DBS final

chi square testing requires which assumption about the shape of the population distribution from which a sample is drawn? 1- no assumptions 2- normally distributed 3- skewed positive for positive values 4- exponential decay 5- distributions must match a t-test distribution

1- no assumptions

what is the shape of a chi-square distribution? 1- skewed 2- normal 3- t-score 4- exponential inverse 5- random

1- skewed

how many sample observations are required to use the goodness of fit test? 1- 10 2- 1 3- 5 4- 15

3- 5 (if less than 5 use the randomization test)

an inspector needs to learn if customers are getting fewer ounces of a toothpaste than the 8 oz stated on the label. after she collects data from a sample of tubes, she is going to conduct a test of hypothesis. she should use: 1- two tailed test 2- one tailed test; alternative to the right 3- one tailed test; alternative to the left 4- either a 1 or 2 tailed test cuz they are equivalent 5- none of the above

3- one tailed test; alternative to the left

what is part of the chi square approach? 1- state hypothesis 2- interpret results 3- analyze data 4- formulate analysis plan 5- all of the above

5- all of the above

age and height are examples of which level of measurement? 1- nominal 2- ordinal 3- qualitative 4- discrete 5- continuous

5- continuous

Which of the following is/are a limitation of the Paired T-test? A. Difference for the matched pairs must follow a normal probability distribution B. The sample of pairs cannot be a random sample from the population C. The data is discontinuous D. All of the above E. None of the above

A. Difference for the matched pairs must follow a normal probability distribution

The Paired T-test has two competing hypotheses, the null and alternative hypothesis. With that being said, what does the null hypothesis assume in comparison to the alternative hypothesis? A. The null hypothesis assumes that the true mean difference between the paired samples is not equal to zero. While the alternative hypothesis assumes that the true mean difference between the paired samples is zero. B. The null hypothesis assumes that the true mean difference between the paired samples is zero. While the alternative hypothesis assumes that the true mean difference between the paired samples is not equal to zero. C. The null hypothesis assumes that the true mean difference between the paired samples is greater than zero. While the alternative hypothesis assumes that the true mean difference between the paired samples is less than zero. D. The null hypothesis assumes that the true mean difference between the paired samples is less than zero. While the alternative hypothesis assumes that the true mean difference between the paired samples is greater than zero. E. None of the above

B. The null hypothesis assumes that the true mean difference between the paired samples is zero. While the alternative hypothesis assumes that the true mean difference between the paired samples is not equal to zero.

what are the types of chi square tests? A- goodness of fit B- independence test C- dependence test D- all of the above E- A and B only

E- A and B only (goodness of fit and independence test)

Which of the following indicates a strong correlation? (Multiple answers) a. .97 b. -.36 c. .25 d. 0 e. -.91

a. .97 e. -.91 (A strong correlation is indicated by the r value approaching either 1 or negative 1. 0 means there is no correlation at all. The positive and negative refer to the direction of the correlation, rather than the strength.)

Which of the following best defines a systematic review? a. A process that scans many articles for data which fit the intent of the study. b. A primary study. c. A study that looks at a specific population at a specific point in time. d. A review where one individual systematically gives a review of the topic at hand, usually with research to back it up. e. A review that looks at a group of people defined by the presence or absence of a specific trait through time.

a. A process that scans many articles for data which fit the intent of the study. (B is the data that makes up a systematic review. C is a cross-sectional study. D is referring to editorials, opinions, and ideas. E is a cohort study.)

What was the cohort study originally designed for? a. A study that compared the disease experience of people born at different periods b. To closely examine a specific person's disease experience c. To look forward at the future risk experience of a specific group d. To determine the likelihood of disease spreading between populations e. Eliminate bias

a. A study that compared the disease experience of people born at different periods

Willis Test: Omnibus test statistic and cannot tell you which specific groups of your independent variable are statistically significantly different from each other a. Both Statements are True b. The first statement is true and the second is false c. The first statement is false and the second statement is true d. Both statements are false

a. Both Statements are True

Which study design should be used when one wants to describe a population, situation, phenomenon? a. Descriptive Study b. Experimental Study c. Cross-sectional Study d. Meta-Analysis e. Case Control Study

a. Descriptive Study (Descriptive studies describe a population, situation, or phenomenon that is being studied. Experimental studies measure the effect of independent variables on dependent variables. Cross-sectional studies analyze data from a population or representative subset at a specific point in time. Meta-analysis combines the results of multiple scientific studies. Case control studies are observational studies in which two existing groups differing in outcome are identified and compared on the basis of some supposed causal attribute.)

