One-Sample T-Test: Example 1: Mortgage Process Time
One-Sample T-Test: Example 1: Mortgage Process Time
One-Sample T-Test: Example 1: Mortgage Process Time
One-Sample t-Test
Example 1: Mortgage Process Time
Problem Data set
A faster loan processing time produces higher productivity Mortgage.MPJ
and greater customer satisfaction. A financial services
institution wants to establish a baseline for their process by Variable Description
estimating their mean processing time. They also want to
determine if their mean time differs from a competitor’s claim Loan Loan application number
of 6 hours. Hours Number of hours until customer receives notification
Data collection
A financial analyst randomly selects 7 loan applications and
manually calculates the time between loan initiation and when
the customer receives the institution’s decision.
Tools
• Descriptive Statistics
• 1-Sample t
• Normality Test
• Time Series Plot
• Individual Value Plot
4. Click OK.
Hypothesis testing
What is a hypothesis test Why use a hypothesis test
A hypothesis test uses sample data to test a hypothesis about Hypothesis testing can help answer questions such as:
the population from which the sample was taken. The
one-sample t-test is one of many procedures available for • Are turn-around times meeting or exceeding customer
expectations?
hypothesis testing in Minitab.
For example, to test whether the mean duration of a
• Is the service at one branch better than the service at another?
transaction is equal to the desired target, measure the duration For example,
of a sample of transactions and use its sample mean to
estimate the mean for all transactions. Using information from • On average, is a call center meeting the target time to answer
a sample to make a conclusion about a population is known customer questions?
as statistical inference. • Is the mean billing cycle time shorter at the branch with a new
billing process?
When to use a hypothesis test
Use a hypothesis test to make inferences about one or more
populations when sample data are available.
One-sample t-test
What is a one-sample t-test Why use a one-sample t-test
A one-sample t-test helps determine whether μ (the A one-sample t-test can help answer questions such as:
population mean) is equal to a hypothesized value (the test
mean). • Is the mean transaction time on target?
3. Click OK.
For example, the t-test results indicate that the sample mean
is 5.079 hours. The test answers the question, “If μ is equal to
6 hours, how likely is it to obtain a sample mean this different
(or even more different)?” The answer is given as a probability
value (P), which for this test is equal to 0.114.
Test statistic
The t-statistic (-1.85) is calculated as:
t = (sample mean – test mean) / SE Mean
What’s next
Check the assumption of normality.
3. Click OK.
Note When data are not normally distributed, you may be able to
transform them using a Box-Cox transformation or use a nonparametric
procedure such as the 1-sample sign test.
Sorting data
You can use Minitab’s Sort command to sort the data in Sort
ascending or descending order—numerically, alphabetically,
or by date. In this example, sort the data by loan application 1. Choose Data > Sort.
number, in ascending, or increasing, order. Sorting the data
by loan application number will put it in time order because 2. Under Column in Level 1, enter Loan.
the loan application numbers are assigned in increasing order 3. In Storage location for the sorted columns, select In the
by the system. Sorting the data chronologically makes it easy
original columns.
to plot the data over time and evaluate it for patterns or
trends. 4. Click OK.
Note Include all appropriate columns in the sorting step, to preserve
the connection between the columns of data.
4. Click OK.
What’s next
Calculate a confidence interval for the true population mean.
Confidence intervals
What is a confidence interval Why use a confidence interval
A confidence interval is a range of likely values for a population Confidence intervals can help answer many of the same questions
parameter (such as μ) that is based on sample data. For as hypothesis testing:
example, with a 95% confidence interval for μ, you can be 95%
confident that the interval contains μ. In other words, 95 out • Is μ on target?
of 100 intervals will contain μ upon repeated sampling. • How much error exists in an estimate of μ?
Note A confidence interval does not represent 95% of the data; this is
a common misconception.
Final considerations
Summary and conclusions
According to the t-test and the sample data, you fail to reject
the null hypothesis at the 0.05 α-level. In other words, the
data do not provide sufficient evidence to conclude the mean
processing time is significantly different from 6 hours.
The normality test and the time series plot indicate that the
data meet the t-test’s assumptions of normality and
randomness.
The 95% confidence interval indicates the true value of the
population mean is between 3.859 hours and 6.298 hours.
Final considerations
Hypotheses Assumptions
A hypothesis test always starts with two opposing hypotheses. Each hypothesis test is based on one or more assumptions about
the data being analyzed. If these assumptions are not met, the
The null hypothesis (H0): conclusions may not be correct.
• Usually states that some property of a population (such The assumptions for a one-sample t-test are:
as the mean) is not different from a specified value or from
a benchmark. • The sample must be random.
• Is assumed to be true until sufficient evidence indicates • Sample data must be continuous.
the contrary. • Sample data should be normally distributed (although this
• Is never proven true; you simply fail to disprove it. assumption is less critical when the sample size is 30 or more).
The alternative hypothesis (H1): The t-test procedure is fairly robust to violations of the normality
assumption, provided that observations are collected randomly
• States that the null hypothesis is wrong. and the data are continuous, unimodal, and reasonably symmetric
(see [1]).
• Can also specify the direction of the difference.
Confidence interval
Significance level
The confidence interval provides a likely range of values for μ (or
Choose the α-level before conducting the test. other population parameters).
• Increasing α increases the chance of detecting a difference, You can conduct a two-tailed hypothesis test (alternative
but it also increases the chance of rejecting H0 when it is hypothesis of ≠) using a confidence interval. For example, if the
actually true (a Type I error). test value is not within a 95% confidence interval, you can reject
H0 at the 0.05 α-level. Likewise, if you construct a 99% confidence
• Decreasing α decreases the chance of making a Type I interval and it does not include the test mean, you can reject H0
error, but also decreases the chance of correctly detecting at the 0.01 α-level.
a difference.