midterm two statistics
In addition to the significance value of the t-test, it is beneficial to calculate the effect size. Cohen's d is a measure of effect size. How is it calculated? (mean 2 - mean 1) / pooled standard deviation (mean 2 - mean 1) × pooled standard deviation (mean 2 + mean 1) - pooled standard deviation (mean 2 / mean 1) + pooled standard deviation
(mean 2 - mean 1) / pooled standard deviation
If the scores on a test have a mean of 26 and a standard deviation of 4, what is the z-score for a score of 18? 2 -1.41 -2 11
-2
Suppose we wanted to apply a one-tailed test as opposed to a two-tailed test. How would we covert a significance of p = .284? .284 / 2 = .142 .284 × 2 = .568 .284 / 11 = .026 .284 × 11 = 3.124
.284 / 2 = .142
If the significance level is set at .05, which of the following best reflects the probability of a chance finding? 1 in 20 1 in 5 1 in 10 1 in 15
1 in 20
If the degrees of freedom for an independent-samples t-test is 38, how many total participants were in the study (i.e, what is the sample size)? 37 38 39 40
40
The interquartile range represents how many percentiles? 25% 10% 50% 75%
50%
Participants rated their mood score out of 20 before and after listening to Reign in Blood by the thrash metal band Slayer with 8 people. What are the degrees of freedom for this study? 7 8 16 15
7
A variable that measures the effect that manipulating another variable has is known as: A predictor variable An independent variable A dependent variable A confounding variable
A dependent variable
Participants take a simulated driving test twice. In one condition they have no alcohol, in the other they have enough alcohol to take them over the legal limit. What type of design is this? Repeated-measures (repeated-measures is a synonym of within-subjects) Related-measures Between-subjects Independent-measures
Repeated-measures
The purpose of a control condition is to: Rule out a tertium quid. Allow inferences about cause. Control for participant characteristics. Show up relationships between predictor variables.
Show up relationships between predictor variables.
A small standard error of differences (i.e., small denominator in a t-test) tells us: That the differences between scores are not normally distributed. That the differences between scores are normally distributed. That most pairs of samples from a population will have very similar means. That sample means can deviate quite a lot from the population mean and so differences between pairs of samples can be quite large by chance alone.
That most pairs of samples from a population will have very similar means.
What does a significant test statistic tell us?There is an important effect. That the test statistic is larger than we would expect if there were no effect in the population. The hull hypothesis is false. All of the above.
That the test statistic is larger than we would expect if there were no effect in the population.
In general, as the sample size (N) increases: The confidence interval is unaffected The confidence interval becomes less accurate. The confidence interval gets narrower. The confidence interval gets wider.
The confidence interval gets narrower.
Complete the following sentence: A large standard deviation (relative to the value of the mean itself) indicates that the data points are close to the mean. indicates that the mean is a good fit of the data. indicates that you should analyse your data with a parametric test. indicates that the data points are distant from the mean (i.e. the mean is a poor fit of the data).
indicates that the data points are distant from the mean (i.e. the mean is a poor fit of the data).
Of what is p the probability? -p is the probability of observing a test statistic at least as big as the one we have if there is no effect in the population (i.e., the null hypothesis is true). -p is the probability that the null hypothesis (H0) is true. -p is the probability that the null hypothesis (H0) is false. -p is the probability that the results would be replicated if the experiment was conducted a second time.
p is the probability of observing a test statistic at least as big as the one we have if there is no effect in the population (i.e., the null hypothesis is true).
A new member of a basketball coaching staff, whose team is at the bottom of the league, has just completed a study into factors that affect player performance levels. However, he finds only one statistically significant factor, which he includes in his report but deliberately omits the other six non-significant findings. What is the term for what the coach has done? p-hacking HARKing Meta analysis Bayesian analysis
p-hacking
The standard deviation is the square root of the: coefficient of determination sum of squares range variance
variance
Which axis is the independent variable usually plotted on? x-axis y-axis z-axis a-axis
x-axis
Which axis is the dependent variable usually plotted on? x-axis y-axis z-axis a-axis
y-axis
What symbol is used to represent the standard error of the mean? Sx SEx σx μx
σx
A within-subjects design would be appropriate for which of the following situations? A researcher would like to study the effect of alcohol on reaction time. A researcher would like to compare individuals from at least two populations. The effect of a new treatment is studied in a small group of individuals with a rare condition. a and b.
A researcher would like to study the effect of alcohol on reaction time.