Cross-sectional study uses data that ____? a. Does not include manipulating variables. b. Does not have any bias. c. Are collected from multiple points in time. d. Follows one group of participant. e. Are hard and difficult to obtain.

a. Does not include manipulating variables. (Variables can not be manipulated when data is taken. Data collected can be biased, collected from a single point in time, and does NOT have to follow a group. This study is actually easy and quick to do.)

Conducting experiments on collected tissue is an example of what kind of study? a. In vitro b. In vivo c. Case report d. Cohort study e. Case-control study

a. In vitro (In vitro studies can be used to explore biological functions while isolated from biological context; in vivo takes place in a living organism)

compares two independent samples (ex: girls vs boys height) and is nonparametric a. Mann-Whitney Test b. One-sample paired T-test c. ANOVA test d. Two-sample unpaired T-test e. Spearman Correlation test

a. Mann-Whitney Test

The WMW Test uses which type of data? a. Ordinal b. Interval c. Ratio d. Nominal

a. Ordinal

Randomized Control Trial (double blind) In our example study design, patients were placed in two groups, receiving either fluoride or no treatment. What kind of randomised controlled trial does this fall under? a. Parallel-Group b. Crossover c. Cluster d. Factorial e. Triple RCT

a. Parallel-Group (Parallel-group→ the groups received only one treatment each (not crossover or Factorial) and were not pre-selected (not cluster). Triple RCT is made up.)

Cross-section studies are often used to determine what? a. Prevalence b. Incidence c. Causation d. Timeline of disease e. Rare diseases

a. Prevalence (Prevalence is the proportion of people in a population who have a particular disease at a given time without taking into account when they developed this disease. Incidence is the rate at which NEW diseases are appearing. Causation is similar to etiology which cannot be determined because the data taken is of a single point in time. Rare diseases are hard to study because of the small population size.)

The Friedman's Test uses what sampling method? a. Random sample b. Systematic sample c. Stratified d. Cluster sample e. Non-random sample

a. Random sample

The Friedman's Test uses what information to find differences in treatments? a. Rank (ranked retrieval) b. Set (set retrieval) c. Discrete d. Non-random e. Non-continuous

a. Rank (ranked retrieval)

The WMW Test must use ordinal data for calculations because the data can be ____? a. Ranked b. Normalized c. Paired d. Easily probed for periodontal pocket depth

a. Ranked (The WMW test uses ordinal data in a ranked calculation so that the test can bypass the necessity of using normally distributed data. These characteristics allow the test to be non-parametric.)

Another name for "case control studies" is __________. a. Retrospective study b. Cohort study c. Cross-sectional study d. Longitudinal study e. Meta-analysis

a. Retrospective study

The Wilcoxon signed-rank test makes use of the magnitude of the difference between paired observations but the a. Sign test uses only the direction of the difference. b. Kruskal-Wallis uses the sign of the difference. c. Sign test uses the square of the difference. d. Sign test uses the residuals. e. Wilcoxon test uses only the square of the difference.

a. Sign test uses only the direction of the difference. (The sign test works only on the difference between related observations, but the Wilcoxon signed-rank test takes into account the magnitude of the differences)

define cases (w outcomes of interest) and controls (without outcome). compares proportion of cases w exposure (risk factor) to proportion of controls w exposure (risk factor). -small sample size -good for rare diseases/outcome -highest potential for bias -weak evidence for causality -cannot determine prevalence or incidence a. case-control (retrospective) study b. meta-analysis c. cross-sectional study d. cohort study e. experimental study

a. case-control (retrospective) study

type of test used when data follows a particular distribution (ex: normal, bell, etc). generally more powerful a. parametric test b. unpaired test c. nonparametric test d. one-tailed test e. paired test f. two-tailed test

a. parametric

What is/are the limitations of case reports and series a) Lacks clinical presentation b) Lacks a comparison or control group c) The evidence is anecdotal based d) None of the above e) All of the above

b) Lacks a comparison or control group (Case reports and series lack a comparison or control group to compare outcomes and have little statistical validity. It cannot compare what is happening with others who do not have the condition or treatment.)

