You are on page 1of 11

STATISTICAL TESTS | FINALS LESSON 09

PROCESS OF TESTING HYPOTHESIS

1. Develop null and alternative hypothesis

2. Establish alpha level (level of significance)

3. Choose appropriate test statistic

4. Compare p value

5. Decide to reject or not to reject null hypothesis

6. Interpret the results

P VALUE

• Probability value

• A measure of the strength of evidence against the null hypothesis

• Probability of getting the observed value of the test statistic, or a value with even greater evidence against
H0, if the null hypothesis is actually true

• Rule:

• _________ = reject null (statistically significant)

• _________ = do not reject the null (not statistically significant)

TYPES OF STATISTICAL TESTS

• Z Test

• T test

• ANOVA

• Chi-square

• Pearson Correlation

• Spearman Correlation

• Regression

• Wilcoxon signed rank test

• Mann-Whitney test

WHAT STATISTICAL TEST SHOULD I USE?

1. What type of data do you have?

2. How many samples do you have?

3. What is the test supposed to do or what is the purpose of the test?

SAN PEDRO COLLEGE | Medical Laboratory Science Department Page 1 of 11


STATISTICAL TESTS | FINALS LESSON 09

WHAT IS THE PURPOSE OF THE TEST?

SAN PEDRO COLLEGE | Medical Laboratory Science Department Page 2 of 11


STATISTICAL TESTS | FINALS LESSON 09

Z TEST AND T TEST

Z TEST

T TEST

SAN PEDRO COLLEGE | Medical Laboratory Science Department Page 3 of 11


STATISTICAL TESTS | FINALS LESSON 09

• SIMILAR TO THE STANDARD NORMAL DISTRIBUTION

• Bell-shaped

• Symmetric about the _________

• Mean, median and mode are equal to 0 and are located at the center of the distribution

• Curve never touches the _________

• DIFFERS TO THE STANDARD NORMAL DISTRIBUTION

• Variance is _________ than 1

• It is a family of curves based on the degree of freedom, which is a number related to sample size

• As the sample size _________, the t distribution approaches the normal distribution

• THREE VERSIONS

• Independent sample t-test which compares mean for two groups

• Paired sample t-test which compares means from the same group at different times

• One sample t-test which tests which tests the mean of a single group against a known mean

ONE SAMPLE T TEST SPSS

• PROBLEM STATEMENT

• According to the CDC, the mean height of adults ages 20 and older is about 66.5 inches (69.3
inches for males, 63.8 inches for females). Let's test if the mean height of our sample data is
significantly different than 66.5 inches using a one-sample t test.

• H0: _________
H1: _________

• where 66.5 is the CDC's estimate of average height for adults, and xHeight is the mean height of the
sample.

• BEFORE THE TEST

• Analyze > Descriptive Statistics > Descriptives

• Graphs > Legacy Dialogs > Histogram

• RUNNING THE TEST

• Click Analyze > Compare Means > One sample t test

SAN PEDRO COLLEGE | Medical Laboratory Science Department Page 4 of 11


STATISTICAL TESTS | FINALS LESSON 09

A. TEST VARIABLE: The variable whose mean will


be compared to the hypothesized population mean

B. TEST VALUE: The hypothesized population mean


against which your test variable(s) will be
compared

C. OPTIONS: Clicking Options will open a window


where you can specify the Confidence Interval
Percentage and how the analysis will
address Missing Values

A. TEST VALUE

B. T STATISTIC: calculated by dividing the mean difference (E) by the standard error mean

C. DF: degrees of freedom (df = n-1)

D. SIG. (2-TAILED): two tailed p-value corresponding to the test statistic

E. MEAN DIFFERENCE: difference between the observed sample mean and the expected mean

F. CONFIDENCE INTERVAL FOR THE DIFFERENCE

CONCLUSION:

 There is a significant difference in the mean height between the sample and the overall adult population
(p < .05)

 The average height of the sample is about 1.5 inches taller than the overall adult population average.

INDEPENDENT T TEST

• Unpaired sample t test

• Dependent variable: Continuous

• Independent variable: Binary (Two categorical, independent group)

• Should have independence of observation

• No significant outliers

• USE:

• Compare the means of two independent groups

• You do not know the population mean or standard deviation

SAN PEDRO COLLEGE | Medical Laboratory Science Department Page 5 of 11


STATISTICAL TESTS | FINALS LESSON 09

• You have two independent, separate samples

• PROBLEM STATEMENT

• In our sample dataset, students reported their typical time to run a mile, and whether or not they
were an athlete. Suppose we want to know if the average time to run a mile is different for athletes
versus non-athletes. This involves testing whether the sample means for mile time among athletes
and non-athletes in your sample are statistically different

• BEFORE THE TEST

• Analyze > Compare means > Means

• Analyze > Descriptives > Explore

• RUNNING THE TEST

• Analyze > Compare means > Independent Sample T test

A. LEVENE’S TEST FOR EQUALITY OF VARIANCE

• F is the test statistic of Levene’s test

• Sig. is the p value corresponding to this test statistic

• This tells us that we should look at the "Equal variances not assumed" row for the t test (and corresponding
confidence interval) results

SAN PEDRO COLLEGE | Medical Laboratory Science Department Page 6 of 11


STATISTICAL TESTS | FINALS LESSON 09

CONCLUSION:

 There was a significant difference in mean mile time between non-athletes and athletes

 The average mile time for athletes was 2 minutes and 14 seconds faster than the average mile time for
non-athletes.

