WGU C207 - Flashcards - Modules 1 – 6 Exam Questions and Verified Answers

Frame the Problem, Solving the Problem and Communicating Results are part of which decision-making model? - Davenport-Kim three-stage model In which stage of the Davenport-Kim model is problem recognition? - Framing the problem In which stage of the Davenport-Kim model is data collection? - Solving the problem What is a key reason we study statistics? - To make informed decisions Visually presenting the data assists in which stage of the Davenport-Kim model? - Communicating the results When does research fail to produce reliable results? - Poor research validity What are the two major issues surrounding research standards? - Best practices and ethics In order to be a statistically valid sample, the sample must be: - The appropriate size and random Not selecting a random sample is what type of bias? - Measurement Not selecting a right sized sample is what type of bias? - Measurement Research best practices eliminate... - Bias Outliers create this type of error - Out-of Range Unpredictable error - Random Error - No correlation Error may occur from missing data. (Example: Space not filled in) - Omission Error - Distorted results This error repeats itself - Systematic Error - Skewed results Observation points that are distant from other observations. - Outliers Note: Can be included or excluded in analysis (causes skewness) Types of Bias: Bias that occurs from not selecting a random sample - Measurement bias Types of Bias: Bias introduced because respondents believe it will be beneficial if selected. - Conscious bias (key word: benefit) Consistent and repeatable data - Reliable Resulting from accurate measurements - Valid data If a responder lies on their survey, this creates what type of bias? - Information Sorting your spreadsheet can expose these errors by moving them to the very top or the very bottom of the column - Omission or Out-of-Range An error that will fix itself over time - Random An error that will not fix itself. You must do something - Systematic Cleaning and organizing data - Data Management Are the following variable quantitative or qualitative? Personality type, social class, or communication style - Qualitative A study used when you a conditions can't be controlled - Observational study Observes people going forward in time from the time of their entry into the study. - Cohort Study What are the three elements of an experimental study? - Unit, Treatment, Response Accurately measures what it is intended to measure - Valid data ________ an experimental study prevents bias. - Blinding Neither the treatment allocator nor the participant knows in which group the participant is contributing. (Who is getting the real drug?) - Double blind study The participants are not told if they are in the treatment group or control group - Blind study Describes characteristics of a dataset. Mean, median, mode, variation, standard deviation, range.... - Descriptive analytics Uses data from t he past to predict the future - Predictive Uses experimental design and optimization to predict a future - Prescriptive If we move to six appointments an hour we can increase revenue 2%. Which form of analytics is this? - Prescriptive - We are taking a specific course of action Based on the last four quarters, we can predict $4,1 million in sales next quarter. Which form of analytics is this? - Predictive: We aren't taking any action The number of appointments per day averaged 7 over the last 6 months. Which form of analytics is this? - Descriptive: We are only describing the past. No future predictions are made. Is Big Data structured, unstructured or both? - Both Where do we store big data - In a big data warehouse Why do marketing teams use big data? - "Datamining" assists in targeting the best customers for new products or reaching existing customers for like products Name the 4 levels of measurement - (NOIR) Nominal, Ordinal, Interval Ratio Continuous data with unique zero point is _______ level of measurement. - Ratio Orders data at equal distance apart is _______ level of measurement. - Interval Identify, Group, or Categorize is _______ level of measurement. - Nominal The colors of cars is which level of measurement? - Nominal The price of the car is which level of measurement? - Ratio Which level of measurement can be multiplied and divided? - Ratio Which level of measurement cannot be analyzed which most statistical test? - Nominal Correlation is not _________ - Causation A good sample of the population being studied will be the right size and ___________ - Random If a sample is not random it creates ____________ - Measurement Bias If a sample is not the right size it creates ___________ - Measurement Bias Measuring the housing market in North Carolina when making an inference about the entire East coast is an example of __________ - Non-representative Sample Lemonade sales increase when it is warmer than 75 degrees. Weather and lemonade are __________ - Correlated. "NOT CAUSE" Pulling names from a hat is a tool to create a ______ sample - Random Asking participants to taste test a yellow candy and a blue candy and select one can create bias. How can we prevent bias? - Blinding You are taking a survey and the question is leading. It seams advantageous to answer a specific way. What type of bias is this? - Conscious KEYWORD: Benefit A question is not leading, but you feel your boss might want you to answer a specific way - Response You feel there is an "expected" response and may not answer honestly (no leading ) pread of the data - Standard Deviation A normally distributed sample spreads from -3 to +3 standard deviations from the mean We should not use this measure of central tendency alone for decisions because it includes outliers - Mean The best measure of central tendency when making decisions - Median We use this measure of central tendency if we want to know what happens the most - Mode (most can also be defined as typical or common) If the mean is 50 and the standard deviation is 5, what is the probability of being between 45 and 55? - 68.2% (of the sample will be within 1 standard deviation of the mean) 50 - 5 = 45 and 50 + 5 + =55 What are the three probabilities of the bell curve? - 68.2% 95.4% 99.7% 68.2% of a sample will be within _______ standard deviation of the mean. - 1 95.4% of a sample will be within ______ standard deviations of the mean. - 2 99.7% of a sample will be within _____ standard deviations of the mean. - 3 The mean is 20 and the standard deviation is 2, what is the probability of being between 14 and 26 - 99.7% (of the sample will be within 3 standard deviations of the mean) 20 + 2 + 2 + 2 = 26 and 20 - 2 - 2 - 2 = 14 _______ can be used to differentiate between two samples with the same mean. - Variation Which measurement can tell us where a single data point is on the bell curve? - z-score. (Tip: Remember z for me. Where are you in the curve of your peers) You want to know how your height compares to all of your family tree. How do you calculate a z score? - (Your height - the mean of the family tree height) divided by the standard deviation of the family tree height (me-mean)/standard deviaiton You are 63" tall and the family tree averages 67" with a standard deviation of 2". What is your z-score? - (63-67)/2 = -2 You are 2 standard deviations shorter than the family tree.