Stat 200 Exam 3
D
In a Stat 200 Survey, students were asked: Do you plan to do an internship while at penn state? Event = yes Variable X N Sample p 95% CI Internship 331 416 0.795673 (0.756927, 0.834419) Using the normal approximation. Which is the correct notation for the highlighted number on the output? A) U: .795673 B) O: 0.795673 C) p = 0.795673 D) P-HAT: 0.795673
A (Statistical Hypotheses: Null and Alternative only include statements about parameters. Parameters are numbers that describe populations)
Statistical Hypotheses (Null Hypothesis and Alternative Hypothesis) include statements about: A) parameters B) statistics C) both A and B are true D) both A and B are false
A
The smaller the p-value, the more support for the statement found in Ha A) True B) False
D
This table summarizes a sample of quantitative data. Min Q1 Median Q3 Max 10 20 30 50 60 When using all of the information found on this table, the sample mean is most likely a value: A) below 10 B) between 10 and 30 C) exactly equal to 30 D) between 30 and 60 E) above 60
B
This table summarizes a sample of quantitative data. Min Q1 Median Q3 Max 10 20 40 50 60 When using all of the information found on this table, the sample mean is most likely a value: A) below 10 B) between 10 and 40 C) exactly equal to 40 D) between 40 and 60 E) above 60
C
This table summarizes amount of time (in hours/day) spent on the computer by 20 Stat 200 students Min Q1 Median Q3 Max 1 3 4 6 10 Approximately what percent of the computer times are at most 4 hours/day? A) 0% B) 25% C) 50% D) 75% E) 100%
B (The null hypothesis is always: Ho: p = a number. Ha: shows the sidedness of the test and how the p-value should be calculated.)
A p-value calculation always matches in sidedness with the statement found in: A) Ho B) Ha
A
A p-value interpretation is always based on the assumption that which hypothesis is true A) Ho B) Ha
D
A recent CNN Poll found that 55% of all American adults believe that marijuana should be legalized based on telephone (both cell and landline) interviews with a random sample of 1,010 national adults, aged 18 and older. How would you calculate the margin of error (M.E.) for this poll? A) M.E.= 1/55 B) M.E.=1/square root of 55 C) M.E.= 1/1010 D) M.E.= 1/square root of 1010
A
A recent Gallup Poll found that 60% of all American adults enjoy saving money more than spending it. The results are based on telephone (both cell and landline) interviews with a random sample of 2,017 national adults, aged 18 and older. Which is untrue about this Gallup Poll? A) the ideal population of interest is: all American Adults who have cell and/or line phones B) when obtaining the sample, replacement was not used C) random variable X: the number of American adults who enjoy saving money more than spending in the sample of 2,017 American adults D) Principle 3 from chapter 1 would best apply in this instance
D
A sample of 100 students was obtained. Each student was asked: What is the distance in miles between your home (hometown) and Penn State. The table below summarizes this variable when considering this sample of 100 students. Distance (in miles) Frequency (Count) (1-100) miles 20 (101-200) miles 8 (201- 300) miles 20 (301-400) miles 4 (401-500) miles 20 (501-600) miles 28 n= 100 students For this variable: which is the range of possible values that the median could assume? A) (1-100) miles B) (101-200) miles C) (201-300) miles D) (301-400) miles E) (401-500) miles F) (501-600) miles
D
A sample of Penn State students were asked two questions: 1. Have you ever missed class because of alcohol? yes no 2. Have you every pulled an all-nighter? yes no The correct statement of the null hypothesis is: the two variables are: A) related in the sample B) related in population C) not related in the sample. D) not related in the population
B
A sampling distribution suggests possible values for ______ A) an individual observation B) a statistic C) a parameter D) a p-value E) confidence interval
A
A stat 200 survey asked two questions: Explanatory variable: Have you ever tried e-cigarettes? yes no Response Variable: Have you ever tried marijuana? yes no The goal is to determine if there is a statistically significant relationship between the two variables: Rows: E_Cig Columns: marijuana_tried No Yes All No 157 115 272 131 141 Yes 35 93 128 61 67 All 192 208 400 Cell Contents: Count Expected count Pearson Chi-Square = 32.178, DF = 1, P-Value = 0.000 Which is untrue? A) we can include a cause and effect statement with our conclusion B) in this instance, we find that the explanatory variable of "having tried e-cigarettes" is important C) the data should be displayed on a two-dimensional bar chart D) on this survey, the most common response was answering "no" for both questions
C
A study asked two questions from people who had heart surgery. 1. Do your religious beliefs give you comfort? yes no 2. Do you regularly participate in social activities? yes no Of those who said "yes" to both questions, 1 in 50 died within 6 months. Of those who said "no" to both questions, 1 in 5 died within 6 months. Which is the correct set-up of the 2X2 table when using the provided information A) After Six Months Total Died Lived Yes to both 1 4 5 No to both 1 49 50 Total 2 53 55 B) After Six Months Total no to both Lived Yes to both 1 1 2 Died 4 49 53 Total 5 50 55 C) After Six Months Total Died Lived No to both 1 4 5 Yes to both 1 49 50 Total 2 53 55 D) After Six Months Total Died Lived No to both 1 5 6 Yes to both 1 50 51 Total 2 55 57
