can tell you that when a large sample of one population is compared to anotherr the average measurements of some behavior may be reliably different. What is true about people on average is almost never true in every case. a conclusion can be true on average and allow for exceptions. Psychological methods reveal patterns rather than absolute truths. ' Freguency' Distributions — graphic representations of the measurements of a sample that are arranged by the number of times each measurement was observed Ecrimivg flgigticg - brief summary statements that capture the essential inform ation from a frequency distribution II Descriptions of Central Tendency — summary statements about the value of the measurements that lie near the center or midpoint of a frequency distribution - Mode — the "most frequent" measurement in a ireeuency distribution v Mean — the average of the measurements in a frequency distribution - Median — the “middle” measurement in a frequency distribution, or the value that is greater than or equal to the values of half the measurements and less than or equal to half of the values of the measurements - Descriptions of "v'ariability— summary statements about the extent to which measurements in a frequency distribution vary from each other - Hange— the numerical difference between the smallest and largest measurements in a frequency distribution v Dther descriptions of variability include variance and the standard deviation, which or; ways ot tiguring out how similar or different scores in a distribution tend to be issues and Problems in the Scientific Method -.r-'i number of different issues arise as part of the scientific method that can call into question the accuracy. applicability, or interpretability of a study. A ‘icw are outlined here and others wilt be discussed later aswe review research techniques —Fteliability moans consistency. Data are reliable if you find the same values each time the variabie is measured. Fieliability can apply to the measures used in a study or to the study itself. Measures shouici be tested to ensure reliability {this is often calied calibration}. .Ei reliabia study is one that can be replicated—that is, obtained again if the study is repeated. 1il‘t'hen reading the results of a study. one should find out whether they have been replicated *‘il'aIidity means that a rne’rh od does in tact measure what it is supposed to measure. Also applies both to measures used and the study. Measures have been used in science that don't actually measure anything related to the property or variable being studied. A study itself may be reliable but not valid. or vice versa. -Bias occurs when conscious or unconscious beliefs. expectation-e. or habits alter how participants in a. study respond or affect how a researcher sets up or conducts a study. thereby influencing its outcome -The act of observing others can change the way they act. Knowing that you‘re being observed may change the way you act itn response eta , people have a tendency to respond a particular way regardless oftheir actual knowledge or beliefs Igamgling bias occurs when the participants or items are not chosen at random but instead are selected so that an atln'bute is over- or underrepresented iExErimenter exEcmneI effects occur when an investigator’s expectations lead him or her [consciously or unconsciously} to treat participants in a way that encourages them to produce the expected results Teehnigues to Avoid Elias oSome fom'is of bias can be reduced or eliminated by altering the way that you collect data Elias muraiistie Observation — a method of gathering scientific knowledge by unobtrusively observing people in their natural environments. You're not prone to observational bias it you don't know you’re being observed. Unfortunately. some of the things that psychologists want to observe do not occur naturally- strange situations. rare events AND some of the things that psychologists want to observe can only be gathered from direct interaction with a person— suweys, interviews. lCitests. physiological tests. Also, it's difficult to test hypotheses using this technique By allowing subjects to respond privately or anonymously {and guaranteeing an onymlty], effects of bias in response may be reduced *Seme behaviors that are not susceptible to bias- reflexes or automatic reactions r 1' _. :e seep the participant ofind to the purpose of the study through deception. bias is not a factor. "::s sometimes requires a cover story. or misleading explanation. It might also require fitter items. or pointiess measures that are meant to mast: the true purpose of the oheenration -Fta ndern sampling — a technique for choosing participants that ensures that every member of a popufation has an equal chance of being inetuded in the sampte. Allows the right to generalize from the behavior of the sample to the behavior of the population. True random sampling is extremely difficult and is never really done. lvlost samples are volunteers that are “encouraged” in some way to participate. Most are also young. educated. weatthier. and white. ExErimenter EIEMF‘IG! effects -To guarantee that these effects don't happen. the experimenter can use a doubleblind design. in which the participant is “blind” to {unaware of} the predictions of the study (and. therefore. cannot consciously or unconsciously produce the predicted results}. and the experimenter is =blind" to the group to which the participant is assigned or the condition that the participant is receiving (and. therefore. experimenter expectancy effects cannot produce the predicted results}. Deserifi've Research Teshnigues *For the scientist. facts are NOT intuit-lens. impressions. or anecdotes. Essential to the scientific method is careful. systematic. and unbiased observation that can be repeated by others. Psychologists use a variety of research tools and techniques. each with its own advantages and disadvantages. The first set of techniques are called Descriptive Flesearch Tools Genie researchers specialize in collecting data from real-world settings. catled naturalistic observation {described earlier] «a case study focuses on a single instance of a situation. examining it in detail {also described eartier‘i IA sgrvey is a set of questions that panicipants are asked about their betiofs, attitudes, preferences. or