HYPOTHESIS

TESTING

Dr HARITIKA CHHATWAL
Probability sampling methods
- Probability sampling means that every member of the population has a chance of being selected. It is mainly
used in quantitative research. If you want to produce results that are representative of the whole population,
probability sampling techniques are the most valid choice.
1. Simple random sampling

- In a simple random sample, every member of the population has an equal chance of being selected.
Your sampling frame should include the whole population.

- To conduct this type of sampling, you can use tools like random number generators or other techniques
that are based entirely on chance.

- Example: Simple random samplingYou want to select a simple random sample of 1000 employees of a
social media marketing company. You assign a number to every employee in the company database
from 1 to 1000, and use a random number generator to select 100 numbers
- .2. Systematic sampling

- Systematic sampling is similar to simple random sampling, but it is usually slightly easier to conduct. Every
member of the population is listed with a number, but instead of randomly generating numbers, individuals are
chosen at regular intervals.

- Example: All employees of the company are listed in alphabetical order. From the first 10 numbers, you
randomly select a starting point: number 6. From number 6 onwards, every 10th person on the list is selected (6,
16, 26, 36, and so on), and you end up with a sample of 100 people.If you use this technique, it is important to
make sure that there is no hidden pattern in the list that might skew the sample. For example, if the HR database
groups employees by team, and team members are listed in order of seniority, there is a risk that your interval
might skip over people in junior roles, resulting in a sample that is skewed towards senior employees.
- 3. Stratified sampling

- Stratified sampling involves dividing the population into subpopulations that may differ in important
ways. It allows you draw more precise conclusions by ensuring that every subgroup is properly
represented in the sample.

- To use this sampling method, you divide the population into subgroups (called strata) based on the
relevant characteristic (e.g., gender identity, age range, income bracket, job role).

- Based on the overall proportions of the population, you calculate how many people should be sampled
from each subgroup. Then you use random or systematic sampling to select a sample from each subgroup.

- Example: The company has 800 female employees and 200 male employees. You want to ensure that the
sample reflects the gender balance of the company, so you sort the population into two strata based on
gender. Then you use random sampling on each group, selecting 80 women and 20 men, which gives you
a representative sample of 100 people.
4. Cluster sampling

- Cluster sampling also involves dividing the population into subgroups, but each subgroup should have
similar characteristics to the whole sample. Instead of sampling individuals from each subgroup, you
randomly select entire subgroups.

- If it is practically possible, you might include every individual from each sampled cluster. If the clusters
themselves are large, you can also sample individuals from within each cluster using one of the techniques
above. This is called multistage sampling.

- Example: The company has offices in 10 cities across the country (all with roughly the same number of
employees in similar roles). You don’t have the capacity to travel to every office to collect your data, so you
use random sampling to select 3 offices – these are your clusters.
Non-probability sampling methods

- In a non-probability sample, individuals are selected based on non-random criteria, and not every
individual has a chance of being included.

- This type of sample is easier and cheaper to access, but it has a higher risk of sampling bias. That
means the inferences you can make about the population are weaker than with probability samples, and
your conclusions may be more limited. If you use a non-probability sample, you should still aim to
make it as representative of the population as possible.

- Non-probability sampling techniques are often used in exploratory and qualitative research. In these
types of research, the aim is not to test a hypothesis about a broad population, but to develop an initial
understanding of a small or under-researched population.
- 1. Convenience sampling

- A convenience sample simply includes the individuals who happen to be most accessible to the
researcher.

- This is an easy and inexpensive way to gather initial data, but there is no way to tell if the sample is
representative of the population, so it can’t produce generalizable results. Convenience samples are at risk
for both sampling bias and selection bias.

- Example: Convenience sampling You are researching opinions about student support services in your
university, so after each of your classes, you ask your fellow students to complete a survey on the topic.
This is a convenient way to gather data, but as you only surveyed students taking the same classes as you
at the same level, the sample is not representative of all the students at your university.
- 2. Voluntary response sampling

- Similar to a convenience sample, a voluntary response sample is mainly based on ease of access.
Instead of the researcher choosing participants and directly contacting them, people volunteer
themselves (e.g. by responding to a public online survey).

- Voluntary response samples are always at least somewhat biased, as some people will inherently be
more likely to volunteer than others, leading to self-selection bias.

- Example: You send out the survey to all students at your university and a lot of students decide to
complete it. This can certainly give you some insight into the topic, but the people who responded are
more likely to be those who have strong opinions about the student support services, so you can’t be
sure that their opinions are representative of all students.
- 3. Purposive sampling

- This type of sampling, also known as judgement sampling, involves the researcher using their
expertise to select a sample that is most useful to the purposes of the research.

- It is often used in qualitative research, where the researcher wants to gain detailed knowledge about a
specific phenomenon rather than make statistical inferences, or where the population is very small
and specific. An effective purposive sample must have clear criteria and rationale for inclusion.
Always make sure to describe your inclusion and exclusion criteria and beware of observer
bias affecting your arguments.

- Example: You want to know more about the opinions and experiences of disabled students at your
university, so you purposefully select a number of students with different support needs in order to
gather a varied range of data on their experiences with student services.
- 4. Snowball sampling

- If the population is hard to access, snowball sampling can be used to recruit participants via other
participants. The number of people you have access to “snowballs” as you get in contact with more people.
The downside here is also representativeness, as you have no way of knowing how representative your
sample is due to the reliance on participants recruiting others. This can lead to sampling bias.

- Example: You are researching experiences of homelessness in your city. Since there is no list of all
homeless people in the city, probability sampling isn’t possible. You meet one person who agrees to
participate in the research, and she puts you in contact with other homeless people that she knows in the
area.
- 5. Quota sampling

- Quota sampling relies on the non-random selection of a predetermined number or proportion of units.
This is called a quota.