D
A survey asked a group of adults who are employed: During the week, do you get at least seven hours of sleep/night? yes no The workers were also classified as either being a blue-collar or white-collar worker. The data is summarized in the 2x2 table found below. worker yes no Total blue-collar 15 10 25 white-collar 12 13 25 Total 27 23 50 The two variables in this problem are: A) both quantitative where (worker) is the response variable and the (yes/no sleeping answer) is the explanatory variable B) both quantitative where (worker) is the explanatory variable and the (yes/no sleeping answer) is the response variable C) both categorical where (worker) is the response variable and the (yes/no sleeping answer) is the explanatory variable D) both categorical where (worker) is the explanatory variable and the (yes/no sleeping answer) is the response variable
A
About 54% of all American adults are "very happy." The results are based on telephone interviews (both cellphone and landline) with a randomly selected national sample of 1000 adults. The reported margin of error is 5%. Which is the correct interpretation of the margin of error for this poll? With random samples of this size, the difference between the ___ A) the sample percent and the population percent will be within 5%. B) the sample percent and the population percent exceeds 5%. C) the sample percent and the population percent will equal 5%.
D (54% +/- 5% = (49 to 61)% - all values are not above 50% - so statistically can not make a claim about a majority because 50% is a possible for the population percent)
About 54% of all American adults are "very happy." The results are based on telephone interviews (both cellphone and landline) with a randomly selected national sample of 1000 adults. The reported margin of error is 5%. (do in lecture tomorrow) Statistically: In this instance it is appropriate to inferentially conclude, when using the appropriate 95% confidence interval, that a majority of American adults are "very happy." After calculating the 95% confidence interval, the answer is: A) yes, because all values are above 50% B) yes, because all values are not above 50% C) no, because all values are above 50% D) no, because all values are not above 50%
B ((42/92) = .456 or about 46%)
An English study considered two variables: 1. Identify your height: (short) (not short) 2. Have you ever been bullied? yes no bullied not bullied total Short 46 54 100 Not Short 26 74 100 total 72 128 200 Among the short "students: what percent have been bullied? A) 26% B) 46% C) 50% D) 54%
C
An insurance company expects 10% of its policyholders to collect claims of $500 this year and the remaining policyholders to collect nothing this year. X = the amount that the insurance company will pay out this year ($) What is the expected value for the amount of money that the insurance company will pay out this year? Which is correct set-up of this calculation? A) E(X) = $0×(0.10) - $500×(0.90) B) E(X) = (0.90)×(0.10) + $500×($0) C) E(X) = $500×(0.10) + $0×(0.90) D) E(X) = $500×(0.90) + $100×(0.10)
A (Feedback: Correlations usually come from observational studies, so cause and effect statements are not possible)
Are big hospitals bad for you? A positive correlation has been found between: (x: hospital size as measured by number of beds) and (y: median number of days that a patient stays in the hospital) A) there is a third variable Z: type of procedures that are done at the hospital that may explain this relationship B) there clearly is a cause and effect relationship: y is influencing x C) there clearly is a cause and effect relationship: x is influencing y
C
Below are three 2x2 tables, where the contents of each cell includes: the actual counts (the first number) and the expected counts (the second number). Table1 Yes No All F 60 40 100 50 50 M 40 60 100 50 50 All 100 100 200 Table2 Yes No All F 90 10 100 50 50 M 10 90 100 50 50 All l00 100 200 Table3 Yes No All F 70 30 100 50 50 M 30 70 100 50 50 All 100 100 200 Which is true about these tables? A) Table 1 would have the largest p-value and Table 3 have the smallest p-value B) Table 1 would have the smallest p-value and Table 3 have the largest p-value C) Table 1 would have the largest p-value and Table 2 have the smallest p-value D) Table 1 would have the smallest p-value and Table 2 have the largest p-value E) Table 2 would have the largest p-value and Table 3 have the smallest p-value F) Table 2 would have the smallest p-value and Table 3 have the largest p-value
C
Below is a data anlysis of data found in a 2x2 Table yes no Total Group 1 8 (80%) 2 10 Group 2 1 (20%) 4 5 Total 9 6 15 Rows: Worksheet rows Columns: Worksheet columns yes no All 1 8 2 10 6 4 2 1 4 5 3 2 All 9 6 15 Cell Contents: Count Expected count Pearson Chi-Square = 5.000, DF = 1, P-Value = 0.025 * NOTE * 3 cells with expected counts less than 5 Which would the appropriate conclusion(s) to report? A) Can claim that descriptively there is a 60% difference in the two row percents and that statistical significance has been found B) Can claim that descriptively there is a 60% difference in the two row percents and that statistical significance has not been found. C) Can only claim that descriptively there is a 60% difference in the two row percents. D) Can only claim that statistical significance has been found.