activities. Surveys are a refativety inexpensive way to collect a lot of data fairly quickly. They provide data that can he used to tormuiate or test a hypothesis. They are by far the most comm on descriptive research technique in psychotogy and one of the most common in all of science riJnfortunatety. the value of surveys is limited by what people are capable of reporting accurater or willing to report honestly. Surveys are not useful for asking certain questions. such as ones about behaviors that are performed uneon sciousty. People may not always respond honestly. especially if a survey touches on sensitive personal issues. such as sex {this represents a form of bias} -hlot everyone who is asked to respond does. in fact. fill in the survey. Because a particular factor [such as income or age] may inctine some people. but not others. to respond. it is difficult to know whether the responses obtained are actually representative of the whole group that the survey was designed to assess vSurvey questions have to be carefully worded so they don‘t lead the respondent to answer in a certain way and yet still get the data of interest Correlational Research IF-lesearchers use another method to study the relations among variables that relies on the idea :' correlation vi correlation is a relationship in which two variables are measured and changes in the measurements ol‘ one variable are acoornpanied by changes in the measurements of another variable. Correlational research involves measuring at least lwothings about each of a number of individuals or groups {or measuring the same individuals or groups at a number of different times} and looking at the way one set of measurements goes up or doom in tandem with the ether set of measurements. Correlations always compare one pair of measurements at a time. -Cine advantage of oorrelational research is that it allows researchers to compare variables that cannot be manipulated directly. it also allows researchers to make predictions about the value of one variable based on what is irnovrn about the value ct another variable -The main disadvantage is that correlations indicate only that fwd variables tend to varytogether, not that one causes the other. Gorrelatr'on is not causation ail. correlation coefficient [often simply called a correlation] is an index; of how closely interrelated two sets of measured variables are. The higher the coefficient, the better the vs[ue of one measurement can predict the valve of the other. it is a measure of the strength and the direction of a correlation, which is signified by the letter riwith a range = 'l to —t }. The number signifies strength while the +."- signifies direction -The closer the correlation is to in or —1.Ei. the stronger the relationship. ivisually, the more tightly the numbers cluster around the line, the higher the correlation. A zero correlation indicates no relationship between the Mo variables. *Poeitive Correlation — describing a relationship between two variables in "more-more" or “lesslees” terms {value of variables co-vary in same direction]. It is a positive relationship is one in which increases in one variable are accompanied by increases in another. It is indicated by a correlation value that falls between CI and 1.0. -Negative Correlation — describing a relationship between two variables in "more-less" or “less- more" terms {value of variables co~van‘.r in opposite directions]. It is a negative re[ationship is one in which increases in one variable are accompanied by decreases in another. It is indicated by a correlation value that falls between —‘l.fl and 0. 'Few variables are perfectly correlated. instead. the value of one tends to change with the value of another, but this tendency may be weak or strong. The stronger the correlation. the more confident you can be in predictions based upon it. Correlations can be said to be strong [e.g.. r= .BCIII. moderate leg, r = -_ac}, or weal: leg: r: -.2EI] depending on how many exceptions there are to the rule .ll=l’l with more exceptions being weaker correlations Correlation and Causation Human beings are eager to connect an effect to some cause. to the point that we often make connections that aren't really there [see pseudopeychology and astrology later}. .Just because two variables are related does not mean that one causes the other or vice versa. CORRELATION IS NOT GAUSATI'DN E -': eescover or prove causality. we need more control and manipulation than mere observation or sfipiricism provides *Confounds {or confounding variables] are other possible aspects of the situation that vary along with one or both variables in a study and could be the actual basis tor measured changes bebveen variables -The Third—Variable Problem — the fact that t'itro variables may lee correlated onlyr because they are both caused by a third variable {a confound). The causal relationship between two variables cannot be inferred from the correlation between them because of the ever-present possibility of a confound causing a third-variable correlation -Foot size has a strong positive correlation to vocabulary in children. The larger your feet, the more words you know. So does one cause the other“? There is a third variable of age. veil variables that are causally rglated are correlated. but not all variables that are correlated are gausalty rclated- causality is just one of many relation ships that correlated variables may have Eerrimentation ilt is impossible to eliminate all confounds around a possible causal relationship using annotations Experiment — a technique for establishing the causal relationship between variables. Involves controlled situations in which the investigator observes the effects of altering one or more variables. Manipulation of one va...
View Full Document

{[ snackBarMessage ]}

What students are saying

  • Left Quote Icon

    As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

    Student Picture

    Kiran Temple University Fox School of Business ‘17, Course Hero Intern

  • Left Quote Icon

    I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

    Student Picture

    Dana University of Pennsylvania ‘17, Course Hero Intern

  • Left Quote Icon

    The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

    Student Picture

    Jill Tulane University ‘16, Course Hero Intern