- You first divide the population into mutually exclusive subgroups (called strata) and then recruit
sample units until you reach your quota. These units share specific characteristics, determined by you
prior to forming your strata. The aim of quota sampling is to control what or who makes up your
sample.

- Example: You want to gauge consumer interest in a new produce delivery service in Boston, focused
on dietary preferences. You divide the population into meat eaters, vegetarians, and vegans, drawing a
sample of 1000 people. Since the company wants to cater to all consumers, you set a quota of 200
people for each dietary group. In this way, all dietary preferences are equally represented in your
research, and you can easily compare these groups.You continue recruiting until you reach the quota of
200 participants for each subgroup.
TRANSFORMING VARIABLES :
- data transformation is reverse scoring

- for instance, the perceived inequity measure of the Excelsior Enterprises case.

- Perceived inequity is measured by five survey items:

- (1) “I invest more in my work than I get out of it”; (reversed)

- (2) “I exert myself too much considering what I get back in return”; (reversed)

- (3) “For the efforts I put into the organization, I get much in return”

- (4) “If I take into account my dedication, the organization ought to give me a better practical training”; (reversed) and

- (5) “In general, the benefits I receive from the organization outweigh the effort I put in”

- For the first, second, and fourth items, a score indicating high agreement would be negative, but for the third and fifth
questions, a score indicating high agreement would be positive.

- NOTE : To maintain consistency in the meaning of a response, the first, second, and fourth items have to be reverse scored
(note that we are measuring equity and not inequity). In this case, a 5 (“I completely agree”) would be transformed to a 1
(“I completely disagree”), a 4 to a 2, and so forth
Coding the responses
- In the Excelsior Enterprises questionnaire, we have 22 items measuring

 perceived equity,

 job enrichment,
 burnout,
 job satisfaction, and
 intention to leave, and

- Since all the above 22 are scale items

- The responses of this particular employee (participant #1 in the data file) to the first 22 questions can be coded by using the actual number
circled by the respondent (1, 2, 3, 1, 4, 5, 1, 3, 3, etc.).

- There are

 six demographic variables.

- For instance, tenure is a special case, because it is a two‐category variable. It is possible to use a coding approach that assigns a 1 = part‐
time and a 2 = full‐time. However, using 0 = part‐time and 1 = full‐time (this is called dummy coding) is by far the most popular and
recommended approach because it makes our lives easier in the data analysis stage. Hence, we code tenure (full‐time) with 1 for participant
#1. Work shift (third shift) can be coded 3, department (production) 2, and age 54. Gender can be coded 0 (male) Finally, education (less
than high school) can be coded 1.
Non Responses

- At this stage you should also think about how you want to code nonresponses. Some researchers leave nonresponses blank,
others assign a “9,” a “99” or a “.” All the approaches are fine, as long as you code all the nonresponses in the same way.
Human errors can occur while coding. At least 10% of the coded questionnaires should therefore be checked for
coding accuracy. Their selection may follow a systematic sampling procedure. That is, every nth form coded could be
verified for accuracy. If many errors are found in the sample, all items may have to be checked.
Data transformation

- Perceived inequity is measured by five survey items:

- (1) “I invest more in my work than I get out of it”;

- (2) “I exert myself too much considering what I get back in return”;

- (3) “For the efforts I put into the organization, I get much in return” (reversed);

- (4) “If I take into account my dedication, the organization ought to give me a better practical training”; and

- (5) “In general, the benefits I receive from the organization outweigh the effort I put in” (reversed).

- For the first, second, and fourth items, a score indicating high agreement would be negative, but for the third and fifth questions, a score
indicating high agreement would be positive. To maintain consistency in the meaning of a response, the first, second, and fourth items have to be
reverse scored (note that we are measuring equity and not inequity). In this case, a 5 (“I completely agree”) would be transformed to a 1 (“I completely
disagree”), a 4 to a 2, and so forth.

- For instance, because five items have been used to measure the concept “perceived equity”, a new “perceived equity” score has to be calculated
from the scores on the five individual items (but only after items 1, 2, and 4 have been reverse coded).

- This involves calculating the summed score (per case/participant) and then dividing it by the number of items (five in this case). For example, our
employee #1 has circled, respectively, 1, 2, 3, 1, and 4 on the five participation in decision‐making questions; his (employee #1 is a man) scores on the
items, once items 1, 2, and 4 have been reverse coded, are 5, 4, 3, 5, and 4. The combined score on perceived equity would be 5 +4 +3 +5 +4 =21/ 5
=4.2 ). This combined score is included in a new column in SPSS/Excel
REGRESSION IN EXCEL :https://www.youtube.com/watch?v=e6PLpuuk8Eo
SUPPOSE SME Growth is a function of risk taking and innovativeness
Frequencies

- Suppose Excelsior Enterprises sample

- Job enrichment was measured using a four-item scale,namely,

1. “My job is quite simple and repetitive” (reversed),

2. “My job requires me to use a number of complex or higher-level skills,”
3. “My job requires a lot of cooperative work with other
people, and
4. “My job itself is not very significant or important in the broader scheme of things.

- ”Perceived equity was measured using a five-item scale comprising the following statements:

1. “I invest more in my work than I get out of it,”

2. “I exert myself too much considering what I get back in return,”
3. “For the efforts I put into the organization ,I get much in return,”
4. “If I take into account my dedication, the company ought to give me better training,” and
5. “In general, the benefits I receive from the organization outweigh the effort I put into it.”
-
- Responses for both job enrichment and perceived equitywere requested on a 5-point
scale from “I agree completely” (5)to “I disagree completely” (1).