D
Below is a distribution in percents of blood types found in the United States Blood Types A B AB O Percents 42% 11% 3% 44% Katie has type B blood. She can safely receive transfusions from people with blood type O or blood type B. If Katie were in an accident and needed a blood transfusion, what percent of the people in the United States could donate blood to her? A) 11% B) 33% C) 44% D) 55% E) 100%
B
Below is a probability distribution for: X = the number of credit cards that Stat 200 students have # of jobs 0 1 2 3 4 Probability 0.30 0 .40 0.15 0.10 0.05 Which is untrue about this distribution? A) P(X = 0) = 0.30 B) the formula used to calculate the standard deviation for this distribution is: the square root of np(1-p) C) the random variable is a discrete (non-binomial) D) the sum of all the probabilities in the table = 1.0
C
Below is a probability distribution function for: X = the number of meals eaten yesterday by individuals in a large population. X 1 2 3 4 probability of X 0.10 0.30 0.50 0.10 What is the probability that a person in this population has eaten fewer than 3 meals yesterday? A) 0.10 B) 0.30 C) 0.40 D) 0.50 E) 0.90
A (Feedback: one group - two levels for the response variable)
Binomial data is summarized in which type of table? A) (1 x 2) table B) (2 x 2) table C) (4 x 4) table D) unable to determine
C B A
Concept: Match the multipliers with the corresponding level of confidence when considering a confidence interval for the population proportion. A. 1.645 B. 1.96 (2.0) C. 2.33 98% confidence 95% confidence 90% confidence
D
Consider 4 different (x, y) pairs found in the provided answers. Which pair, when removed, would lead to the other pairs to having a correlation of 1.0. A) (10, 20) B) (15, 25) C) (20, 30) D) (30, 35)
D
Consider a sample where n = 4: 20 30 50 100 sample mean = 50 Which statement is untrue about the provided information? A) if 10 were added to each observation in the sample, the standard deviation would be the same as found with the original sample B) the observation of 100 contributes the most to the final value of the standard deviation C) the value of the median is 40 D) the observation of 20 contributes the least to the final value of the standard deviation
C
Consider data from 9 homes from Orange County, California. Two variables were of interest are: House Size: Square Feet Asking price ($1000's) Below are some results from the regression analysis when using this data. The regression equation is Price($1000s) = - 1.1 + 0.26 Square_Ft S = 164.652 R-Sq = 62.2% Which is the correct interpretation of the squared correlation? A) the strength and direction of the linear relationship between the asking price and the size of the home is 0.622 B) the strength and direction of the linear relationship between the asking price and the size of the home is 0.26 C) 62.2% of the variation in the asking prices can be explained by the size of the home D) 62.2% of the variation in the house size can be explained by the asking price
A
Consider data from a sample of college students. The question is how well does the number of beers that a student consumes explain their blood alcohol concentration (BAC)? BAC's were measured thirty minutes after consumption by a police officer. Below are the results from the regression analysis when using this data.. The regression equation is BAC = - 0.01270 + 0.01796 Beers Which is true? A) both variables are quantitative where: number of beers consumed is the explanatory variable and BAC is the response variable B) both variables are quantitative where: number of beers consumed is the response variable and BAC is the explanatory variable C) both variables are categorical where: number of beers consumed is the explanatory variable and BAC is the response variable D) both variables are categorical where: number of beers consumed is the response variable and BAC is the explanatory variable
s:.45 o:.55 u:3.1 x-hat:3.2
Consider the variable X: GPA for a Stat 200 student For the population of all Stat 200 students, the mean is 3.1 and the standard deviation is 0.55. When a sample of 20 students is taken from the population, the mean is 3.2 and the standard deviation is 0.45. Match the statistical symbol with the number. A. x-hat B. u C. s D. o 0.45 0.55 3.1 3.2
B
Consider the variable X: the life of a battery for a cell phone in hours. Which is untrue? The variable: A) is an example of quantitative data B) is a discrete random variable C) could be displayed on a histogram D) could be a response variable
C
Consider two Survey Questions: 1. Are you on twitter? yes no 2. Do you worry about identity theft? yes no A chi-square test was done and below are the results. Pearson Chi-Square = 11.726, DF = 1, P-Value = 0.001 Which is the correct inferential conclusion to report? When considering the two variables, there is: A) insufficient information to conclude that there is a statistically significant relationship in the population B) insufficient information to conclude that there is a statistically significant relationship in the sample C) sufficient information to conclude that there is a statistically significant relationship in the population D) sufficient information to conclude that there is a statistically significant relationship in the sample