What value range will the Spearman rank correlation coefficient ρ (rho) always fall in? a. 0 to 1 b. -1 to 1 c. -1 to 0 d. 0 to 5 e. -2 to 2

b. -1 to 1 (The Spearman rank correlation coefficient, ρ (pronounced rho), considers the ranks of the values for the two variables. ρ will always be a value between 1 and -1, and the farther from zero, the stronger the relationship between the variables.)

How many factors can the Friedman's Test analyze? a. 0 b. 1 c. 2 d. ≥3 e. No greater than 5

b. 1

tests the null hypothesis that the distribution of a categorical variable is the same in 2 (or more) independent samples and is parametric a. Fisher exact test b. Chi square test c. one way ANOVA d. paired T-test e. Mann-whitney test

b. Chi square test

Case studies attempt to demonstrate an association between _________ and _________. a. Disease; population b. Exposure; outcome c. Sensitivity; specificity d. Frequency ; time e. None of the above

b. Exposure; outcome

tests the null hypothesis that the distribution of a categorical variable is the same in 2 (or more) independent samples and is nonparametric a. Fisher exact test b. Chi square test c. one way ANOVA d. paired T-test e. Mann-whitney test

b. Fisher exact test

What level of information is in a Randomized Control Trial (single blind)? a. Level I b. Level II c. Level III d. Level IV e. Level V

b. Level II

The Wilcoxon-Mann-Whitney test compares ____ between two independent sets of data? a. Median b. Mean c. Bounds d. Shape

b. Mean

What type of correlation would one have in a Spearman Correlation test if one variable decreases as the other variable increases? a. Positive Correlation b. Negative Correlation c. Zero Correlation d. Pearson Correlation e. Spearman Correlation

b. Negative Correlation (Positive correlation is one where as one variable increases, so does the other. Negative correlation is if one variable decreases as the other increases. Zero correlation is one where there is no relationship between the variables. Pearson correlation is a test that measures of linear correlation between two sets of data)

What does double blind mean? a. Participants and experimenters know who is receiving the specific treatments b. Neither participants nor experimenters know who is receiving the specific treatments c. Only experimenters know who is receiving the specific treatments d. Only participants know who is receiving the specific treatments e. The specific treatment itself is unknown

b. Neither participants nor experimenters know who is receiving the specific treatments

Can a cross-sectional study determine etiology? a. Yes, because cross-section study gathers data before and after incidence b. No, because cross-section study gathers at a single point in time c. Yes, because cross-section study has no data bias d. No, because cross-section study are relatively easy and quick to do e. Yes, because cross-section studies are a figment of our imagination

b. No, because cross-section study gathers at a single point in time (Etiology is the cause of a disease or condition, cause and effect cannot be determined by a snapshot. Cross-section study does not gather data before or after, and has data bias. The study is easy and quick to do but has little relevance to etiology.)

Fisher's exact test is a statistical test used to determine if there are _____ associations between ______ categorical variables. a. Random, three b. Nonrandom, two c. Random, two d. Nonrandom, four e. Random, four

b. Nonrandom, two

compares two sets of observations on a single sample (ex: to compare weight of infants before and after eating) and is parametric a. Fisher test b. One-sample paired T-test c. one-way ANOVA test d. Wilcoxon matched pairs test e. Pearson Correlation test

b. One-sample paired T-test

Which of these is NOT required for an in vitro study? a. Sample preparation and handling b. Patient consent c. Isolated environment to perform tests d. Sufficient annotation of the array e. Statistical analysis

b. Patient consent (In vitro studies does not require human participation.)

assesses the strength and direction of a linear association between 2 continuous variables a. Fisher exact test b. Pearson correlation c. one way ANOVA d. Spearman rank correlation e. Mann-whitney test

b. Pearson correlation

What data is NOT needed for a Randomized Control Trial (single blind)? a. Randomly assigned groups b. Qualitative data that describes the investigator's purpose c. Data that describes the result of the control group d. Data that describes the result of the experimental or treatment group e. b and d

b. Qualitative data that describes the investigator's purpose

In which type of randomization can groups be unequally sized? a. Stratified b. Simple c. Block d. Complex e. a and b

b. Simple (In stratified and block RCT, groups are equally sized.)

