STRAIGHTER LINE INTRODUCTION TO STATISTICS EXAM QUESTIONS AND ANSWERS

STRAIGHTER LINE INTRODUCTION TO STATISTICS EXAM QUESTIONS AND ANSWERS "Lurking Variable - Correct Answer a variable that is not among the explanatory or response variables in a study, but could substantially affect your interpretation of the relationship among those variables" "Simpson's paradox - Correct Answer When a lurking variable causes you to rethink the direction of an association" "Probability distribution - Correct Answer a list of a variable's possible values and their corresponding probabilities" "Categorical variable - Correct Answer places individuals into one of several groups Two types: nominal and ordinal" "Quantitative Variable - Correct Answer represents a measurement or a count Two types: Interval and ratio" "Nominal Variable - Correct Answer categorical variables where there is no natural order among the categories" "Ordinal variable - Correct Answer categorical variables where there is natural order among the categories" "Interval Variable - Correct Answer a measurement or count for which it makes sense to talk about the difference between values, but it does not make sense to talk about the ratio between values; 0 does not represent the absence of quanitity" "Ratio Variable - Correct Answer quantitative variables for which it makes sense to talk about the difference between values AND the ratio between values; 0 represents the absence of quantity" "What type of variable?: eye color - Correct Answer nominal" "What type of variable?: socioeconomic status with categories low, med, high - Correct Answer Ordinal" "Conditional probability P(B | A) - Correct Answer the conditional probability of event B occurring given that event A has occurred P(B | A) = P(A and B) / P(A)." "Standard deviation of all sample proportions - Correct Answer √{[p(1−p)]/n}." "Standard deviation of all sample means - Correct Answer σ/(√n)" "What type of variable?: Temperature - Correct Answer Interval" "What type of variable?: Income - Correct Answer Ratio" "Visual display and numerical summary for a single categorical variable - Correct Answer pie chart or bar chart and category percentages" "Visual display and numerical summary for a single quantitative variable - Correct Answer histogram or stemplot and descriptive statistics" "Visual display and numerical summary for C->C - Correct Answer Two way table and conditional percentages" "Visual display and numerical summary for C->Q - Correct Answer Side by side box plots and descriptive statistics" "Visual display and numerical summary for Q->Q - Correct Answer Scatterplot and correlation coefficient (r)" "Standard Deviation Rule - Correct Answer Approximately 68% of observations fall within 1 sd of the mean, 95% within 2 sd, 99.7% (or virtually all) within 3 sds" "Interquartile Range (IQR) - Correct Answer Middle 50% of the data IQR= Q3-Q1" "Finding an outlier using IQR - Correct Answer An observation is considered a suspected outlier if it is: less than Q1 - 1.5(IQR), or more than Q3 + 1.5(IQR)." "Interpreting scatterplots: 1. positive relationship displays as 2. negative relationship displays as - Correct Answer 1. upward slope 2. downward slope" "Interpreting Scatterplots: How to tell if a linear relationship is strong or weak - Correct Answer closer to -1 is a strong negative linear relationship closer to +1 is a strong positive linear relationship close to 0 is a weak linear relationship" "Interpreting Scatterplots: Linear regression - Correct Answer Finding the line that best fits the pattern of the linear relationship (the line that describes how the response variable linearly depends on the explanatory variable" "Interpreting Scatterplots: Least Squares Regression Line - Correct Answer Has the smallest sum of squared vertical deviations of the data points from the line." "Interpreting Scatterplots: Extrapolation - Correct Answer Prediction for ranges of the explanatory variable that are not in the data; is not reliable and should be avoided" "Association (does/does not) imply causation. - Correct Answer Does not" "Probability sampling plan - Correct Answer any sampling plan that relies on random selection (avoids bias)." "Simple Random Sampling - Correct Answer Every member of the population has an equal probability of being selected for the sample" "Cluster Sampling - Correct Answer Used when the population is naturally divided into groups. Take a random sample of clusters and use all individuals within those clusters as the sample." "Stratified sampling - Correct Answer Used when the population is naturally divided into sub-populations called stratum. Choose a simple random sample from each stratum and use these together as the sample." "Multistage sampling - Correct Answer a probability sampling technique involving at least two stages: a random sample of clusters followed by a random sample of people within the selected clusters" "Observational study - Correct Answer values of the variable or variables of interest are recorded as they naturally occur; no interference" "Sample surveys - Correct Answer a particular type of observational study in which individuals report variables' values themselves, frequently by giving their opinions." "Experiment - Correct Answer researchers "take control" of the values of the explanatory variable because they want to see how changes in the value of the explanatory variable affect the response variable" “Four steps in the process of statistics - Correct Answer 1. Producing Data 2. Exploratory Data Analysis 3. Probability 4. Inference" "The Complement Rule - Correct Answer P(not A) = 1 - P(A) useful for finding events of the type "at least one of..."" "General Addition Rule - Correct Answer P(A or B) = P(A) + P(B) - P(A and B) used to find events of the type events of the type "A or B"" "General Multiplication Rule - Correct Answer P(A and B) = P(A) * P(B | A) Used for events of the type "A and B" or when A and B are independent: P(A and B) = P(A) * P(B)" "1. Discrete random variable 2. Continuous random variable - Correct Answer 1. things we count 2. things we measure" "Center of a random variable distribution is measured by its - Correct Answer mean" "Spread of a random variable distribution is measured by its - Correct Answer variance or standard deviation" "Rules for the linear transformation of one random variable - Correct Answer μ(a+b)X=a+b μX σ^2a+bX=b^2σ^2X" "1. Usual 2. Unusual - Correct Answer 1. Within two standards deviations of the mean 2. More than two standard deviations above or below the mean" "Binomial Experiment - Correct Answer 1. a fixed number of trials (notation: n trials) 2. each trial must be independent of the others 3. each trial has two possible outcomes, called "success" (the outcome of interest) and "failure" 4. there is a constant probability (p) of success for each trial, the complement of which is the probability (1 - p) of failure" "Binomials The Number of outcomes with x successes out of n trials (formula) - Correct Answer [n!]/[x!*(n-x)!]" "Mean of a binomial - Correct Answer μX=np" "z-score for normal random variable - Correct Answer z=(x−μ)/σ" "1. Parameter 2. Statistic - Correct Answer 1. Number that describes the population 2. Number that is computed from the sample" "In Point Estimation, Estimate the population proportion using the ________, and the population mean using the _______. - Correct Answer Sample proportion, sample mean" "General formula of confidence intervals - Correct Answer point estimation +- margin of error" "Confidence intervals for the population mean - Correct Answer Xhat ± z∗⋅[σ/(√n)]" "Various values of z for different levels of confidence - Correct Answer 90%= 1.645 times the standard deviation of sample mean · 95%= 2 (or precisely 1.96) times the standard deviation of sample mean · 99%= 2.576 times the standard deviation of sample mean" "Methods for checking for independence of two variables - Correct Answer If the two variables are independent: · P(A|B)= P(A) · P(B|A)=P(B) · P(B|A)=P(B| not A) · P(A and B)= P(A) * P(B)" "3 Types of inference in this course - Correct Answer Point estimation Interval Estimation Hypothesis Testing"