A
Consider two Survey Questions: 1. What is your sex? female male 2. Do you like to take a "selfie'"? no yes Below is the Minitab Output which summarizes data from these two survey questions Rows: Sex Columns: Selfie no yes All Female 47 48 95 59.53 35.47 2.639 4.429 Male 47 8 55 34.47 20.53 4.558 7.650 All 94 56 150 Cell Contents: Count Expected count Contribution to Chi-square Pearson Chi-Square = 19.275, DF = 1, P-Value = 0.000 How many males in the sample actually said that they like to take a "selfie"? A) 8 B) 21 C) 35 D) 47 E) 48
D
Consider two Survey Questions: 1. Who is paying for your Penn State education? parents other 2. Was Penn State your first choice? yes no Below is the Minitab Output for this data. Rows: Who_Pays Columns: PSU_First Yes No All Parent 170 115 285 179 106 0.4971 0.8450 Other 85 35 120 76 44 1.1806 2.0069 All 255 150 405 Cell Contents: Count Expected count Contribution to Chi-square Pearson Chi-Square = 4.530, DF = 1, P-Value = 0.033 Which is untrue? A) for the cell: (parent and yes), the correct calculation of the expected count is:(285)x(255)/(405) B) one would expect 76 students to say: (other and yes) if in fact there is no relationship between the two variables D) P(X^2=4.53)= 0.033
C
Consider two Survey Questions: 1. Who is paying for your Penn State education? parents other 2. Was Penn State your first choice? yes no Below is the Minitab Output for this data. Rows: Who_Pays Columns: PSU_First Yes No All Parent 170 115 285 179 106 0.4971 0.8450 Other 85 35 120 76 44 1.1806 2.0069 All 255 150 405 Cell Contents: Count Expected count Contribution to Chi-square Which statement is untrue? A) the overall sample size for this study is 405 students B) cell: (other and no) contributes the most to the value of the chi-square test statistic C) in each cell, the difference between the actual count and the expected count is 10 D) for those who said "parents are paying for their education,": there were more students who answered "yes" than "no"
A (Always compare against the position of no relationship (null hypothesis). This is not the same thing as making a decision about statistical significance)
Consider two Survey Questions: 1. Who is paying for your Penn State education? parents other 2. Was Penn State your first choice? yes no Included are the results from the chi-square analysis. Pearson Chi-Square = 4.530, DF = 1, P-Value = 0.033 The likelihood of obtaining our chi-square statistic of 4.53, or any value_____ A) larger, when assuming that there is no relationship between the two variables in the population, is 0.033. B) larger, when assuming that there is a relationship between the two variables in the population, is 0.033. C) smaller, when assuming that there is no relationship between the two variables in the population, is 0.033. D) smaller, when assuming that there is a relationship between the two variables in the population, is 0.033.
A
Consider two questions from a Stat 200 survey: What is your sex? female male How do you prefer to exercise? (with company) (alone) with company alone Total female 60 40 100 male 30 70 100 Total 100 100 200 Which is untrue? A) women are 100% more likely to prefer to exercising with company when compared to the males B) the odd for males when considering (exercising with company) to (exercising alone) is 7 to 3 C) the difference in the two row percents is 30% D) females are two times as likely to prefer exercising with company as found with the males
C B A
Determine which graph is appropriate for the defined variables. Each graph should only be used once. Select best choice. A. Bar Graph B. Histogram C. Side-by-Side boxplots the number of years that current faculty in the statistics department have been employed at Penn State (amount of debt after graduating from Penn State and (whether or not the student is a PA resident) organization of management in a company: (low, middle, top)
C B A E D
Determine which graph is appropriate for the variables found below. Use each qraph only once. A. side-side boxplots B. scatterplot C. histogram D. bar graph E. two-dimensional bar graph the daily high temperature for every day in the month of February (number of items in a grocery cart) and (amount of time needed to self-checkout at the grocery store) (number of hours of exercise/week) and (whether or not the student has a PSU fitness pass) (whether or not a person has at least one credit card) and (preference for purchase: cash or plastic) feelings about height: (too short) (just right) (too tall)
A (Feedback: It is quoting a rate of change for two different quantitative variables)
From a Harvard Study: For every $1 spent on employee wellness programs, an average of $3 less is spent on health care costs. Which statistical quantity is being reported? A) sample slope B) correlation C) y-intercept D) relative risk E) squared correlation