- The Burnout Measure: short version (Pines, 2005) wasused to study the burnout
experience. It comprised a ten-itemscale—

1. “tired,”
2. “disappointed with people,”
3. hopeless,”
4. “trapped,”
5. “helpless,”
6. “depressed,”
7. “physically weak/sickly,”
8. “worthless or like a failure,”
9. “sleep difficulties,” and
10.“I have had it.”
- Responses were on a 5-point scale from “always” (5) to “never” (1).

- Job satisfaction, a six-item scale was used,which included statements like

1. “respect and fair treatment from the boss,”

2. “getting along well with most of my co-workers,”
3. “opportunity for personal growth and development,”
4. “feeling of worthwhile accomplishment,”
5. “participation in determining methods, procedures and goals,” and
6. “feeling of job security.”

7. Responses were given on a 5-point scale ranging from “not at all” (1) to “very much” (5).
- Intention to quit was measured using a single-item scale,

1. “with what level of certainty do you intend to leave thisorganization within the next year?”

- The responses ranged from “very certain” (5) to “not at all certain” (1).
It may be seen therefrom that the greatest number of individuals in the sample came from the production
department (28.1%), followed by the sales department (25.3%). Only three individuals (1.7%) came from
public relations, and five individuals each from the finance, maintenance, and accounting departments
(2.9% from each). The low numbers in the sample in some of the departments are a function of the total
population (very few members) in those departments.
it was found that 79.9% of the respondents were men and 20.1% women; about 62% worked the first shift,
20% the second shift, and 18% the third shift. About 16% of the respondents
Bar charts and pie charts
Frequencies can also be visually displayed as bar charts, histograms, or pie charts. Bar charts,
histograms, and pie charts help us to understand our data.
Measures of central tendency and dispersion
Mean

- to estimate the raw materials inventory, all that the manager might want to know is how many units per
month, on average, the department has been producing over the past six months. This measure of central
tendency – that is, the mean – might offer the manager a good idea of the quantity of materials that need to be
stocked.

- The median The median is the central item in a group of observations when they are arrayed in either an
ascending or a descending order.

- The mode : It can be signified by the most frequently occurring phenomenon. For instance, in a department
where there are 10 white women, 24 white men, 3 African American women, and 2 Asian women, the most
frequently occurring group – the mode – is the white men.
- Measures of dispersion: Two sets of data might have the same mean, but the dispersions could be
different. For example, if Company A sold 30, 40, and 50 units of a product during the months of April,
May, and June, respectively, and Company B sold 10, 40, and 70 units during the same period, the average
units sold per month by both companies is the same – 40 units – but the variability or the dispersion in the
Co B is larger.

- Range: The range is between 30 and 50 for Company A (a dispersion of 20 units), while the range is
between 10 and 70 units (a dispersion of 60 units) for Company B.

- Variance: the variance is much larger in Company B than Company A. This makes it more difficult for the
manager of Company B to estimate how many goods to stock than it is for the manager of Company A.
- Standard deviation: In the case of the above two companies, the standard deviation for Companies A
and B would be √66.7 and √600 or 8.167 and 24.495, respectively

- Other measures of dispersion: When the area of observations is divided into 100 equal parts, there
are 99 percentile points. Any given score has a probability of 0.01 that it will fall in any one of those
points. If John’s score is in the 16th percentile, it indicates that 84% of those who took the exam scored
better than he did, while 15% did worse.

- For instance, telephone companies can compare long‐distance charges of customers in several areas by
taking samples of customer bills from each of the cities to be compared. By plotting the first and third
quartiles and comparing the median and the spread, they can get a good idea of where billings tend to
be highest, to what extent customers vary in the frequency of use of long‐distance calls, and so on. This
is done by creating a box‐and‐whisker plot for each area. The box‐and‐whisker plot is a graphic device
that portrays central tendency, percentiles, and variability. A box is drawn, extending from the first to
the third quartile, and lines are drawn from either side of the box to the extreme scores, as shown in
Figure 14.6(a). Figure 14.6(b) has the median represented by a dot within each box.
- VIMP FOR THE REPORT

- EXCELSIOR ENTERPRISES: HYPOTHESIS TESTING

- The following hypotheses were generated for this study, as stated earlier:

- H1 : Job enrichment has a negative effect on intention to leave.

- H2 : Perceived equity has a negative effect on intention to leave.

- H3 : Burnout has a positive effect on intention to leave.

- H4 : Job satisfaction mediates the relationship between job enrichment, perceived equity, and burnout on intention to
leave.

- To test the hypothesis that job satisfaction mediates the effect of perceived justice, burnout, and job enrichment on
employees’ intentions.

- Model 1= Dependant Variable= job satisfaction

- Independent Variable=perceived justice, burnout, and job enrichment;

- Model 2= Dependant Variable= intention to leave

- Independent Variable= perceived justice, burnout, and job enrichment; and

- Model 3= Dependant Variable= employees’ intentions to leave

- Independent Variable= perceived justice, burnout, job enrichment, and job satisfaction.

- The R‐square of the first regression model (model 1) was 0.172 and the model was statistically
significant. In this model perceived equity, burnout and job enrichment were all significant predictors
of job satisfaction. The R‐square of the second regression model (model 2) was 0.264 and this model
was also statistically significant. Model 2, as depicted in Table 15.5 indicated that perceived equity and
job enrichment affected employees’ intention to leave, whereas burnout did not.
- The R‐square of the last model (model 3) was 0.577 and again the model was statistically significant.
In this model, job satisfaction was a significant predictor of intention to leave.

