1. Science
  2. Other
  3. question 1 what does sampling distribution of means show calculated...

Question: question 1 what does sampling distribution of means show calculated...

Question details

Question 1

What does ‘Sampling distribution of means’ show:


Calculated means from several samples of same size and from same population.


Individual actual values from two samples of different size but same population


Mean calculated from one sample


Individual actual values from one sample

Question 2

Which one of the following study designs has the key identification feature of using aggregate or group level data for the analyses?




Case control







Question 3

Standardized scores or z-scores allow us to compare variables with different units and different means and standard deviations, commonly used in health sciences and health practice. If mean weight for a sample of patients is 74 kgs and standard deviation is 5 kgs. What is the standardized score (or z-score) for a patient whose weight is 62 kgs? Use of brackets, at least for the numerator part, is highly recommended. Please remember only the final answer with two decimals is required (and not the whole working out).

Question 4

A cross-sectional study may allow us to compare prevalence of an outcome between exposed and non-exposed groups using __________________ while in an ecological study  the use of _____________________ is quite common to establish a link between exposure and an outcome especially where data on both are continuous.

Please choose one option from below that has  both correct terms, and in correct order, for the two blanks in the statement above.


Prevalence ratio and squared value of Pearson's correlation coefficient r, respectively.


Squared r (Pearson's correlation coefficient) and Prevalence ratio, respectively


Pearson's r squared and odds ratio, respectively


Prevalence ratio and Risk ratio, respectively


Incidence rate and r squared, respectively.


Question 5

Which one of the following statements is incorrect about Histogram?


Y axis represents Frequency/Count


Intervals are of equal width


Bands are vertical and should not touch each other.


Vertical axis should start at zero and not have any breaks.


It is the most common graph to display frequency distribution of a continuous variable.

Question 6

Which one of the following statements about study designs is INCORRECT?


Case control studies are observational analytic design.


Case Report and Case Series belong to descriptive category of study designs.


Ecological studies are based on population level or group based aggregate data.


Difference between a true experiment and a quasi-experiment is the lack of random assignment of study subjects into experimental and control groups.


Cross-sectional studies can be both descriptive as well as analytical.


Cohort studies are usually descriptive design.

Question 7

If sample sizes are large enough sampling distribution of mean will show normal distribution even if the variable itself is skewed in the population. This is a simplified description of:


Standard Normal distribution


Assumption test rule 


Empirical rule of 68%, 95% & 99%


Central Limit Theorem


Murphy’s Law

Question 8

Which one of the following is not 'Analytic' type of study design?






Case control




Case Series

Question 9

Both are experimental studies but the main differnce between a randomized controlled Trial (RCT) and a quasi-experimental trial (experiment-like trial) is the absence of:


Control group




Random sample




Sense of humour

Question 10

This question will help you to interpret correctly and differentiate between p value for an assumption test  as opposed to p value for a hypothesis test(most common error in the first written assignment).

All statements below are correct except TWO; please identify the two incorrect statements. Two answers are required. 



P value (or probability value) of a hypothesis test tells us how likely are our findings due to random chance factors if a study's null hypothesis was true and there really was nothing going on (in terms of relationship between variables) in the population represented by the sample. 


If p value for Shapiro Wilk test of normality is less than .05, likelihood of chance factors responsible for the observed findings is low and we conclude that a real correlation  between the two variables exists in the population represented by the sample. 


If p value for Shapiro Wilk test of normality is less than .05 we conclude that the assumption of normality, on the basis of this test, is not violated.


If p value generated by Pearson’s correlation analysis is less than .05 (p=<.05) it means that the likelihood of random chance alone for the observed correlation (or even a stronger one or more extreme if null was correct) is less than .05 (or <5%) we reject null and conclude a real correlation exists between the two variables in the population and is statistically significance.


If p value generated by Pearson’s correlation analysis is .05 (or higher) we conclude that the likelihood is high that the observed correlation is probably due to random chance factors and in the wider population represented by the sample there really is no correlation between the two variables.


If p value for Shapiro Wilk test of normality is .067 we conclude that the assumption of normality is met or not likely to be violated.  


Question 11

What is 'Homoscedasticity'?


It is one of the assumption (i.e. requirement) for correlation analyses that the variability in one variable should be roughly similar or uniform across all values of the other variable.


It is one of the assumption for correlation analysis that the variability in one variable should not be similar across all values of the other variable.


It is one of the assumption for 'Association' that the variability in one variable is similar across all values of the other variable.


It refers to same-sex marriage.

Question 12

All of the following statements are correct except one; please identify the incorrect statement.


If p value after conducting a hypothesis test is .005 we reject null.


Results of a study have 'Statistical significance' if there is only less than 5% random chance likely for the observed findings (determined by p value) whereas Practical significance means if results are actually meaningful or clinically important (determined by measures of association and effect which may be different for different situations/studies/analyses).


If p value for a hypothesis test is .054 null will be rejected and results will be considered statistically significant.


Although some researchers may use these terms interchangeably, however, the difference between association and correlation is that these terms are used for relationship between two categorical variables and relationship between two continuous variables, respectively.


Inclusion and Exclusion criteria for an epidemiological research study are list of conditions or characteristics, varying from study to study, that determine who should be included in the study and who should be excluded from participating in that study.


The purpose of performing a statistical test is to rule out that the observed findings are not due to chance factors but in fact real and exist in the population represented by the sample.


Question 13

Which one of the following is INCORRECT statement?


If Pearson's r is .61, then 37% of variation in y/dependent variable can be explained by the x/independent variable.


An apparently strong correlation can simply be due to extreme values or outliers, if present.


If Pearson's r is 0, there is no linear correlation between the two variables.


For correlation between study hours and final mark r = .72 while for negative correlation between years of education and time spent in prison r = -.72.  We can conclude that both correlations are equally strong.


If Pearson's r is .71, then 71% of variation in the dependent variable can be explained by the independent variable.


If Pearson's r is .35 then the value for the suitable measure of effect is .12

Question 14

If Pearson's correlation coefficient 'r value' is -0.96 then what will be the value for the measure of association and effect used here? Please calculate and type in your final answer as percentage with two decimals after correct rounding.

Question 15

Please choose one answer from below that has all three correct terms  (and in correct order) to go in the three blank spaces this statement has:

Standard error obtained from a sampling distribution (i.e. a distribution that is based on several hypothetical samples from a population) provides us some general idea as to how close our ______________is to the unknown_______________ that we would like to make _______________about.


Sample parameter, population sample, inferences.


Population statistic, sample parameter, hypothesis


Population parameter, sample parameter, predictions


Population, sample statistic, conclusions


Sample statistic, population parameter, inferences

Question 16

For an 'assumption test' (that tests an assumption or requirement before analysis) we would want the p value to be greater than .05 whereas for a statistical test we use for NHST we would want the p value to be less than .05.





Solution by an expert tutor
Blurred Solution
This question has been solved
Subscribe to see this solution