To help reduce the effects of hypertension (high blood pressure), researchers were interested in the effects of an acute 30 min bout of exercise over a two-week period. Resting blood pressure was measured before and after the two weeks of exercise and statistical significance was determined to be p = .001. Which of the following descriptions best describes its meaning? -A significant difference was found between the pre and post measurements and there may be an important effect. -A significant difference was found between the pre and post measurements and there is an important effect. -A significant difference was not found between the pre and post measurements but there may be an important effect. -A significant difference was not found between the pre and post measurements and neither was there an important effect.
A significant difference was found between the pre and post measurements and there may be an important effect.
A sports nutritionist undertook a study to examine the impact of a reduction in protein intake and team performance. The nutritionist found a showed a statistically significant effect of reduced protein intake on increased team performance. How can she explain to her manager that this does not mean she should start removing protein from the team's diet? A significant result does not mean that the effect is important A significant result means that the effect is strong. A significant result means that the effect is not relevant. A significant result means that the effect is weak.
A significant result does not mean that the effect is important
What is an outlier? A set of data outside the data file. A single score (e.g., participant response) that is very different from others. A score derived from a participant who has lied. A variable that cannot be quantified.
A single score (e.g., participant response) that is very different from others.
Which of the following best describes a confounding variable? A variable that affects the outcome being measured as well as, or instead of, the independent variable. A variable that is manipulated by the experimenter A variable that has been measured using an unreliable scale. A variable that is made up only of categories.
A variable that affects the outcome being measured as well as, or instead of, the independent variable.
A frequency distribution in which low scores are most frequent (i.e. bars on the graph are highest on the left hand side) is said to be: Positively skewed Leptokurtic Platykurtic Negatively skewed
Positively skewed
If a researcher sets a level of significance at .05 (i.e. 5%), what does this mean? About 5 times out of 100, a significant result will be found that is due to chance alone and not the intervention. About 95 times out of 100, a significant result will be found that is due to chance alone and not the intervention. About 5 times out of 100, a significant result will be found that is not due to chance, but the intervention. None of the above.
About 5 times out of 100, a significant result will be found that is due to chance alone and not the intervention.
Which of the following is true about a 95% confidence interval of the mean:-About 95 out of 100 confidence intervals will contain the population mean.-About 95 out of 100 sample means will fall within the limits of the confidence interval.-95% of population means will fall within the limits of the confidence interval.-There is a 0.05 probability that the population mean falls within the limits of the confidence interval.
About 95 out of 100 confidence intervals will contain the population mean.
Two distributions (D1 and D2) are plotted onto the same graph. D1 is right skewed, D2 is left skewed. The mean of D1 is lower than D2. Which of the following statements is incorrect? The mean of D2 is higher than the median of D2. The mean of D2 is lower than the median of D1. The median of D1 is the same as the mean of D2. All of the above
All of the above
Which of the following are important components of graphical illustrations? Labelled axes Clarity and conciseness A legend if appropriate All of the above
All of the above
If my null hypothesis is 'Dutch people do not differ from English people in height', what is my alternative hypothesis? Dutch people differ in height from English people. English people are taller than Dutch people. Dutch people are taller than English people All of the statements are plausible alternative hypotheses.
All of the statements are plausible alternative hypotheses.
If you use a paired samples t-test: The same participants take part in both experimental conditions. Other things being equal, you do not need as many participants to get a significant result (p < .05) as you would for an independent samples t-test. All of these are correct. There ought to be less unsystematic variance (i.e., less error) compared to the independent-samples t-test. The difference expected by chance (i.e., the denominator of the t equation) should be smaller than for the independent-samples t-test.
All of these are correct.
A variable manipulated by a researcher is known as: A discrete variable An independent variable A dependent variable A confounding variable
An independent variable
If you were to graphically present the learning style data, which might be the most appropriate option? Bar chart Scatterplot Histogram Stem-and-leaf plot
Bar chart
Confidence intervals: -Can be used instead of conventional statistics based on point estimates. -Are not frequently used in research articles because they can mislead the reader. -Are constructed using subjective evaluations of confidence. -None of these options are correct
Can be used instead of conventional statistics based on point estimates.
What effect would increasing the sample size have on the confidence intervals of the group? Confidence intervals would decrease in size. Confidence intervals would increase in size. Confidence intervals are unaffected by sample size. Confidence intervals could either increase or decrease in size.
Confidence intervals would decrease in size.
When questionnaire scores predict or correspond with external measures of the same construct that the questionnaire measures it is said to have: Ecological validity Content validity Criterion validity Factorial validity
Criterion validity
A frequency distribution in which high scores are most frequent (i.e. bars on the graph are highest on the right hand side) is said to be: Leptokurtic Platykurtic Negatively skewed Positively skewed
Negatively skewed
A swim coach is assessing swimmers' satisfaction with a new training regime. He had a sample size of 22 and a p-value of 0.3. Does the coach recommend that the swimmers stop using the new training regime? Yes, because the sample has low confidence levels. No, because the sample size is large and therefore the p-values are accurate. Yes, because statistical significance has nothing to do with sample size. No, because the sample size is small and p-values are easily affected by sample size.