- The descriptive results, reflect that the mean on perceived equity is rather low (2.44 on a five‐point
scale). The mean of job enrichment is clearly higher (3.49 on a five‐point scale), but it is still below
the standards of the company.

- Hence, if retention of employees is a top priority for the president, it is important to formulate
policies and practices that help to enhance equity perceptions and to redesign jobs in such a way that
they are more challenging to the employees . Whatever is done to improve employees ’ perceptions of
equity and to enrich the jobs of employees will improve job satisfaction and thus help employees to
think less about leaving and induce them to stay.
Relationships between variables
1. Correlation

- we would like to see the nature, direction, and significance of the bivariate relationships of the variables used in the
study (i.e., the relationship between any two variables among the variables tapped in the study)

- Nonparametric tests: are available to assess the relationship between variables measured on a nominal or an ordinal
scale. Spearman’s rank correlation and Kendall’s rank correlation are used to examine relationships between two
ordinal variables. A correlation matrix is used to examine relationships between interval and/or ratio variables.
Relationship between two nominal variables:
χ 2 test

- Relationship between two nominal variables or whether they are independent of each other. As examples:

- (1) Is viewing a television advertisement of a product (yes/no) related to buying that product by individuals (buy/don’t buy)?

- (2) Is the type of job done by individuals (white‐collar job/ blue ‐collar job) a function of the color of their skin (white/nonwhite)?

- • indicates whether or not the observed pattern is due to chance.

- • nonparametric tests are used when normality of distributions cannot be assumed as in nominal or ordinal data.

- The null hypothesis Ho =There is no significant relationship between two variables (color of skin and nature of the job), and the
H1= There is a significant relationship color of skin and nature of the job

- Chi‐square statistic is associated with the degrees of freedom (df), which denote whether or not a significant relationship exists
between two nominal variables. The number of degrees of freedom is one less than the number of cells in the columns and rows.
If there are four cells (two in a column and two in a row), then the number of degrees of freedom would be
- one might be interested to know if four groups of employees – production, sales, marketing, and R&D
personnel – react to a policy in four different ways (i.e., with no interest at all, with mild interest,
moderate interest, and intense interest). Here, the 2 value for the test of independence is generated by
cross‐tabulating the data in 16 cells – that is, classifying the data in terms of the four groups of
employees and the four categories of interest. The degrees of freedom here will be

- Fisher exact probability test and the Cochran Q test are used to determine the relationship between
two nominally scaled variables.
1. Correlations
- correlation matrix will indicate the direction, strength, and significance of the bivariate relationships
among all the variables that were measured at an interval or ratio level
- data on two variables – price and sales – for two different products. The volume of sales at every
price level can be plotted for each product
 - Step 1
(a) correlation = −1.0 and +1.0,

(b) correlation found between two variables is significant or not (i.e., if it has occurred solely by chance
or if there is a high probability of its actual existence). As we know, a significance of p 0 05 . is the
generally accepted conventional level in social science research. This indicates that 95 times out of
100, we can be sure that there is a true or significant correlation between the two variables, and
there is only a 5% chance that the relationship does not truly exist. If there is a correlation of 0.56
(denoted as r 0 56 . ) between two variables A and B, with p 0 01 . , then we know that there is a positive
relationship between the two variables and the probability of this not being true is 1% or less.
(c) We don’t know causality, but we do know that the two variables are associated with each other. Thus, a
hypothesis that postulates a significant positive (or negative) relationship between two variables can be
tested by examining the correlation between the two
(d) interval‐ and ratio‐scaled variables-Pearson correlation coefficient
- ordinal scale-Spearman Rank or the Kendall’s tau coefficients
- TESTING THE GOODNESS OF MEASURES

- Reliability: Consistency indicates how well the items measuring a concept hang together as a set.

- Cronbach’s alpha is a reliability coefficient that indicates how well the items in a set are positively correlated to one
another. Cronbach’s alpha is computed in terms of the average intercorrelations among the items measuring the concept.
The closer Cronbach’s alpha is to 1, the higher the internal consistency reliability.

 reliabilities less than 0.60 = poor,

 those in the 0.70 range= acceptable, and
 those over 0.80 good

 Cronbach’s alpha test for job enrichment

- If, however, our Cronbach’s alpha was too low (under 0.60) then we could use this table to find out which of the items
would have to be removed from our measure to increase the inter‐item consistency.

- In case our Cronbach’s alpha was too low (under 0.60) then we could use this table to find out which of the items would
have to be removed from our measure to increase the inter‐item consistency. Note that, usually, taking out an item,
although improving the reliability of our measure, affects the validity of our measure in a negative way
DESCRIPTIVE STATISTICS PART 2

- Descriptive statistics such as maximum, minimum, means, standard deviations, and variance can now be obtained for the
multi‐item, interval‐scaled independent and dependent variables.

- A correlation matrix can also be obtained to examine how the variables in our model are related to each other

- This will help us to answer important questions such as:

- ● How big is the problem? In other words, to what extent are the employees of Excelsior Enterprises inclined to leave?
What is the average inclination to leave?

- ● What is the nature of the problem? Compare, for instance, the histograms provided in Figure 14.8. The average
Intention To Leave(ITL) is the same in both cases. However, the graphs show us that in the first hypothetical histogram
ITL is "fairly normally" distributed.1 In the second hypothetical histogram, the distribution is clearly not normal. In
fact, it looks bimodal (with two peaks indicative of two modes). The first distribution suggests that most of the
respondents are neither bent on leaving nor staying. The bimodal distribution, on the other hand, suggests that one group
of employees is not inclined to leave at all, whereas another group is determined to leave the organization.2

-
HYPOTHETICAL HISTOGRAM ON INTENTION TO LEAVE

The distribution is clearly not normal. Infact, it looks

the first hypothetical histogram ITL is "fairly
bimodal (with two peaks indicative of two modes). The
normally" distributed. bimodal distribution, on the other hand, suggests that one
The first distribution suggests that most of the group of employees is not inclined to leave at all,
respondents are neither bent on leaving nor whereas another group is determined to leave the
staying. organization
Descriptive statistics will also help us to answer the following questions:

- ● Are the employees satisfied with their jobs?