D (Statistical hypotheses only include statements about population parameters, not sample statistics - word "decreasing" suggests one-sided test on lower tail)
Historically, it has been found that about 70% of PSU students are "in-state" students. However, more recent data has suggested that this percent will decrease. Which is the correct set-up of the hypotheses? A) Ho: p-hat=.7 Ha: p<.7 B) Ho: p-hat=.7 Ha: p-hat<.7 C) Ho: p=.7 Ha: p-hat<.7 D) Ho: p=.7 Ha: p<.7
B (Feedback: Proportions come from categorical data (based on a yes or no) with an underlying binomial distribution)
Hypotheses that include statements about population proportions are used with which type of data? A) quantitative B) categorical
C
In a Stat 200 Survey, students were asked: Do you plan to do an internship while at penn state? Event = yes Variable X N Sample p 95% CI Internship 331 416 0.795673 (0.756927, 0.834419) Using the normal approximation. Statistically: can we inferentially conclude that a majority of Stat 200 students plan to do an internship whilea at Penn State? When looking a the 95% confidence interval: A) no, because all values in the interval are > 0.50 B) no, because all values in the interval are not > 0.50 C) yes, because all values in the interval are > 0.50 D) yes, because all values in the interval are not > 0.50 Feedback: CI is giving possible values for an unknown population parameter
C (Feedback: CI is giving possible values for an unknown population parameter)
In a Stat 200 Survey, students were asked: Do you plan to do an internship while at penn state? Event = yes Variable X N Sample p 95% CI Internship 331 416 0.795673 (0.756927, 0.834419) Using the normal approximation. Which would be the correct interpretation of the 95% confidence interval that is found on the output? We are 95% confident that the: A) the population mean is between 0.76 to 0.83 B) the sample mean is between 0.76 to 0.83 C) the population proportion is between 0.76 to 0.83 D) the sample proportion is between 0.76 to 0.83
C (Feedback: Sample estimate ± (Margin of error) Sample estimate ± (Multiplier × Standard error) Margin of error = (Multiplier)(Standard Error))
In a poll of n = 300 randomly selected students, 80% said "yes". Which choice correctly shows the calculation of the "normal approximate" margin of error for a 95% confidence interval that estimates the population proportion who said "yes"? A) .8 +- 2 x the square root of .8(1-.8)/300 B) 2 x the square root of .8-.8/240 C) 2 x the square root of .8(1-.8)/300 D) 1/800
E
In the population of all Stat 200 students (around 1800 students for spring semester), the eye color has been determined for each student. Using Minitab, a random sample of 10 Stat 200 students was obtained. From each selected student, it was determined whether or not the student has brown eyes. The outcome of interest is having brown eyes. Let X = number of Stat 200 students needed until you first find a student who has brown eyes in the sample Which binomial condition is not met in this instance? A) n is fixed B) a success is adequately defined C) independence is met D) p will remain essentially constant E) the random variable, as defined by itself, is a binomial
A B C D
Match Statistical Formula or Notation with the correct label A. Population Proportion B. Sample Proportion C. Standard Deviation for Sample Proportion D. Standard Error for Sample Proportion (estimated standard deviation for the sample proportion) Square root p-hat(1-p-hat)/n square root p(1-p)/n p p-hat
E B A C D
Match the graph with the type of data A. bar graph B. two-dimensional bar graph C. histogram D. side-by-side boxplots E. scatterplot both variables are quantitative both variables are categorical and displayed in a (2x2) contingency table one categorical response variable one quantitative response variable a quantitative response variable and a categorical explanatory variable (to form the boxes)
D C A C (Feedback: Statistically: If the confidence interval contains includes 0.5 ( or 0.50) as a possible value, you can not claim that there is a majority and you can not claim that there is a minority)
Match the inferential "statistical" conclusion with the appropriate confidence interval for the population proportion. A. Can claim a majority has been found B. Can claim both a majority and a minority has been found C. Can not claim either a majority or a minority has been found D Can claim a minority has been found 95% C.I. for p: (0.36 to 0.48) 95% C.I. for p: (0.44 to 0.62) 95% C.I. for p: (0.52 to 0.66) 95% C.I. for p (0.40 to 0.50)
D A B C
Match the name with the corresponding statistic. Use each answer only once. A. individual risk B. odds C. relative risk D. increased risk People who have a strong sweet tooth are 20% more likely to develop metabolic syndrome than those who do not have a strong sweet tooth. One in four cats and dogs are declared to be overweight For people who pay taxes: they believe Obamacare will make things (not better) to (better), with regard to healthcare, by 80% to 20% People who don't eat chocolate are 1.4 times as likely to have heart disease when compared to those who regularly eat chocolate."