No, because the sample size is small and p-values are easily affected by sample size.
When the results of an experiment can be applied to real-world conditions, that experiment is said to have: Ecological validity Factorial validity Content validity Criterion validity
Ecological validity
A randomized controlled trial (RCT) is often used to test? Efficacy of various types of intervention within a patient population Popularity of types of music Methods of data collection Versions of SPSS software
Efficacy of various types of intervention within a patient population
Other things being equal, compared to the paired-samples (or dependent) t-test, the independent t-test: Is less robust. Has less power to find an effect. Has more power to find an effect. Has the same amount of power, the data are just collected differently.
Has less power to find an effect.
Which of the following best describes the relationship between sample size and significance testing? In small samples only small effects will be deemed 'significant'. Large effects tend to be significant only in small samples. Large effects tend to be significant only in large samples. In large samples even small effects can be deemed 'significant'
In large samples even small effects can be deemed 'significant'
Which of the following t-tests has a different research design? Independent t-test Paired-samples t-test Matched-pairs t-test Dependent t-test
Independent t-test
Which measure of data distribution is presented as the 'box' in a box-whisker plot? Interquartile range Standard deviation Standard rrror of the mean Range
Interquartile range
The t-statistic: When significant, indicates an important finding. Is accurate only when using large samples. Is the standard deviation of the sampling distribution of a statistic. Is the ratio of the systematic variation (caused by the IV) to the unsystematic variation (not caused by the IV).
Is the ratio of the systematic variation (caused by the IV) to the unsystematic variation (not caused by the IV).
What do the error bars on a bar chart represent? The confidence interval round the mean. The standard error of the mean. The standard deviation of the mean. It can represent any of a, b or c, and the graph legend needs to always specify what the error bars show.
It can represent any of a, b or c, and the graph legend needs to always specify what the error bars show.
Why is the standard error important? It gives you a measure of how well your sample parameter represents the population value. It is unaffected by outliers. It is unaffected by the distribution of scores. It tells us the precise value of the variance within the population.
It gives you a measure of how well your sample parameter represents the population value.
In the above study, which statement is true? The type of alcohol could be a confounding variable. It is appropriate to analyse the results using a paired sample t-test. The experiment has two dependent variables. The experiment has two independent variables.
It is appropriate to analyse the results using a paired sample t-test.
A researcher randomized 75 children into three groups (25 per group). Each group was taught how to perform a basketball free throw using either a visual, aural or verbal learning style. The success of the learning style was determined by the number of points scored from ten attempts. Which of the following would be considered the independent variable? Number of successful free throw attempts Learning style of group Number of unsuccessful free throw attempts Both successful and unsuccessful free throw attempts
Learning style of group
How is a t-statistic calculated? Mean difference / standard error of the mean Mean difference / standard deviation Standard error of the mean / standard deviation Standard deviation / degrees of freedom
Mean difference / standard error of the mean
The discrepancy between the numbers used to represent something that we are trying to measure and the actual value of what we are measuring is called: Reliability The 'fit' of the model Variance Measurement error
Measurement error
Which measure of central tendency is presented in a box-whisker plot? Median Mean Mode Standard error of the mean
Median
Which of the following is not a form of t-test? Independent-samples t-test Paired-samples t-test One-sample t-test Mixed model t-test
Mixed model t-test
You work for a performance sports clothing company. Your CEO has just read a book on criticisms of the NHST and worries that all company data analysis is now flawed and will lead to huge financial losses. How might you reassure her? NHST does have its flaws but if we incorporate an examination of effect sizes into our analysis, we should be able to trust our research outputs. NHST does have its flaws but everyone else uses it, therefore we should. NHST is a flawless approach and the book was probably written by a disciple of the Bayesian approach. NHST is a flawless approach and we need to invest in more data analysts who are trained in it.
NHST does have its flaws but if we incorporate an examination of effect sizes into our analysis, we should be able to trust our research outputs.
Twenty-five percentile points is commonly referred to as a Quartile Interquartile range Quarter Range
Quartile
Which of the following does a box-whisker plot not display? The range The interquartile range The lower quartile The mean
The mean
You have income data for your entire customer database. Some of your clients are far wealthier than others. Which of the following do outliers least affect? The range The mean The median The standard deviation
The median
The median is always? The middle score when results are ranked in order of magnitude The most frequently occurring value in a data set The same as the mean Never the same as the mode
The middle score when results are ranked in order of magnitude
If my experimental hypothesis were 'Eating cheese before bed affects the number of nightmares you have', what would the null hypothesis be? Eating cheese is linearly related to the number of nightmares you have. Eating cheese before bed gives you more nightmares. The number of nightmares you have is not affected by eating cheese before bed. Eating cheese before bed gives you fewer nightmares.