- ● What are the employees’ perceptions on job enrichment?

- ● How many employees have which degrees of burnout?

- ● Is there much variance in the extent to which employees perceive the relationship with the company as equitable?

- ● What are the relationships between perceived equity, burnout, job enrichment, job satisfaction, and intention to leave?

- Descriptive statistics such as maximum, minimum, means, standard deviations, and variance were obtained for the
interval‐scaled independent and dependent variables in the Excelsior Enterprises study. The results are shown in Below.
It may be mentioned that all variables except ITL were tapped on a five‐point scale. ITL was measured on a four‐
point scale
For ITL, it may be seen that the mean of 2.59 on a four‐point scale for ITL indicates
that Excelsior Enterprises has a problem with regard to turnover. The minimum of 1
reveals that there are some employees who do not intend to leave at all, and the
maximum of 4 reveals that some are seriously considering leaving.
 Job satisfaction is about average (2.91 on a five‐point scale).

The mean on perceived equity is rather low (2.44 on a five‐point scale), as is the mean on experienced burnout (2.57).
Finally, the job is perceived as somewhat enriched (3.49).
Table also points out that the variance for all the variables is rather high, indicating that participants’ answers are
not always very close to the mean on all the variables.
This table shows that a large group of employees seriously considers leaving Excelsior Enterprises!
Testing our hypotheses will improve our understanding of why employees consider leaving Excelsior Enterprises and
will provide us with useful tools to reduce employees’ intentions to leave the company.
The Pearson correlation matrix obtained for the five interval‐scaled variables.
The intention to leave is, as would be expected, significantly negatively correlated to job satisfaction, perceived
equity, and job enrichment.
- That is, the intention to leave is low if job satisfaction and equitable treatment are experienced, and the
job is enriched.

- However, when individuals experience burnout (physical and emotional exhaustion), their intention
to leave does not increase (this relationship is not significant)

- Job satisfaction is positively correlated to perceived equity and an enriched job and negatively
correlated to burnout and ITL. These correlations are all in the expected direction.

- Note : The correlations between the independent variables does not exceed 0.272 for this sample. This
is an important finding, because if correlations between the independent variables were very high (say,
0.75 and above), we might run into a collinearity problem
Quantitative data analysis: Hypothesis testing
- 1. State the null and the alternate hypotheses.

- 2. Determine the level of significance desired (p 0 05 , or more, or less).

- 3. Choose the appropriate statistical test depending on the type of scales that have been used (nominal,
ordinal, interval, or ratio).

- 4. See if the output results from computer analysis indicate that the significance level is met. When the
resultant value is larger than the critical value, the null hypothesis is rejected, and the alternate accepted. If the
calculated value is less than the critical value, the null hypothesis is accepted and the alternate hypothesis
rejected.
TYPE I ERRORS, TYPE II ERRORS, AND STATISTICAL POWER

- The null hypothesis is presumed true until statistical evidence, in the form of a hypothesis test, indicates otherwise. The required statistical
evidence is provided by inferential statistics, such as regression analysis or MANOVA. Inferential statistics help us to draw conclusions (or to
make inferences) about the population from a sample.There are two kinds of errors (or two ways in which a conclusion can be incorrect),
classified as type I errors and type II errors.

 A type I error- alpha (α), is the probability of rejecting the null hypothesis when it is actually true.

- In the Excelsior, a type I error would occur if we concluded, based on the data, that burnout affects intention to leave when, in fact, it does
not. The probability of type I error, also known as the significance level, is determined by the researcher. Typical significance levels in
business research are 5% (<0.01)
 A type II error, - beta (β), is the probability of failing to reject the null hypothesis given that the alternate hypothesis is actually true; e.g.,
concluding, based on the data, that burnout does not affect intention to leave when, in fact, it does.
- The probability of type II error is inversely related to the probability of type I error:
- the smaller the risk of one of these types of error, the higher the risk of the other type of error.
 A third important concept in hypothesis testing is statistical power (1 − β). Statistical power, or just power, is the probability of correctly
rejecting the null hypothesis. In other words, power is the probability that statistical significance will be indicated if it is present

- Univariate statistical techniques - two‐variable relationships.:For instance, if you want to examine the effect of gender on the
number of candy bars that students eat per week, univariate statistics are appropriate. If, on the other hand, you are interested in the relationships
between many variables, such as in the Excelsior Enterprises case, multivariate statistical techniques are required.
Testing a hypothesis about a single mean
- The one sample t ‐test is used to test the hypothesis that the mean of the population from which a sample is drawn is equal
to a comparison standard

- you have read that the average student studies 32 hours a week. From what you have observed so far, you think that
students from your university (the population from which your sample will be drawn) study more. Therefore, you ask 20
class mates how long they study in an average week. The average study time per week turns out to be 36.2 hours, 4
hours and 12 minutes more than the study time of students in general. The question is: is this a coincidence?

- H 0 : The number of study hours of students from our university is equal to the number of study hours of students in
general.