Analogous to the chi-square test, Fisher's exact test is a nonparametric testfor categorical data, but can be used in situations in which the chi-square test cannot, such as with _____________________. a. Large sample sizes b. Small sample sizes c. Data sets with a high average d. Data sets with a low average e. Data sets with no outliers

b. Small sample sizes (Small sample sizes are necessary because utilizing an approximation method will not work. All of the expected numbers are greater than 5→ use the chi-square test; if an expected number is less than 5, you should use an alternative (Fisher exact test))

Which statistical test determines the strength and direction of the monotonic relationship between two variables? a. Pearson Correlation b. Spearman Correlation c. Binomial Test d. Chi-Square Test e. One way anova

b. Spearman Correlation (Spearman Correlation tests strength and direction of the monotonic relationship between variables. Pearson correlation tests strength and direction of the linear relationship between variables. Binomial tests determine if results differ from what was expected. Chi-Square tests measures how well the observed distribution of data fits with the distribution that is expected if the variables are independent.)

What is the data collected in a one sample T-test ultimately compared to? a. Margin of error b. Standard value c. Second group in the study d. Critical-value chart e. ANOVA Test

b. Standard value (The standard value is also known as the known value. It is an accepted value that often comes from published literature. We compare the mean of the data collected to the known mean value to see if there is a statistical difference between the 2 values.)

If conditions for a Wilcoxon-Mann-Whitney test are met AND the data is normally distributed, which test should you use instead? a. Chi-Squared b. T-Test c. Binomial Test d. The Statistics test

b. T-Test (The WMW Test compares the difference of means between two independent sets of data using non-parametric data. If the data is normally distributed, a T-test is a higher power test that is also used to evaluate differences in the mean of two groups.)

Which of the following is not a requirement of the one sample t-test? a. Data must be normally distributed b. Test variable must be discrete c. Data must be a random sample of the population d. Data must have homogeneity of variance e. There must be no outliers in the data set

b. Test variable must be discrete (The test variable must be continuous for a one sample t-test. This means that there must be an unlimited number of values between the highest and lowest values. An example of a continuous variable is height.)

Choose the best study design to use One-Way ANOVA: a. In a group of randomly picked people, which have composite restorations vs. amalgam restorations. b. Testing to see the difference in monomer release from 3 different composite resins. c. Determine if the risk assessment for caries differ between family members. d. Comparing if full mouth crowns are significantly better than complete dentures.

b. Testing to see the difference in monomer release from 3 different composite resins. (One-Way ANOVA needs a dependent variable that is continuous and independent variables that are categorical. The best study design listed would be B: Dependent variable = amount of monomer release; Independent variables = 3 different composite resins.)

When utilizing binomial tests, which of the following is not an assumption? a. Items are binary, meaning there are two of them and they are nominal b. The sample item is dependent, meaning one item has bearing on the other c. The same sample size is significantly less than the population size d. The sample is a fair representation of the population e. The sample items are independent, meaning one item has no bearing on the other

b. The sample item is dependent, meaning one item has bearing on the other (In binomial designs, you assume the opposite, that the sample items are independent, meaning one item has no bearing on the other. The events A and B are independent. For example, if one participant likes the Oral-B toothbrush and the other does not like the Oral-B toothbrush, the knowledge that one participant likes the item does not affect the chance for the other participant to not like the item.)

Do animal research studies help animals? a. No, animal research studies only benefits humans b. Yes, animal research studies have allowed for medications, treatments, etc. for the animal kingdom to become much more vast. c. No, animal research studies are abusive towards animals. d. Yes, animal research studies help animals by giving them a purpose in life e. No, animal researches studies have little benefit to humans and or animals and should be considered an outdated study method.

b. Yes, animal research studies have allowed for medications, treatments, etc. for the animal kingdom to become much more vast. (Although we gain much benefit from animal research as humans, many of the drugs tested on animals have shown to help them just as effectively if not more so than what it was intended for for humans. It also allowed us to gain a much better understanding of animal anatomy, physiology, and psychology.)

