Rp 20049-29

Part III. Administrative, Procedural, and Miscellaneous
26 CFR 601.105: Examination of returns and claims
for refund, credit or abatement; determination of correct tax liability.
(Also Part I, §§ 132, 162, 274; 1.132–6.)

Rev. Proc. 2004–29
SECTION 1. PURPOSE
This revenue procedure provides the
statistical sampling methodology that
a taxpayer may use in establishing the
amount of substantiated meal and entertainment expenses excepted from the 50%
deduction disallowance of § 274(n)(1) of
the Internal Revenue Code by reason of
§ 274(n)(2)(A), (B), (C), (D), or (E).
SECTION 2. BACKGROUND
.01 Section 162(a) allows a deduction
for all ordinary and necessary expenses
paid or incurred during the taxable year in
carrying on any trade or business, including certain expenses for meals and entertainment.
.02 Section 274(d) disallows a § 162
deduction for any expense for travel (including meals and lodging while away
from home), entertainment, gifts, or listed
property unless the taxpayer substantiates
the elements of the expense by adequate
records or by sufficient evidence. See
§ 1.274–5T of the Income Tax Regulations.
.03 Section 274(n)(1) provides that the
amount allowable as a deduction for any
expense for food or beverages, or any
item with respect to an activity that is of
a type generally considered to constitute
entertainment, amusement, or recreation,
or with respect to a facility used in connection with these activities, may not exceed
50% of the amount of the expense.
.04 Section 274(n)(2)(A) provides
that the 50% deduction disallowance of
§ 274(n)(1) does not apply to expenses
described in § 274(e)(2) (expenses treated
on the taxpayer’s return as compensation
to an employee under chapter 1 and as
wages to the employee for purposes of
chapter 24), (e)(3) (expenses paid or incurred under a reimbursement or similar
arrangement in connection with the performance of services), (e)(4) (recreational
and similar expenses for employees),

May 17, 2004

(e)(7) (expenses relating to items available
to the public), (e)(8) (expenses relating to
entertainment sold to customers), or (e)(9)
(expenses includible in income of persons
who are not employees).
.05 Section 274(n)(2)(B) provides
that the 50% deduction disallowance of
§ 274(n)(1) does not apply to an expense
for food or beverages that is excludable
from the gross income of the recipient
under § 132(e) (relating to de minimis
fringe benefits excluded from income under § 132(a)(4)).
.06 Section 132(e) defines a de minimis fringe as any property or service the
value of which is (after taking into account the frequency with which similar
fringes are provided by the employer to
the employer’s employees) so small as
to make accounting for it unreasonable
or administratively impracticable. Under
§ 1.132–6(c), a cash fringe benefit (other
than overtime meal money and local transportation fare) is never excludable as a de
minimis fringe benefit. For example, expenses for meals and entertainment reimbursed to employees under an accountable
plan (as defined in § 1.62–2(c)(2)) do not
qualify as de minimis fringe benefits.
.07 Section 1.132–6(b) provides that
the frequency with which similar fringes
are provided by the employer to the employer’s employees is generally determined by reference to the frequency with
which the employer provides the fringes
to each individual employee. However,
if it would be administratively difficult
to determine frequency with respect to
individual employees, the frequency with
which similar fringes are provided by the
employer to the employer’s employees is
determined by reference to the workforce
as a whole. This exception to the employee-measured frequency requirement
does not apply to overtime meals, meal
money, or local transportation fare.
.08 Section 274(n)(2)(C) provides
that the 50% deduction disallowance of
§ 274(n)(1) does not apply to an expense
covered by a package involving a ticket
described in § 274(l)(1)(B) (exception for
certain charitable sports events).
.09 Section 274(n)(2)(D) provides
that the 50% deduction disallowance of
§ 274(n)(1) does not apply to taxable

918

payments or reimbursements of moving
expenses of an employee by the employer.
.10 Section 274(n)(2)(E) provides
that the 50% deduction disallowance of
§ 274(n)(1) does not apply to expenses for
food or beverages (i) required by Federal
law to be provided to crew members of a
commercial vessel, (ii) provided to crew
members of certain commercial vessels, or
(iii) provided on or in proximity to certain
oil or gas platforms or drilling rigs.
SECTION 3. SCOPE
This revenue procedure applies to a
taxpayer filing an original return, under examination, in litigation, or making
a refund claim that desires to establish
with respect to its income tax liability the
amount of substantiated expenses paid
or incurred for meals and entertainment
excepted from the 50% deduction disallowance of § 274(n)(1) by reason of
§ 274(n)(2)(A), (B), (C), (D), or (E).
SECTION 4. APPLICATION
.01 In general. A taxpayer filing an
original return, under examination, in litigation, or making a refund claim, may
use statistical sampling in connection with
establishing, with respect to its income
tax liability, the amount of the taxpayer’s
substantiated expenses paid or incurred
for meals and entertainment excepted
from the 50% deduction disallowance of
§ 274(n)(1) by reason of § 274(n)(2)(A),
(B), (C), (D), or (E) by following the
procedures provided in Appendix A (Sampling Plan Standards), Appendix B (Sampling Documentation Standards), Appendix C (Technical Formulas), and (in the
case of de minimis fringes) in paragraph
4.02 of this revenue procedure.
.02 Additional procedures required for
de minimis fringe benefits.
(1) Reimbursements under accountable
plans. In conducting the study, expenses
for meals and entertainment reimbursed by
employers to employees under an accountable plan may not be treated as de minimis
fringe benefits.
(2) Determination of frequency. To establish the amount of identified expenses
that are excepted from § 274(n)(1) by reason of § 274(n)(2)(B), a taxpayer is required to determine the frequency with