- The alternate hypothesis:

- H1 : The number of study hours of students from our university differs from the number of study hours of students in
general.
- The way to decide whether there is a significant difference between students from your university and students in general
depends on three aspects: the value of the sample mean (36.2 hours);

- the value of the comparison standard (32 hours);

- and the degree of uncertainty concerning how well the sample mean represents the population mean (the standard error of
the sample mean
If there would be two observations for each employee, one before the training and one after the training. We
would use a paired samples t‐test to test the null hypothesis that the average of the differences between the
before and after measure is zero
The Wilcoxon signed‐rank test is a nonparametric test for examining significant differences between two related
samples or repeated measurements on a single sample. It is used as an alternative to a paired samples t‐test when the
population cannot be assumed to be normally distributed.
McNemar ’ s test is a nonparametric method used on nominal data. It assesses the significance of the difference between
two dependent samples when the variable of interest is dichotomous. It is used primarily in before− after studies to test for
an experimental effect.
The cells of Table 15.2 can be represented by the letters a, b, c, and d. The totals across rows and columns are marginal
totals (a + b, c + d, a + c, and b + d). The grand total is represented by n, as shown in Table 15.3. McNemar’s test is a rather
straightforward technique to test marginal homogeneity. Marginal homogeneity refers to equality (or the lack of a
significant difference) between one or more of the marginal row totals and the corresponding marginal column totals.

Marginal homogeneity would mean there was no effect of the treatment. In this case it would mean that the new training
method would not affect the performance of athletes.
Note that if b and/or c are small ( b + c < 20) then χ 2 is not approximated by the chi ‐square distribution. Instead a sign test
should be used.
Testing hypotheses about two unrelated means

- Interested to know whether two groups are different from each other on a particular interval‐scaled or ratio‐scaled
variable of interest.
- Examples :

 Would men and women press their case for the introduction of flextime at the workplace to the same extent, or would their
needs be different?
 Do MBAs perform better in organizational settings than business students with only a bachelor’s degree?
 Do individuals in urban areas have a different investment pattern for their savings than those in semi‐urban areas?
 Do CPAs perform better than non‐CPAs in accounting tasks?

- Independent samples t ‐test is carried out to see if there are any significant differences in the means for two groups in the
variable of interest.

- That is, a nominal variable that is split into two subgroups (e.g., smokers and nonsmokers; employees in the marketing
department and those in the accounting department; younger and older employees) is tested to see if there is a significant mean
difference between the two split groups on a dependent variable, which is measured on an interval or ratio scale (for instance,
extent of wellbeing; pay; or comprehension level).
Testing hypotheses about several means
- Whereas the (independent samples) t‐ test indicates whether or not

- There is a significant mean difference in a dependent variable between two groups, an analysis of variance
( ANOVA ) helps to examine the significant mean differences among more than two groups on an interval or ratio‐
scaled dependent variable.

- For example, is there a significant difference

 In the amount of sales by the following four groups of salespersons: those who are sent to training schools; those who
are given on‐the‐job training during field trips; those who have been tutored by the sales manager; and those who
have had none of the above?
 Or is the rate of promotion significantly different for those who have assigned mentors, choose their own mentors,
and have no mentors in the organizational system?
- The results of ANOVA show whether or not the means of the various groups are significantly different from one
another, as indicated by the F statistic. The F statistic shows whether two sample variances differ from each other
or are from the same population.

- When significant mean differences among the groups are indicated by the F statistic, there is no way of knowing
from the ANOVA results alone where they lie; that is, whether the significant difference is between Groups A and
B, or between B and C, or A and C, and so on.

- However, several tests, such as Scheffe’s test, Duncan Multiple Range test, Tukey’s test, and
Student−Newman−Keul’s test are available and can be used, as appropriate, to detect where exactly the mean
differences lie.
Regression analysis:

- Simple regression analysis is used in a situation where one independent variable is hypothesized to affect one
dependent variable.

- For instance, assume that we propose that the propensity to buy a product depends only on the perceived quality of
that product. In this case we would have to gather information on perceived quality and propensity to buy a product.
We could then plot the data to obtain some first ideas on the relationship between these variable
The coefficient of determination, R 2 , provides information about the goodness of fit of the regression model: it is a
statistical measure of how well the regression line approximates the real data points. R 2 is the percentage of
variance in the dependent variable that is explained by the variation in the independent variable. If R 2 is 1, the
regression model using perceived quality perfectly predicts propensity to buy.
- Multiple Regression Analysis: more than one independent variable to explain variance in the dependent
variable. Example: that a researcher believes that the variance in performance can be explained by four
independent variables, A, B, C, and D (say, pay, task difficulty, supervisory support, and organizational culture).

- When these variables are jointly regressed against the dependent variable in an effort to explain the variance in
it, the sizes of the individual regression coefficients indicate how much an increase of one unit in the
independent variable would affect the dependent variable, assuming that all the other independent variables
remain unchanged.
Other multivariate tests and analyses:
- Discriminant analysis Discriminant analysis helps to identify the independent variables that discriminate a
nominally scaled dependent variable of interest – say, those who are high on a variable from those who are low
on it.

- The linear combination of independent variables indicates the discriminating function showing the large
difference that exists in the two group means.

- In other words, the independent variables measured on an interval or ratio scale discriminate the groups of
interest to the study.

- Logistic regression: Logistic regression is also used when the dependent variable is nonmetric. However,
when the dependent variable has only two groups, logistic regression is often preferred because it does not face
the strict assumptions that discriminant analysis faces and because it is very similar to regression analysis. Thus,
logistic regression allows the researcher to predict a discrete outcome, such as “will purchase the product/will not
purchase the product,” from a set of variables that may be continuous, discrete, or dichotomous.
 Conjoint analysis:
- In marketing, conjoint analysis is used to understand

•how consumers develop preferences for products or services.