A meta-analysis is described as a. a study design that randomly assigns participants into an experimental group or a control group. b. a quantitative, formal, epidemiological study design used to systematically assess previous research studies to derive conclusions about that body of research. c. a type of observational study in which two existing groups differing in outcome are identified and compared on the basis of some supposed causal attribute. d. a type of observational study that analyzes data from a population, or a representative subset, at a specific point in time e. retrospective study that looks back in time to find the relative risk between a specific exposure (e.g. second hand tobacco smoke) and an outcome (e.g. cancer).

b. a quantitative, formal, epidemiological study design used to systematically assess previous research studies to derive conclusions about that body of research.

combines data from multiple independent studies to maximize precision and power in testing for statistical significance -limited by publication bias a. case-control (retrospective) study b. meta-analysis c. cross-sectional study d. cohort study e. experimental study

b. meta-analysis

test that compares values from independent samples a. parametric test b. unpaired test c. nonparametric test d. one-tailed test e. paired test f. two-tailed test

b. unpaired test

Which of the following conditions about case reports and series is true? a) Case report and series is always retrospective B) Case report and series involve hypothesis testing c) For all case reports and case series a HIPAA authorization should be obtained d) Case report and series are comparative and have a large number of individuals e) When there is more than two patients a submission to the designated IRB is required

c) For all case reports and case series a HIPAA authorization should be obtained (A HIPPA form is required from the parent or legally authorized representative for use and disclosure of their protected health information. De-identifying case reports will not need a HIPAA authorization.)

What kind of data do editorial study designs need? a) quantitative b) experimental c) qualitative and quantitative d) survey / interview e) qualitative

c) qualitative and quantitative (Quantitative research deals with numbers and statistics, while qualitative research deals with words and meanings - and editorial deals with both. Editorials attempt to formulate viewpoints based on a subjective analysis of what is happening and conflicting/contrary opinions)

An editorial discusses which of the following? a) published research published over 10 years ago b) meta-analysis reviews only c) subjective research topic of interest d) objective opinions only e) news only

c) subjective research topic of interest (Editorials are known specifically for being subjective. It is an individual's opinion on a current event or social issue. The goal of a good editorial is to persuade the reader to consider your perspective and change their opinion)

Which study design has only uncontrolled variables? a. Experimental Study b. Cohort Study c. Descriptive Study d. Meta-Analysis e. Case Control Study

c. Descriptive Study (Descriptive studies only contain uncontrolled variables. Experimental, Meta-Analysis, Cohort, and Case Control studies contain independent and dependent variables.)

compares 3 or more sets of observations made on a single sample and is nonparametric a. Fisher exact test b. Chi square test c. Kruskal-Wallis analysis of variance by ranks d. Two-way analysis of variance by ranks e. One-way ANOVA

c. Kruskal-Wallis analysis of variance by ranks

In a One-Way ANOVA, the dependent variable is ______ and the independent variable is ______. a. Nominal; Interval b. Ordinal; Ratio c. Ratio; Nominal d. Nominal; Ordinal

c. Ratio; Nominal (There are 4 different levels of statistical measurements: Nominal, Ordinal, Interval, and Ratio. This can be further divided into categorical (nominal/ordinal) and continuous (interval/ratio). In One-Way ANOVA, the dependent variable needs to be continuous, while the independent variable needs to be categorical. Therefore, the correct answer is C, since ratio is a continuous measurement and nominal is a categorical measurement.)

What is a disadvantage of case control studies? a. Large sample size required b. Discontinuous data c. Recall bias d. Simultaneously looks at multiple risk factors e. More time needed

c. Recall bias

The binomial distribution depends on which of the following? a. Mean and standard deviation b. Standard deviation and number of successes c. Sample size and probability of success d. Mean and probability of success e. Both C & D

c. Sample size and probability of success (Binomial test specially calculates the probability from a specific sample size, n, and the number of the desired outcome. It can be thought of as simply the probability of a SUCCESS/ FAILURE or LIKED/DISLIKED outcome in an experiment or survey from a specific sample size.)

The Cohort study allows us to calculate all of the following, except one: a. Incidence rate b. Cumulative Incidence Rate c. Secondary Attack Rate d. Relative risk e. Hazard ratio

c. Secondary Attack Rate

The probability of rejecting the null hypothesis when it is in fact correct is known as what? a. Degrees of Freedom b. Standard Value c. Significance Level d. Mean Value e. Median Value

c. Significance Level (The significance value is also known as the alpha-level, this value indicates the probability of rejecting the null hypothesis when it is true.)

