APR 280 Week 6 Notes
APR 280 Week 6 Notes APR 280
Popular in Investigation and Insights
Popular in Advertising
This 7 page Class Notes was uploaded by Tricia Sylvia on Friday March 25, 2016. The Class Notes belongs to APR 280 at University of Alabama - Tuscaloosa taught by Brandon K. Chicotsky in Spring 2016. Since its upload, it has received 14 views. For similar materials see Investigation and Insights in Advertising at University of Alabama - Tuscaloosa.
Reviews for APR 280 Week 6 Notes
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: 03/25/16
Lesson 14 Tuesday, March 8, 2016 8:08 AM What is research? • Trying to find solutions • Explanations • New facts Why does research matter? • Save time and money • Gain insights • Insights lead to action o You know what to do on behalf of your client Goals of Research • Describe • Diagnose • Predict Sources of Secondary Data • Internal corporate information • Gov't agencies • Trade and industry associations • Marketing research firms • Commercial publications • News media o Pros: allows for specialized searches generally easy to use/navigate o Cons: often no raw data. Sometimes need licenses to access which may be cost prohibitive Databases • pew Research Center o Media o Us politics o Social trends o Religion o Internet and technology o Hispanics o Global • Lexus nexus o News media o Legal pairings • Simmons one view o Contains data profiling consumers of a wide range of products including both demographic data and media preferences Types of Research methods (field research) • Test marketing o Good data if random sampling • Surveys o Questionnaires • Postal • Face to face o Consumer panels o Interviews • Telephone • Open ended • Group interviews • Observation Validity • Face validity = criterion • Critical because it weighs on the perception of your client that you are doing something of value o Internal validity • Are you doing what you set out to study o External validity • Can other people replicate • Is it correct? Reliability • The consistency or repeatability of the measurement tools and the results Example: your friend who lies all the time is reliable in that they will like but they will not be valid in what they say Generalization • Sample represents the population Population (N) Sample (n) Sample frame • the list of pop elements from which we draw the sample Sample size • The people we actually sample Bigger sample does not always mean better results In stats, we have confidence intervals and margin of error that can tell us how the sample represents the population Example: confidence interval = 95%, margin of error (SE) = +/ -‐3% 60% of people Meaning if we conducted th is survey 100 times, the percentage who gave the same response to this question will range from 57% -‐63% 95 out of the 100 times Sampling steps 1. Determine the population 2. Get the sampling frame 3. Draw your samples Sampling methods • Probability o Random selection o Each unit has a non-‐zero chance of being selected • Non probability o Does not use random selection Simple random sampling is ideal Probability: Systematic random sampling 1. Obtain list of entire population (N) 2. Determine sample size (n) 3. Determine sample width (k) 4. Calculate (k) by N/n Probability: Stratified sampling • Population is divided into different subgroups based on demographic • Sample is picked from each strata Non-‐Probability: Convenient sampling Non-‐ Probability: Purposive sampling • Samples are selected based on specific, preselected criteria or profile o Example: iPhone users, mothers, people who have brain injury etc. How is purposive sampling similar and different to stratified sampling?< -‐-‐ on test Non probability: snowball • Each person brings 3 people Lesson 15 Thursday, March 10, 2016 8:09 AM Probability • Simple random o Most basic o Units have equal chance of selection • Systematic random o Units are ordered and every nth member of the population is selected o First n is random Probability: • You can generalize to the population • Pros o Less prone to bias o Calculation of sampling error is possible form which one can determine statistical significance • Cons o Requires a list of all elements o Time consuming/costly o No advantage w small numbers Non probability • Pros o Quicker o Cheaper o Flexible • Cons o Less generalizable Surveys • With focus groups, these are the most popular form of market research Survey Research can show correlation but not causation • Pitfalls of survey research o You must ensure a large number of the selected sample will reply • Responding rate • Partial/full question completion o Are people telling the truth • Malingering • Social desirability bias o Wording can diminish validity • Survey design o Think small-‐-‐most surveys will be taken on a phone screen o Make it clean o Clarity o Flow • Start easy, be engaging o Relevance o Objectivity • Avoid question bias • Space choices evenly • Randomize choices o Look and feel o Question structure • Nominal questions o Answers like male/female • Ordinal o Ranking things • What makes a good survey question? o Simple o Specific o Individual question at once o Exhaustive (all possible answer choices are given) • Closed ended questions o Dichotomous • Yes/no o Multiple choice with an option for other • Exhaustive and exclusive o Ranking scales • Likert scale § Agree-‐disagree • Semantic differential scale § Happy-‐sad • Open ended questions o Include a few o Ensures that people pay attention, more possibilities o Big consideration how much is too much o Is the range of answers extremely long?? Use open ended o Are you unsure how respondents might answer? Use open ended • Tips o Go over objectives • Make sure your questions feed into them o Avoid leading/loaded questions • There should not be a right or wrong answer § Example: how would you rate the career of legendary outfielder joe DiMaggio o Multiple choice questions should be mutually exclusive and exhaustive o Ask DIRECT questions • Don’t assume respondents will understand this is not a test § Example: what suggestions do you have for improving the apple watch • This could be interpreted in many ways; feel, look, system o Don’t use unbalanced scales • Example: strongly agree, agree, neither, strongly disagree o Avoid double barreled questions • One question, one answer at a time § Example: DON’T: how likely are you to go to dinner AND a movie this weekend o Pretest the survey Myths about sampling: Myth: • Large sample sizes are best • WRONG o Representativeness is key Myth: • Researches should sample a fixed % of a population to produce an acceptable sample size • WRONG o Probability based sampling uses mathematical calculations to debunk this Myth: • Researches should bases sample sizes on industry standards or "typical" sample sizes used in other research projects • WRONG o Make thoughtful decisions based on individual requirements of research needs Sample Distribution • Grouping or arrangement of a characteristic that researches measure for each sample member • It reflects the frequency with which research assign a sample characteristics to each point on a measurement scale • Common in survey research Normal Distribution • Bell curve • Frequency by which data occurs Conducting a "census" • Everyone in target population is included Standard deviation • Standardized measurement of dispersion (or variation) around a mean • Simple unit of measurement • Dispersion of possibilities or responses • Gives researchers a basis for estimating the probability of normal distribution and probability based sample distribution that always contains some error Confidence Level • Degree of certainty researchers can have when they draw inferences about a population based on data from a sample • How confident are we that our sample is representative of the population (+/-‐) • 95% is standard rarely is a lower level used Confidence interval • Range or margin of error that researchers permit when making inferences from a population/sample • Usually stated as a positive to negative range (+/ -‐3) o Margin of error is SIX Variance • How something is dispersed throughout a population • Variance measure most used in research: .5 o This represents 50% of a population belonging to a category Calculating sample size: • Variance is always .5 • Confidence elvel and margin of error turn into decimals (+/ -‐3= .03) Standard Deviation • 90% confidence level= 1.65 • 95% = 1.96 • 99% = 2.58 Read the final part of chapter six • Calculating sample size strategic management austin and pinkleton
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'