•Conjoint analysis is built on the idea that consumers evaluate the value of a product or service by combining the value that is
provided by each attribute. An attribute is a general feature of a product or service, such as price, product quality, or delivery
speed.

Each attribute has specific levels.

-
Two-way ANOVA
- Two‐way ANOVA can be used to examine the effect of two nonmetric independent variables on a single metric
dependent variable.

- Note that, in this context, an independent variable is often referred to as a factor and this is why a design that aims to
examine the effect of two nonmetric independent variables on a single metric dependent variable is often called a
factorial design.

- Two‐way ANOVA enables us to examine main effects (the effects of the independent variables on the dependent
variable) but also interaction effects that exist between the independent variables (or factors). An interaction effect
exists when the effect of one independent variable (or one factor) on the dependent variable depends on the level
of the other independent variable (factor)
MANOVA

- ANOVA tests the mean differences of more than two groups on one dependent variable, whereas MANOVA tests mean
differences among groups across several dependent variables simultaneously

- In MANOVA tests the independent variable is measured on a nominal scale and the dependent variables on an interval or
ratio scale. The null hypothesis tested by MANOVA is:
Hypothesis Testing for Single Population
Canonical correlation

- Canonical correlation examines the relationship between two or more dependent variables and several
independent variables; for example, the correlation between a set of job behaviors (such as
engrossment in work, timely completion of work, and number of absences) and their influence on a set
of performance factors (such as quality of work, the output, and rate of rejects). The focus here is on
delineating the job behavior profiles associated with performance that result in high‐quality production

-
-BIBLIOGRAPHY
-APA STYLE
What Is p-Value?

- The p-value is known as the probability value. P-values are used in hypothesis testing to help
determine whether the null hypothesis should be rejected. The lower the p-value, the more likely the
null hypothesis will be rejected.

• If the p-value is less than 0.05, the result is statistically significant. In this case, you reject the null
hypothesis favoring the alternative hypothesis.

• If the p-value is greater than 0.05, then the result is not statistically significant and hence doesn't reject
the null hypothesis.
Z-test is the statistical test used to analyze whether two population means are different or not when the variances are known,
and the sample size is large.

The z-test is based on the normal distribution.

The assumptions for Z-test are:

All observations are independent.

The size of the sample should be more than 30.
The Z distribution is normal when the mean is 0, and the variance is 1.
The test statistic is defined by:

Z_Test.

Xbar is the sample mean

σ is the population standard deviation

n is the sample size

μ is the population mean

Example
Let's say that the mean score of students in a class is greater than 70 with a standard deviation of 10. If a sample of 50
students was selected with a mean score of 80, calculate the Z-value to check if there is enough evidence to support
this claim at a 0.05 significance level.

Solution:
Here, the sample size is 50 and we know the standard deviation. This is a case of a right-tailed one-sample z test.

The Null hypothesis is the mean score is 70

The Alternative hypothesis is mean score is greater than 70

From the z-table, the critical value at alpha = 0.05 is 1.645

Xbar = 80

μ = 70

n = 50

σ = 10

Substituting the values in the formula, you will get the Z value to be equal to 7.09.
T-test is a parametric test applied to identify how the average of two data sets differs when variance is not given.

When the sample size is small, and the population standard deviation is unknown, the T-test is used in conjunction
with the t-distribution. The degree of freedom significantly impacts the shape of a t-distribution. The number of
independent observations in a given set of observations is the degree of freedom.

There are the following assumptions taken for the T-Test:

All the data points are independent.

The sample size is very small.
The sample size should be taken and recorded accurately.
T test and z test
- The ANOVA Test

- An ANOVA test is a way to find out if survey or experiment results are significant. In other words, they
help you to figure out if you need to reject the null hypothesis or accept the alternate hypothesis.

- Basically, you’re testing groups to see if there’s a difference between them. Examples of when you
might want to test different groups:

• A group of psychiatric patients are trying three different therapies: counseling, medication and
biofeedback. You want to see if one therapy is better than the others.

• A manufacturer has two different processes to make light bulbs. They want to know if one process is
better than the other.

• Students from different colleges take the same exam. You want to see if one college outperforms the
other.

- What Does “One-Way” or “Two-Way Mean?

- One-way or two-way refers to the number of independent variables (IVs) in your Analysis of Variance
test.

• One-way has one independent variable (with 2 levels). For example: brand of cereal,

• Two-way has two independent variables (it can have multiple levels). For example: brand of cereal,
calories.
- What are “Groups” or “Levels”?

- Groups or levels are different groups within the same independent variable. In the above example, your
levels for “brand of cereal” might be Lucky Charms, Raisin Bran, Cornflakes — a total of three levels.
Your levels for “Calories” might be: sweetened, unsweetened — a total of two levels.

- What Does “Replication” Mean?

- It’s whether you are replicating (i.e. duplicating) your test(s) with multiple groups. With a two way
ANOVA with replication , you have two groups and individuals within that group are doing more than
one thing (i.e. two groups of students from two colleges taking two tests). If you only have one group
taking two tests, you would use without replication.

- Types of Tests.

- There are two main types: one-way and two-way. Two-way tests can be with or without replication.

• One-way ANOVA between groups: used when you want to test two groups to see if there’s a difference
between them.

• Two way ANOVA without replication: used when you have one group and you’re double-testing that
same group. For example, you’re testing one set of individuals before and after they take a medication
to see if it works or not.

• Two way ANOVA with replication: Two groups, and the members of those groups are doing more than
one thing. For example, two groups of patients from different hospitals trying two different therapies.
- One Way ANOVA

- A one way ANOVA is used to compare two means from two independent (unrelated)
groups using the F-distribution. The null hypothesis for the test is that the two
means are equal. Therefore, a significant result means that the two means are
unequal.

