Business Statistics, Midterm Exam 2024-2025. Questions & Correct Verified Answers. Grade A, Exams of Business Statistics

Download Business Statistics, Midterm Exam 2024-2025. Questions & Correct Verified Answers. Grade A and more Exams Business Statistics in PDF only on Docsity!

Business Statistics, Midterm Exam 2024-

2025. Questions and Correct Verified

Answers. Graded A

A good experiment.. - ANS-makes comparisons -avoids bias -has enough data all good samples are... - ANSrandom avoid bias two criteria - ANS1. a sampling procedure must be used

2. the sample must represent the entire population (truly random) b1= - ANSslope Biased Sample: Convenience - ANSchoose individuals in the easiest way -going to the oval and asking OSU students for their opinion on tuition Issue: sampling procedure is used, sample won't represent any population biased sample: under-coverage - ANSa subgroup of the population is excluded from the very beginning Issues: sample procedure is used, but can only represent the remaining population without the subgroup

Biased Sample: Volunteer (AKA Self-Selected) - ANSa call goes out and people enter the study on their own Issues: no sampling procedure is used, sample won't represent any population bo= - ANSy intercept box plot - ANSgraph of quantitative data box plots mat not always show the ... - ANSpattern of a graph boxplot - ANSone dimensional graph breaking the data into four equal parts, marks off the 5 number summary: min, Q1, Q2, Q3, and max center - ANSmean and median coefficient of determination - ANS-percentage of variability in Y that is explained by X -r squared conditional distribution - ANSsomething given something confounding variable - ANSvariable not included in the study that can influence results control group - ANSgroup getting fake treatment

dependent variable - ANSresponse, response to what you change, what happens in the end design: question wording - ANSthe wording of a survey question can affect the results -should, don't you think? -can lead to bias design: type of survey - ANSphone, door to door, mail does the mean or median have to be in the data set? - ANSno events (characteristics) - ANSsubsets of S that you're interested in , A, B examining residuals - ANSif there are patterns, that is bad, no systematic change, unusually large values, no influential points experiment - ANS-deliberately imposes some treatment on individuals -observes their responses -any sizable enough difference is deemed to be due to treatment, not chance frequency - ANS# in each category, shown through table, bar graph histogram - ANSdivides data into contiguous groups on the number line and shows how many are in each group -horizontal: variable measured

-vertical: number or percentage in each group if the conditional distributions are different, then - ANSthe variables are dependent, there is a relationship if the conditional distributions are the same/close, then - ANSthe variables are independent, no relationship implementation: nonresponse - ANSan individual is selected to be in the sample but doesn't respond to the survey -those who respond are likely to have stronger opinion than those who do not respond -dont be fooled by a high number of respondents, look for a high percentage of respondents implementation: response bias - ANSan individual in the sample responds but doesn't give the correct data -what you can do: -anonymity: don't have a way to connect you to your data -confidentiality: do have a way to connect you to your data, but won't use it and promise not to give away your data implementation: timing - ANSthe timing of a survey can affect the results -daytime home phone surveys on job satisfaction or unemployment independent variable - ANSfactor, thing you are changing to see effect on

interpreting correlation - ANSr=1 or more than one, perfect linear relationship r=.7, strong r=.5, moderate r=.3, weak r=0, none interquartile range (IQR) - ANSdistance taken up by the middle 50% of the data, if high concentration of data is in the middle, the IQR is small -need to divide into quarters to find it IQR= - ANSQ3-Q joint distribution - ANSand distribution marginal distribution - ANSone variable at a time most common observational study - ANSsurvey notes about box plots - ANScan't tell what the sample size is -bigger boxes don't mean more data, mean more variability -boxplots can be horizontal or vertical -you can't see a mean on a boxplot -there is always 25% of the data in each section of a boxplot -you are interested in how concentrated the data are within each section

observational study - ANS-observes individuals -measures variables and makes conclusions, comparisons -does not attempt to influence the responses -most common observational study: survey probability of an event (characteristic) - ANSP(A) properties of correlation (important) - ANS-2 quantitative variables ONLY -linear relationships ONLY -has no units -switching X and Y doesn't change r -r is affected by outliers and skewness properties of standard deviation - ANSsame units as original data never negative can equal zero is affected by outliers and skewness random sample characteristics - ANS1. each group of the same size has the same chance of being selected as the sample

2. allows no favoritism by the sampler or the sampled relative frequency - ANS% in each category, shown through table, pie char, bar graph

residuals - ANS-observed y-predicted y -negative residual: point is below the line -positive residual: point is above the line response rate - ANSnumber of respondents/sample size sample space - ANSset of all possible outcomes simple random sample - ANSexamine the entire population as it exists -Gallup poll, random digit calling Simpson's paradox - ANSresults of two variables may reverse if a third variable is added skewed left - ANSmedian is great than mean, more data on the right side of the histogram skewed left box plot - ANSthe median will be towards the right of the box skewed right - ANSmean is greater than median, more data on the left side of the histogram skewed right box plot - ANSthe median will be towards the left of the box

SSE - ANSsum of the squares for error standard deviation - ANSused to measure the concentration of the data around the mean, DO NOT CALCULATE BY HAND statistical significance - ANSif differences are big enough, we say that is due to the treatment and not just chance stratified random sample - ANScompare subgroups of the population equally -divide population into subgroups, choose a simple random sample from each subgroup the difference between an observational study and an intervention - ANSthe difference between an observational study and an experiment three things that can affect the graph - ANS1. starting point

2. number of bars
3. scale of graph to describe a graph, we use three characteristics: - ANS1. shape
4. center
5. variability treatment groups - ANSgroup getting real treatments two challenges of getting good survey results - ANS1. selecting a good sample

2. collect good data variability - ANSstandard deviation, quartiles variability: concentration around the center - ANS-more variability will have data that is more spread away from the center -less variability has more concentrated data around the center want to find the line with the ________ SSE, from all the potential lines that go through the data - ANSsmallest what is a group of individuals who you want to study? - ANSsample what is bias? - ANSsystematic favoritism, happening a lot in one direction or the other what is the impact of bias - ANSloss of credibility when to interpret the y-intercept? - ANS1. must have data in the area
3. number must make sense (not negative, for example)