A A C (Only the p-value is affected by the sidedness of the test - and it is doubled)
Match the quantity used in hypothesis tests with the change that will take when going from a one-sided to a two-sided test with a given sample. Cover in next lecture. A. stays the same B. becomes larger C. becomes smaller sample statistic test statistic p-value
B A C D
Match the value for the r2 with the corresponding ANOVA table. Use each answer only once. A. r2 > 50% B. r2 < 50% C. r2 = 50% D. r2 = 100% ANOVA Table SSR 300 SSE 700 SSTO 1000 ANOVA Table SSR 30 SSE 20 SSTO 50 ANOVA Table SSR 300 SSE 300 SSTO 600 ANOVA Table SSR 500 SSE 0 SSTO 500
C B A
Match the variable with its name. Use each answer only once. A. categorical - ordinal B. categorical - not ordinal C. quantitative a person's cholesterol level (in mg/dl) your nine digit student number your identification when purchasing a movie ticket: (child) (adult) (senior citizen)
E
On a recent survey, Stat 200 students were asked: How low must the temperature go (in degrees Fahrenheit) for you to stop wearing shorts when you are out and about, such as going to class. This data takes on a normal shape where the mean is 55 degrees and the standard deviation is 10 degrees. About 95% of the these lowest temperatures for wearing shorts will fall within what boundaries? Identify the correct calculation of these boundaries. A) 55 ± 1 B) 55 ± 2 C) 55 ± 3 D) 55 ± 1×(10) E) 55 ± 2×(10) F) 55 ± 3×(10)
A
Penn state has a salad bar at the HUB that is priced base on weight with salads costing 55 cents for an ounce. Students fill a container that weighs 10 ounces when empty. x = weight of filled container (in ounces) y = price charged for salad (in dollars) The regression equation is: y= -2.50+.55x Which is the correct interpretation of the sample slope? On the average: A) for every additional ounce of salad, the price goes up by 55 cents B) for every additional ounce of salad, the price goes down by 55 cents C) for each additional cent spent, the salad size increases in by 10 ounces D) for each additional cent spent, the salad size decreases in by 10 ounces
B
People whose blood type is A, B or AB have an increased risk of heart disease according to a new study. This study included a group of 50,045 people who were placed into one of two groups: those with blood type 0 and those with non-0 blood type. The study participants were followed for 6 years where each was classified as either having or not having a heart attack in this six year period. Which is untrue about this study? A) this data could be summarized on a bar chart B) this is a randomized experiment C) the explanatory variable is blood type D) it would be helpful to have a baseline risk for heart disease in the general population when examining the results
C
Scores on an achievement test had an average of 80 points and a standard deviation of 10 points. Devon's score was 90 points on this achievement test. What would be the correct interpretation of the Z-score for Devon's score: Devon scored: A) two standard deviations below the mean for the test B) one standard deviation below the mean for the test C) one standard deviation above the mean for the test D) two standard deviations above the mean for the test
D
Study Title: Why Antioxidants Don't Belong in Your Workout. A study included fifty-four young athletes who were randomly allocated to daily receive either: (1000 mg of vitamin C and 235 mg of vitamin E) or a (placebo). After 11 weeks, the athletes taking the supplements had lower concentrations of certain enzymes (in units/ml) that spur an increase in muscle mitochondria when compared to the placebo group. Which is untrue about this study? A) the data could be displayed on side-by-side boxplots B) a cause and effect statement can be included with the conclusion C) this is an example of a comparative study D) the explanatory variable is quantitative
C
Suppose the population parameter (p) represents the proportion that select the number "7": when given the option to randomly select numbers from 1 to 10. In a hypothesis test: the null states the people do no better than random guessing when selecting the number "7" while the alternative suggests that people are more likely to select the number '7", when considering numbers from 1 to 10. Which is the correct statement of the null hypothesis (Ho) and alternative hypotheses (Ha) in terms of the population proportion (p) who select the number "7"? A) Ho: p = 1/2 Ha: p > 1/2 B) Ho: p = 1/7 Ha: p > 1/7 C) Ho: p = 1/10 Ha: p > 1/10 D) Ho: p = 7 Ha: p > 7 E) Ho: p = 70% Ha: p > 70%
B
The Brann family is financially planning to have children. Their financial advisor provides them with the following probability distribution function (pdf) based on families very similar to the Brann family. X = the number of children the Brann family might have number of children 0 1 2 3 probability 0.05 0.60 0.30 0.05 For this pdf, E(X) = 1.35 children. Which is the correct interpretation of this expected value? The average number of children: A) for the next generation of the Brann family is 1.35 children B) per family over many families similar to the Brann family is 1.35 children C) for siblings of the Brann family is 1.35 children D) for the Brann family is 1.35 children
D