Which of the following statements is correct about test tubes? a. Test tubes are used to measure solutions. b. Test tubes are used to measure liquids. c. Test tubes are used for qualitative observations, but not for measuring solutions and liquids. d. Test tubes are used for quantitative observations, but not for measuring solutions and liquids. e. Test tubes are used for very large scale experiments and reactions.

c. Test tubes are used for qualitative observations, but not for measuring solutions and liquids. (Test tubes are widely used by researchers to handle chemicals, especially for qualitative experiments and assays. Their spherical bottom and vertical sides reduce mass loss when pouring, make them easier to wash out, and allow convenient monitoring of the contents.)

The Kruskal-Wallis Test does assumes normality in data and is much less sensitive to outliers a. Both Statements are True b. The first statement is true and the second is false c. The first statement is false and the second statement is true d. Both statements are false

c. The first statement is false and the second statement is true (does not assume normality in date; less sensitive to outliers)

What is a limitation of an animal research study? a. Animals have too long of a lifespan to show any experimental data b. The variety of animals is too large and can interfere with data collection accuracy. c. There is often a discord between human diseases and animal diseases d. Animals do not have the same human awareness, so they cannot participate in experimental research as well as humans can. e. Animal research is very inexpensive.

c. There is often a discord between human diseases and animal diseases (Animals and humans do not always have the same presentation of disease for example they lack comorbidities, risk factors & pre-existing conditions)

Which of the following is not needed for a Pearson Correlation? a. A random sample b. Each of the data points has both variables (X and Y) c. There must be at least one outlier in the data set d. There is a linear association e. All of the above are needed

c. There must be at least one outlier in the data set (There are preferably no outliers as these can throw the correlation off.)

The sign test and the Wilcoxon signed-rank test both a. Assume normal populations. b. Assume independent samples. c. Use the nominal scale of measurement. d. Assume grouped samples. e. Uses square of the difference.

c. Use the nominal scale of measurement.

The Paired T-test, also called the dependent T-test, is a statistical procedure used to measure/determine ____________. a. Whether the mean difference between two sets of observations is one. b. Whether the mean difference between two sets of observations is two. c. Whether the mean difference between two sets of observations is zero. d. Whether the mean difference between two sets of observations is not zero. e. None of the above

c. Whether the mean difference between two sets of observations is zero. (The null hypothesis is always assumed to be that there are no differences between the two populations.)

in study population, concurrently measures outcome (disease) and risk factor; compares the proportion of a diseased group with risk factor to proportion of nondiseased group with risk factor. defines prevalence but may have selection bias a. case-control (retrospective) study b. meta-analysis c. cross-sectional study d. cohort study e. experimental study

c. cross-sectional study

type of test used when a particular distribution cannot be assumed; rank data rather than taking absolute differences into account a. parametric test b. unpaired test c. nonparametric test d. one-tailed test e. paired test f. two-tailed test

c. nonparametric

Which of the following is not a limitation in Ideas, Editorials, Opinions? a) controversy is difficult to avoid b) prone to bias and errors of reasoning c) experts at the bottom level of evidence quality d) a highly credible source e) least reliable source

d) a highly credible source (Editorials are one of the least credible sources, prone to controversy, bias, and errors)

atic Review Which of the following studies would NOT be useful to a systematic review? a. A study found in a public access journal with easy to reference materials. b. A study with clear cut explanations for data gathering procedures. c. A study published in a journal with a subscription fee. d. A study without references published outside of an official scientific journal. e. A study based on clinical results and examination from a rural area of the country.

d. A study without references published outside of an official scientific journal. (A, B, and E are all examples of good studies to use for a systematic review. C seems tricky, as it is a bit harder to access due to the subscription fee- however, journals with subscription fees tend to publish good research. D is the best choice for this question, as a study without references and published outside of a trusted method is not a great option for a systematic review.)

In a graphical representation, an r value of -.61 will determine a. The slope of the line of best fit b. The direction of the line of best fit c. The strength of the correlation d. B and C e. All of the above

d. B and C (A is incorrect. The slope of the line of best fit is determined by the data points, not the r value. The direction of the line is indicated by the positive or negative value of r. The strength of the correlation is represented by the numerical portion of the r value.)