MANN WHITNEY TEST

• non-parametric equivalent to the independent t-test

• Also known as Wilcoxon test for independent samples

• Dependent variable: _________

• Independent variable: _________

• USE:

• It is used to compare whether two groups containing different people are the same or not.

• Ranks all of the data and then compares the sum of the ranks for each group to determine whether
the groups are the same or not.

• PROBLEM STATEMENT

• Data contain the ratings of 3 car commercials by 18 respondents, balanced over gender and age
category. Our research question is whether men and women judge our commercials similarly.

• NULL HYPOTHESIS:

• BEFORE THE TEST

• Graphs > Legacy Dialogs > Histogram

• RUNNING THE TEST

• Analyze > Nonparametric tests > Legacy Dialogs > 2 independent samples

SAN PEDRO COLLEGE | Medical Laboratory Science Department Page 7 of 11


STATISTICAL TESTS | FINALS LESSON 09

• _________ method:

• means that p values are estimated based on the assumption that the data, given a sufficiently large
sample size, conform to a particular distribution

• _________ method:

• Although exact results are always reliable, some data sets are too large for the exact p value to be
calculated, yet don’t meet the assumptions necessary for the asymptotic method

• provides an unbiased estimate of the exact p value, without the requirements of the asymptotic
method

• _________:

• Can be performed quickly with sample sizes of less than 30

• Calculates the exact p value

CONCLUSION:

 Women rated the “Family Car” commercial more favorably than men (p = 0.001). The other two
commercials didn't show a gender difference (p > 0.10).

PAIRED T TEST

• Dependent variable: _________

• Independent variable: _________

• Assesses whether the mean difference between paired observations on a particular outcome is significantly
different from zero

• USE:

• When the data is paired or matched

SAN PEDRO COLLEGE | Medical Laboratory Science Department Page 8 of 11


STATISTICAL TESTS | FINALS LESSON 09

• Before/after measurements of the same variable

• Compare how a group of subjects perform under two different test conditions

• PROBLEM STATEMENT

• The sample dataset has placement test scores (out of 100 points) for four subject areas: English,
Reading, Math, and Writing. Suppose we are particularly interested in the English and Math
sections and want to determine whether English or Math had higher test scores on average. We
could use a paired t test to test if there was a significant difference in the average of the two tests.

• BEFORE THE TEST

• Analyze > Descriptive statistics > Descriptives

• Analyze > Descriptives > Explore

• RUNNING THE TEST

• Analyze > Compare means > Paired Sample T test

CONCLUSION:

 English and Math scores were weakly and positively correlated (r = 0.243, p < 0.001).

 There was a significant average difference between English and Math scores (t397 = 36.313, p < 0.001).

 On average, English scores were 17.3 points higher than Math scores (95% CI [16.36, 18.23]).

WILCOXON SIGNED RANK TEST

• non-parametric equivalent to the paired t-test

• Dependent variable: _________

• Independent variable: _________

• USE:

SAN PEDRO COLLEGE | Medical Laboratory Science Department Page 9 of 11


STATISTICAL TESTS | FINALS LESSON 09

• Compare two related samples, matched samples or repeated measurements on a single sample to
assess whether their population mean rank differ

• PROBLEM STATEMENT

• A car manufacturer had 18 respondents rate 3 different commercials for one of their cars. They first
want to know which commercial is rated best by all respondents.

• BEFORE THE TEST

• Graphs > Legacy Dialogs > Histogram

• RUNNING THE TEST

• Analyze > Nonparametric test > Legacy Dialogs > 2 Related samples

CONCLUSION:

 “A Wilcoxon Signed-Ranks test indicated that the “Family car” commercial (mean rank = 10.6) was rated
more favorably than the “Youngster car” commercial (mean rank = 4.0), Z = -3.2, p = 0.001.”

CHI SQUARE INDEPENDENCE TEST

• Non parametric test

• is a procedure for testing if two categorical variables are related in some population

• Both dependent and independent variable are _________

• USE:

• The null hypothesis is that there is no relationship/association between the two categorical
variables

SAN PEDRO COLLEGE | Medical Laboratory Science Department Page 10 of


11
STATISTICAL TESTS | FINALS LESSON 09

• Compares expected frequencies, assuming the null is true, with the observed frequencies from the
study

• ASSUMPTIONS:

• For a 2 by 2 table, all expected frequencies > 5

• For a larger table, all expected frequencies > 1 and no more than 20% of all cells may
have expected frequencies < 5

• PROBLEM STATEMENT

• A sample of 183 students evaluated some course. Apart from their evaluations, we also have their
genders and study majors. We'd now like to know: is study major associated with gender? And -if
so- how?

• RUNNING THE TEST

• Analyze > Descriptive Statistics > Crosstabs

CONCLUSION:

 We reject the null hypothesis that our variables are independent in the entire population.

• ADJUSTING TABLE

• Right click table > Edit Content > In Separate Window

• Pivoting trays > Drag and drop Statistics right underneath “What’s your gender?”

SAN PEDRO COLLEGE | Medical Laboratory Science Department Page 11 of


11

You might also like