The ages (in years) for participants on a reality tv show are summarized below Descriptive Statistics: ages Variable N Mean StDev Minimum Q1 Median Q3 Maximum ages 13 45.0 18.0 16.0 30.0 40.0 50.0 76.0 In this instance, which is the correct interpretation of the resistant measure of spread? The variation in the _________ A) outer 50% of the data spans 18 years B) outer 50% of the data spans 20 years C) middle 50% of the data spans 18 years D) middle 50% of the data spans 20 years
D (remember age is continuous random variable)
The ages (in years) for participants on a reality tv show is summarized below Descriptive Statistics: ages Variable N=13 Mean=45 StDev=18.1 Minimum=17 Q1=30 Median=42 Q3=52 Maximum=76 When considering the summary of this sample, which is untrue? A) the value of the resistant measure of spread is 22 years B) the age of the oldest contestant is 76 years C) the value of the 75th percentile is 52.0 years D) the suggested shape for the data is left/negative skewed
B
The amount of salt consumed daily (in milligrams) is summarized for a sample of 200 Americans Descriptive Statistics: Amount of Salt Variable N Mean SE Mean StDev Minimum Q1 Median Q3 Maximum Amount of Salt 20 3600 105 470 2900 3200 3600 4000 4500 When considering the summary of this sample, which is untrue? A) the variable is continuous B) the value of the resistant measure of spread is 470 milligrams C) the value of the 25th percentile is 3200 milligrams D) the suggested shape for the data is bell-shaped
A (Feedback: Either using X or phat - both are statistics - sampling distributions tell you possible values for a statistic)
The binomial distribution is an example of a sampling distribution. A) True B) False
A
The goal of a confidence interval is to suggest possible values for an unknown _____ A) parameter B) p-value C) z-score D) statistic E) sampling distribution
D
The goal of the Z test statistic is to standardize the difference (in the order found in the formula) between the: A) (the parameter and the sample estimate) B) (the standard deviation and the standard error) C) (the p-value and the alpha value) D) (the sample estimate and the parameter)
B
Two variables were obtained from the Stat 200 data survey. The two variables include: What is your actual height (in inches) What is your ideal height (in inches)? Below is Minitab output based on this data. The regression equation is Ideal_Ht = 9.5 + 0.88 Actual_Ht S = 2.72 R-Sq = _____ Analysis of Variance Source DF SS MS F P Regression 1 6421.59 6421.59 865.10 0.000 Error 395 2932.06 7.42 Total 396 9353.64 When using the provided output, along with the other information, which is untrue? A) the squared correlation would be > 50% B) the method of least squares minimized the value of 6421.59 on the output C) The number 9353.64 quantifies the amount of variation in ideal heights
B ( two-sided test because says "different" - sample data does not appear in hypothesis. p-hat does not appear in hypotheses)
USAToday/Gallup poll finds that nationally 36% of people find that a good education matters the most for getting ahead in life. Data suggests a different value for Stat 200 students? From a sample of 1000 Stat 200 students, 270 said the a good education was most important. Does the data suggest that the population porportion is different from 0.36 for Stat 200 students?. Which are the correct hypotheses? A) Ho: p = 0.36 Ha: p < 0.36 B) Ho: p = 0.36 Ha: p ≠ 0.36 C) Ho: p = 0.27 Ha: p < 0.27 D) Ho: p = 0.27 Ha: p ≠ 0.27
B
USAToday/Gallup poll finds that nationally 36% of people find that a good education matters the most for getting ahead in life. Data suggests a different value for Stat 200 students? From a sample of 1000 Stat 200 students, 270 said the a good education was most important. Does the data suggest that the population proportion is different from 0.36 for Stat 200 students?. The Z test statistic is 5.93. Which is the correct interpretation of the Z statistic. The: A) sample proportion is 5.93 standard deviations above the null population proportion of 0.36 B) sample proportion is 5.93 standard deviations below the null population proportion of 0.36 C) sample mean is 5.93 standard deviations above the null population mean of 0.36 D) sample mean is 5.93 standard deviations below the null population mean of 0.36 E) population proportion is 5.93 standard deviations above the sample proportion of 0.36
A
What is the center value for each confidence interval? A) statistic (or sample estimate) B) multiplier C) parameter D) margin of error E) standard error
B A
When considering a sample that is obtained from a binomial distribution, p-hat is ___ and x is ___ A. number of successes B. proportion of successeS
F
When the Chi-Square statistic = 0: which is untrue? A) relative risk = 1.0 B) two individual row percents (risks) are the same C) p-value = 1.0 D) with each cell: actual count = expected count E) increased risk = 0% F) the odds are different for the two groups
C
When the p-value > 0.05, which is untrue? (Note: only one correct answer) A) can not reject Ho in favor of Ha B) can not claim statement found in Ha is true C) can claim the statement in Ho is true D) can not rule out random chance as a plausible explanation E) can not consider the result to be a rare event.