Strengths of meta-analyses include all of the following except: a. Considered reliable and accurate b. Establish statistical significance across studies that might otherwise seem to have conflicting results c. Provide an overview of multiple studies d. Can be difficult, time-consuming, and include publication bias e. They enable generalization of results to a larger population

d. Can be difficult, time-consuming, and include publication bias (Meta-analyses are time consuming and require synthesis of a large amount of data. Also, publication bias may be present in meta-analyses because a study is more likely to be published if the results are significant.)

Fisher's exact test assumes that the individual observations in a given test are _____ and the row and column totals are ________. a. interdependent , flexible b. Independent, flexible c. Dependent, fixed d. Independent, fixed e. Interdependent, fixed

d. Independent, fixed (Assuming the marginal totals are fixed greatly simplifies the mathematics and means that probabilities can be estimated using the hypergeometric distribution with four classes. Hypergeometric distribution is similar to the binomial distribution, in which is the probability of success or failure, or with this test: significant or not significant)

Limitations of cross-sectional study includes which of the following? a. Must be performed before a cohort study. b. Must collect data from multiple points in time. c. Cannot compare groups across defined variables. d. May have bias' including non-response, recall, and prevalence bias. e. Able to measure prevalence for all factors.

d. May have bias' including non-response, recall, and prevalence bias. (Cross-section study may have many bias' such as non-response, recall, or prevalence-incidence bias. This study does NOT have to be performed before a cohort study, collects data from a SINGLE point in time, and CAN compare groups across defined variables. E is an advantage.)

Analysis of Variance (One-way ANOVA) is a statistical method of comparing the _______ of several populations. a. Variance b. Standard deviation c. Proportion d. Means e. None of the above

d. Means (One Way Analysis Of Variance (ANOVA) shows if there are any statistically significant differences between the means of 2 or more independent groups)

The null hypothesis in a fisher exact test says that rows and columns are: a. Are associated b. The same c. Not the same d. Not associated e. Inversely associated

d. Not associated (Null hypothesis→ no association between the rows and columns of the 2 × 2 table→ probability of a subject being in a particular row is not influenced by being in a particular column. If the columns represent the study group and the rows represent the outcome, the null hypothesis is interpreted as the probability of having a particular outcome not being influenced by the study group, and the test evaluates whether the two study groups differ in the proportions with each outcome.)

What does the one sample median test attempt to measure/show? a. An exact test of statistical significance of any deviation from what is expected in the distribution of observations in two particular categories b. To show if two groups from the same population are the same or different in some way c. Used to detect differences in treatments across multiple test attempts after ranking each block or row d. Significant difference between our hypothesized median and the real median of a sample e. Attempts to draw a line of best fit through the data of two variables and the pearson's correlation

d. Significant difference between our hypothesized median and the real median of a sample (Significant difference between our hypothesized median and the real median of a sample. The one sample median test is a non-parametric test testing non-metric values and cannot determine actual differences in a population)

assesses the strength and direction of a monotonic association between 2 continuous variables a. Fisher exact test b. Pearson correlation c. one way ANOVA d. Spearman rank correlation e. Mann-whitney test

d. Spearman rank correlation

Which of the following is NOT true regarding animal research studies? a. Animal research studies have led to the development of human vaccines b. A researcher must first obtain a license before conducting animal research c. Animal research studies have led to development of animal vaccines d. Test animals are typically gathered from shelters & animal rescues e. There is an ethical debate regarding whether or not animals should be tested on

d. Test animals are typically gathered from shelters & animal rescues (Most of these animals are bred in the lab specifically for use in research)

Which of the following is not needed to have an effective RCT design? a. PICOT format for hypothesis b. A well defined and approved protocol c. Random allocation of subjects d. The study must be double-blind e. All of the above are necessary

d. The study must be double-blind (The study does not have to be double blind to be effective. In many situations, it is impossible to have a double blind RCT (physical therapy trials).)