- Examples of when to use a one way ANOVA

- Situation 1: You have a group of individuals randomly split into smaller groups and
completing different tasks. For example, you might be studying the effects of tea on
weight loss and form three groups: green tea, black tea, and no tea.
Situation 2: Similar to situation 1, but in this case the individuals are split into groups
based on an attribute they possess. For example, you might be studying leg strength of
people according to weight. You could split participants into weight categories (obese,
overweight and normal) and measure their leg strength on a weight machine.
- Two Way ANOVA

- A Two Way ANOVA is an extension of the One Way ANOVA. With a One Way, you have
one independent variable affecting a dependent variable. With a Two Way ANOVA,
there are two independents. Use a two way ANOVA when you have one
measurement variable (i.e. a quantitative variable) and two nominal variables. In
other words, if your experiment has a quantitative outcome and you have two
categorical explanatory variables, a two way ANOVA is appropriate.

- For example, you might want to find out if there is an interaction between income and
gender for anxiety level at job interviews. The anxiety level is the outcome, or the
variable that can be measured. Gender and Income are the two categorical variables
. These categorical variables are also the independent variables, which are
called factors in a Two Way ANOVA.

- The factors can be split into levels. In the above example, income level could be split
into three levels: low, middle and high income. Gender could be split into three levels:
male, female, and transgender. Treatment groups are all possible combinations of the
factors. In this example there would be 3 x 3 = 9 treatment groups.
- Main Effect and Interaction Effect

- The results from a Two Way ANOVA will calculate a main effect and an interaction effect. The main
effect is similar to a One Way ANOVA: each factor’s effect is considered separately. With the interaction
effect, all factors are considered at the same time. Interaction effects between factors are easier to test
if there is more than one observation in each cell. For the above example, multiple stress scores could be
entered into cells. If you do enter multiple observations into cells, the number in each cell must be equal.

- Two null hypotheses are tested if you are placing one observation in each cell. For this example, those
hypotheses would be:
H01: All the income groups have equal mean stress.
H02: All the gender groups have equal mean stress.

- For multiple observations in cells, you would also be testing a third hypothesis:
H03: The factors are independent or the interaction effect does not exist.

- An F-statistic is computed for each hypothesis you are testing.

- Assumptions for Two Way ANOVA

• The population must be close to a normal distribution.

• Samples must be independent.

• Population variances must be equal (i.e. homoscedastic).

• Groups must have equal sample sizes

- What is MANOVA?

- MANOVA is just an ANOVA with several dependent variables. It’s similar to many other tests and experiments in
that it’s purpose is to find out if the response variable (i.e. your dependent variable) is changed by manipulating the
independent variable. The test helps to answer many research questions, including:

•
Do changes to the independent variables have statistically significant effects on dependent variables?

• What are the interactions among dependent variables?

• What are the interactions among independent variables?

- MANOVA Example

- Suppose you wanted to find out if a difference in textbooks affected students’ scores in math and science.
Improvements in math and science means that there are two dependent variables, so a MANOVA is appropriate.

- An ANOVA will give you a single (univariate) f-value while a MANOVA will give you a multivariate F value. MANOVA
tests the multiple dependent variables by creating new, artificial, dependent variables that maximize group
differences. These new dependent variables are linear combinations of the measured dependent variables.

- Interpreting the MANOVA results

- If the multivariate F value indicates the test is statistically significant, this means that something is significant.
In the above example, you would not know if math scores have improved, science scores have improved (or both).
Once you have a significant result, you would then have to look at each individual component (the univariate F
tests) to see which dependent variable(s) contributed to the statistically significant result.
REGRESSION VS ANOVA
Example 1: ANOVA Model Preferred
Suppose a biologist wants to understand whether or not four different fertilizers lead to
the same average plant growth (in inches) during a one-month period. To test this, she
applies each fertilizer to 20 plants and records the growth of each plant after one
month.
In this scenario, the biologist should use a one-way ANOVA model to analyze the
differences between the fertilizers because there is one predictor variable and it is
categorical. In other words, the values for the predictor variable can be classified into
the following “categories”:
•Fertilizer 1
•Fertilizer 2
•Fertilizer 3
•Fertilizer 4
A one-way ANOVA will tell the biologist whether or not the mean plant growth is equal
between the four different fertilizers.
Example 2: Regression Model Preferred
Suppose a real estate agent wants to understand the relationship between
square footage and house price. To analyze this relationship, he collects data on
square footage and house price for 200 houses in a particular city. In this
scenario, the real estate agent should use a simple linear regression model to
analyze the relationship between these two variables because the predictor
variable (square footage) is continuous. In this scenario, the real estate agent
should use a simple linear regression model to analyze the relationship between
these two variables because the predictor variable (square footage) is
continuous.
Example 3: Regression Model with Dummy Variables Preferred
Suppose a real estate agent wants to understand the relationship between the predictor
variables “square footage” and “home type” (single-family, apartment, townhome) with the
response variable of house price.
In this scenario, the real estate agent can use multiple linear regression by converting
“home type” into a dummy variable since it’s currently a categorical variable. The real
estate agent can then fit the following multiple linear regression model:
House price = β0 + β1(square footage) + β2(single-family) + β3(apartment)
Here’s how we would interpret the coefficients in the model:
•β1: The average change in house price associated with one extra square foot.
•β2: The average difference in price between a single-family home and a townhome,
assuming square footage is held constant.
•β3: The average difference in price between a single-family home and an apartment,
assuming square footage is held constant.