C
When the p-value ≤ 0.05, which is untrue? (Only one correct answer) A) Can reject Ho in favor of Ha B) Can claim the statement found in Ha is true C) Can "accept" Ho D) can rule out random chance as a plausible explanation E) the result can be considered to be a rare event
B
Which correlation shows the weakest linear relationship? A) -0.88 B) -0.05 C) 0.27 D) 0.41 E) 0.73
B
Which distribution is used to obtain the p-value for a hypothesis test about the population proportion when using the "normal" approximate method? A) chi-square distribution B) Z distribution
D
Which factors the final value of the Z statistic? The value of: A) n B) the sample proportion C) the population proportion found in Ho D) answers A, B and C are all true
C
Which is not a correct generic formula for any confidence interval? A) (Sample Estimate) +/- (Multiplier)(Standard Error) B) (Sample Estimate) +/- (Margin of Error) C) (Sample Estimate) +/- (Standard Error)
B
Which is the correct generic formula for any test statistic? A) t.s. = (null value - sample statistic)/ (standard error) B) t.s. = (sample statistic - null value)/ (standard error) C) t.s. = (null value - sample statistic)/ (sample standard deviation) D) t.s.= (sample statistic - null value)/ (sample standard deviation)
A (Always compare against the position of no relationship (null hypothesis). This is not the same thing as making a decision about statistical significance)
Which is the generic language for a p-value interpretation. The likelihood of obtaining the test statistic or any value_____ A) more extreme, in the direction found with the alternative hypothesis, if in fact the null hypothesis is true. B) more extreme, in the the direction found with the alternative hypothesis, in fact the alternative hypothesis is true. C) less extreme, in the direction found with the alternative hypothesis, if in fact the null hypothesis is true. D) less extreme, in the direction found with the alternative hypothesis, if in fact the alternative hypothesis is true.
A
Which is true about a statistical interpretation of a calculated number? It is a ___ A) one-sentence statement about what the number represents B) comparison of the number to .05 so that it can be determined whether or not statistical significance has been found.
E (Feedback: A sampling distribution suggests possible for the sample statistic. A population parameter can only assume one value. It is not affected by values for the statistic.)
Which is untrue about a parameter? A parameter: A) is a number that describes a characteristic of the population B) can only assume one value once the population is defined C) has a value that may or may not be known once the population is defined. D) is estimated when a confidence interval calculated E) has a corresponding sampling distribution
A
Which is untrue about a statistic? A statistic ________ A) can only assume one value once the population has been defined B) does vary in value from sample to sample C) has a corresponding sampling distribution D) is a number that describes a characteristic of the sample E) is also called a sample estimate
B (Never use data to set-up Ho and Ha)
Which is untrue about statistical hypotheses? A) researcher hopes the data supports the statement found in Ha B) should "data snoop" prior to setting up Ho & Ha C) up until now "accepted value" is stated in Ho D) research question is always stated in Ha
C (Standard deviation requires a normal and can only be interpreted when considering the sample mean)
Which is untrue about the standard deviation? The standard deviation: _____ A) is a sensitive measure of spread B) has the same units of measurement as found with the mean C) is an accurate measure of spread no matter what is the shape of the data. D) can only be fully interpreted when the empirical rule is applied E) is roughly defined as the average distance of an observed value from the mean
B
Which is untrue about the standard deviation? The standard deviation: _____ A) is a sensitive measure of spread B) is roughly defined as the average distance of an observed value from the median C) is an accurate measure of spread only when the data is normal in shape. D) has the same units of measurement as found with the mean E) can only be fully interpreted when the empirical rule is applied
E
Which is untrue is about a correlation? A correlation, when calculated, _____ A) does not needs to designate one variable as the explanatory variable and one variable as the response variable B) can either increase or decrease in strength when an outlier is present C) should only be compared to correlations that come from the same sample size D) is stripped of the original units of measurement found with the two variables E) is a resistant statistic
A
Which is untrue when considering an outlier in sample of quantitative data where n = 20? When an outlier is present in this sample: A) the standard deviation decreases in value B) the value of the mean is drawn towards the outlier C) the mean and median assume different values D) the IQR is unaffected.
C
Which sample proportion would lead to the smallest p-value where: Ho: p = 0.60 Ha: p > 0.60 & n= 100? A) 0.56 B) 0.62 C) 0.68
A
Which statistical hypothesis takes the assumption that nothing new is going on in the population? A) null hypothesis B) alternative hypothesis
D
Which will change the value of the correlation for a data set when considering y in a sample of (x,y) pairs? A) multiply each y observation by 10 B) add 5 to each y observation C) change the units of measurement for y (i.e. change weight from pounds to kilograms) D) remove the (x,y) pair where y is found to be an extreme outlier
A
Which would not be a way to determine the shape of a sample of quantitative data? A) compare the standard deviation to the IQR B) find position of the median inside the box portion of the boxplot C) compare the mean to the median D) examine the shape of the histogram
B
With the Population Proportion: which is the multiplier for a 68% confidence interval? A) 0 B) 1 C) 2 D) 3
C
With the Population Proportion: which is the multiplier for a 95% confidence interval A) 0 B) 1 C) 2 (or 1.96) D) 3
D
With the Population Proportion: which is the multiplier for a 99.7% confidence interval? A) 0 B) 1 C) 2 D) 3
D
his table summarizes the Exam 1 scores (in points) for my Stat 200 students during Fall semester 2014 Min Q1 Median Q3 Max 45 78 84 90 100 Approximately what percent of the exam scores lie between 78 and 100 points? A) 0% B) 25% C) 50% D) 75% E) 100%
A
u and o are examples of paramaters