The number of nightmares you have is not affected by eating cheese before bed.
A 95% confidence interval is: -The range of values of the statistic which we can be 5% confident contains a significant effect in the population. - The range of values of the statistic which probably contains the true value of the statistic in the population. -The range of values of the statistic that we can be 95% confident contains a significant effect in the population. -The range of values of the statistic which we can by 95% certain does not contain the true population effect.
The range of values of the statistic which probably contains the true value of the statistic in the population.
What does the standard error of the mean represent? The standard deviation of the sample means The standard deviation of the population mean The confidence intervals of the sample means The confidence intervals of the population mean
The standard deviation of the sample means
Which of the following statements is true?The standard deviation is calculated only from sample attributes. The standard error is a measure of central tendency. All of the above. The standard error is calculated solely from sample attributes.
The standard error is calculated solely from sample attributes.
If a test is valid, what does this mean? The test will give consistent results. The test has internal consistency. The test measures a useful construct or variable. The test measures what it claims to measure.
The test measures what it claims to measure.
Of what is the standard error a measure? The variability of scores in the population. The 'flatness' of the distribution of sample scores. The variability of sample estimates of a parameter. The variability in scores in the sample.
The variability of sample estimates of a parameter.
Two samples of data are collected and the sample means calculated. If the samples come from the same population, then: Their means should be roughly equal. Their means should differ significantly. The experiment is unreliable. The difference between the samples we have collected is likely to be larger than we would expect based on the standard error.
Their means should differ significantly.
What is the null hypothesis for the following question: Is there a relationship between heart rate and the number of cups of coffee drunk within the last 4 hours? There is no relationship between heart rate and the number of cups of coffee drunk within the last 4 hours. People who drink more coffee will have significantly higher heart rates. People who drink more coffee will have significantly lower heart rates. There will be a significant relationship between the number of cups of coffee drunk within the last 4 hours and heart rate.
There is no relationship between heart rate and the number of cups of coffee drunk within the last 4 hours.
Under a null hypothesis, a sample value yields a p-value of .015. Which of the following statements is true? This finding is statistically significant at the .01 level of significance. This finding is not statistically significant. This finding is statistically significant at the .001 level of significance. This finding is statistically significant at the .05 level of significance.
This finding is statistically significant at the .05 level of significance.
When might the independent t-test be used? One experimental condition and all participants used in that condition Two experimental conditions and all participants used in both conditions Two experimental conditions and different participants used in each condition None of the above
Two experimental conditions and different participants used in each condition
A researcher interested in the effects of interval training on VO2 max reported an increase following the intervention when, in reality, interval training has no effect on VO2 max. What type of error has occurred? Type I Type II Type IIA Type IIB
Type I
A researcher interested in the effects of interval training on VO2 max reported no significant increase following the intervention when, in reality, interval training leads to improvement in VO2 max. What type of error has occurred? Type I Type II Type IIA Type IIB
Type II
If you were researching a medical procedure that could potentially diagnose pancreatic cancer earlier than the procedures we have at the moment, what type of error should you be most concerned about? Type I Type II Type IIA Type IIB
Type II
A Type I error occurs when: The data we have typed into SPSS is different from the data collected. We conclude that there is an effect in the population when in fact there is not. We conclude that there is not an effect in the population when in fact there is. We conclude that the test statistic is significant when in fact it is not.
We conclude that there is an effect in the population when in fact there is not.
A Type II error occurs when : We conclude that there is not an effect in the population when in fact there is. We conclude that there is an effect in the population when in fact there is not. We conclude that the test statistic is significant when in fact it is not. The data we have typed into SPSS is different from the data collected.
We conclude that there is not an effect in the population when in fact there is.
A demand characteristic is: A personality trait that makes a participant likely to find an experiment too demanding. When a person responds in an experiment in a way that is consistent with their beliefs about how the experimenter would like them to behave. When the experimenter's behaviour affects the results of an experiment. A personality trait that affects the results of an experiment in an undesirable way.
When a person responds in an experiment in a way that is consistent with their beliefs about how the experimenter would like them to behave.
The 99% confidence interval usually is: Narrower than the 95% confidence interval. Wider than the 95% confidence interval. The same as the 95% confidence interval. A less precise estimate of the effect in the population than the 95% confidence interval.
Wider than the 95% confidence interval.