Which is not a limitation of the cohort study? a. You may have to follow large numbers of subjects b. They are not good for very rare diseases. c. They are not good for diseases with a long latency. d. They are low cost and have a quick turnaround time e. Differential losses to follow up can occur, which creates bias

d. They are low cost and have a quick turnaround time

compares two independent samples (ex: girls vs boys height) and is parametric a. Mann-Whitney Test b. One-sample paired T-test c. ANOVA test d. Two-sample unpaired T-test e. Spearman Correlation test

d. Two-sample unpaired T-test

What type of questions are descriptive studies unable to answer? a. Who b. What c. Where d. Why e. How

d. Why (Descriptive studies do not answer the why of a research problem as one needs to have thorough understanding of a research problem before ascertaining why the problem exists)

compares two sets of observations on a single sample (ex: to compare weight of infants before and after eating) and is nonparametric a. Fisher test b. One-sample paired T-test c. one-way ANOVA test d. Wilcoxon matched pairs test e. Pearson Correlation test

d. Wilcoxon matched pairs test

You have designed a study where people either say that they like the Oral-B electric toothbrush or they do not. What type of distribution would you use? a. normal distribution b. non-normal distribution c. noncentral t-distribution d. binomial distribution e. central distribution

d. binomial distribution (The binomial test is used when an experiment has two possible outcomes, such as success/failure; yes/no; like/dislike. In the Oral-B design, we are doing the same, asking if the participants like or dislike the electric toothbrush.)

in study population, define exposed group (risk factor) and nonexposed group (without risk factor). compares proportion of exposed group with outcome (disease) to proportion of nonexposed group with outcome (disease) -defines incidence -strong causality evidence -decreased bias -not good for rare diseases/outcomes a. case-control (retrospective) study b. meta-analysis c. cross-sectional study d. cohort study e. experimental study

d. cohort study

test used when an intervention can only have 1 plausible effect on the outcome a. parametric test b. unpaired test c. nonparametric test d. one-tailed test e. paired test f. two-tailed test

d. one-tailed test

Fisher's (exact) test is practically applied in analysis of _________ samples; however, it is actually valid for _________ sample sizes. a. all, only small b. all, only large c. all, no d. only small, all e. only large, all

d. only small, all (Fisher's exact test is practically applied only in analysis of small samples but actually it is valid for all sample sizes. For example, when more than 20% of cells have expected frequencies < 5, Fisher's exact test must be used because applying an approximation method is inadequate. It is also worth noting that many packages provide the results of Fisher's exact test for 2 × 2 contingency tables but not for bigger contingency tables with more rows or columns.)

Which of the following data does case reports and series not use? a) Case series b) Quantitative data c) Archival data d) Patient data e) Case reports and series use all of the data above

e) Case reports and series use all of the data above (The data used for case reports and series are case data, patient data, quantitative data, field notes and research observations, data about explanations and studies that rival the case study reports, archival data, time period over which study was conducted, and case series.)

What is the first step taken when performing a systematic review? a. Conduct a literature search for important resources. b. Grab a coffee with your fellow scientists. c. Analyze the level of bias. d. Set inclusion and exclusion standards e. Define a clear research question and method.

e. Define a clear research question and method. (E is the first step in any good scientific process- ask a question, and define the steps you wish to take to reach an answer)

According to the hierarchy of scientific evidence, what provides the highest quality of evidence? a. Case control b. Randomized controlled trials c. Cohort studies d. Case reports e. Meta-analyses and systematic reviews

e. Meta-analyses and systematic reviews (Systematic reviews and meta-analyses are considered to be the highest quality evidence on a research topic because their study design reduces bias and produces more reliable findings)

compares 3 or more sets of observations made on a single sample and is parametric a. Fisher exact test b. Chi square test c. Kruskal-Wallis analysis of variance by ranks d. Two-way analysis of variance by ranks e. One-way ANOVA

e. One-way ANOVA

in study population, randomly assigns subjects to receive intervention or no intervention. compares rate of outcomes between intervention and control groups -best evidence for causality -not suitable for rare diseases/outcomes a. case-control (retrospective) study b. meta-analysis c. cross-sectional study d. cohort study e. experimental study

e. experimental study

test performed on paired data (where the same parameter is measured on each patient before and after an intervention) a. parametric test b. unpaired test c. nonparametric test d. one-tailed test e. paired test f. two-tailed test

e. paired test

test used when an intervention could potentially lead to an increase or decrease in the outcome a. parametric test b. unpaired test c. nonparametric test d. one-tailed test e. paired test f. two-tailed test

f. two-tailed test