2004-20 I.R.B.

which similar fringes were provided by the
taxpayer to the taxpayer’s employees on
an employee-measured or employer-measured basis, as described in paragraphs (3)
and (4) below. Thus, after selecting a statistical sample, as discussed below, the taxpayer may be required to review documentation from outside both the sample and
the target population (the set of items from
which the sample is drawn) to identify similar fringes included in employees’ gross
income and similar fringes previously excluded from employees’ gross income as
de minimis fringe benefits.
(3) Employee-measured frequency.
(a) In general.
When using employee-measured frequency to determine
the amount of identified expenses that
are excepted from § 274(n)(1) by reason
of § 274(n)(2)(B), the taxpayer must establish the frequency with which similar
fringes were provided to each individual
employee of the taxpayer. Therefore, after identifying the statistical sample, the
taxpayer must review the remainder of the
target population (and records that document similar fringes that are not included
in the target population) to identify the aggregate number of similar fringes provided
to the individual employees included in
the statistical sample.
(b) Example. Taxpayer maintains a
meal and entertainment expense account
that includes invoices for meals provided
in-kind to Taxpayer’s employees that may
be de minimis fringe benefits. The invoices specifically identify the employees
who received the in-kind meals. Therefore, it would not be administratively
difficult to determine the frequency with
which in-kind meals were provided to individual employees, and Taxpayer must
determine the frequency with which it
provided in-kind meals to each of the individual employees included in the sample.
Taxpayer has no other accounts that include expenses for in-kind meals provided
to employees.
Taxpayer selects a statistical sample
of the meal and entertainment expense
account that identifies 10 employees who
have received in-kind meals. In order
to determine if the meals are de minimis
fringes, Taxpayer must review documentation (such as invoices) in the remainder
of the target population to identify all
in-kind meals provided to each of the

2004-20 I.R.B.

10 individual employees included in the
sample. Taxpayer must consider in-kind
meals that Taxpayer included in each employee’s gross income and similar fringes
previously excluded from the employees’
gross income as de minimis fringe benefits
in determining the frequency with which
similar fringes were provided to each of
the 10 employees. After conducting this
review, Taxpayer determines (after considering both the value and frequency of
the meals) that the meals provided to 4 of
the 10 employees in the sample are de minimis fringe benefits not subject to the 50%
deduction disallowance of § 274(n)(1).
Taxpayer may increase proportionately
the deductible amount of expenses in the
population not subject to the § 274(n)(1)
limitation. See paragraph 6 of Appendix
A.
(4) Employer-measured frequency.
(a) In general.
When using employer-measured frequency to determine
the amount of identified expenses that are
excepted from § 274(n)(1) by reason of
§ 274(n)(2)(B), the taxpayer must establish
the frequency with which similar fringes
were provided to the taxpayer’s workforce
as a whole. Thus, the target population
must include all relevant records prior
to selection of the statistical sample in
order to determine the aggregate number
of similar fringes provided to all eligible
employees and the aggregate number of
employees eligible to receive such fringes.
(b) Example. Taxpayer maintains a
meal and entertainment expense account
that includes invoices for meals provided
in-kind to Taxpayer’s employees that may
be de minimis fringe benefits. The invoices are for in-kind meals of a type
for which it is administratively difficult
to identify the particular employees who
received the meals, and the invoices do
not specifically identify those employees.
Therefore, it would be administratively
difficult to determine the frequency with
which in-kind meals were provided to
individual employees, and Taxpayer may
determine the frequency with which similar fringes were provided by Taxpayer
to Taxpayer’s employees by reference to
all employees eligible to receive in-kind
meals. Taxpayer maintains an account in
addition to the meal and entertainment
expense account that includes expenses
for in-kind meals provided to employees.

919

Taxpayer’s workforce includes 500 employees who are eligible to receive the
fringe benefit of in-kind meals.
Taxpayer merges the meal and entertainment expense account and the other
account that includes expenses for in-kind
meals to create a target population that includes all relevant records and conducts a
statistical sample of the merged accounts.
In determining whether the in-kind meals
included in the sample are de minimis
fringes, Taxpayer must consider in-kind
meals that Taxpayer included in eligible employees’ gross income and similar
fringes previously excluded from employees’ gross income as de minimis fringe
benefits. Taxpayer identifies in the sample
50 in-kind meals provided to employees.
The 50 meals represent 1000 in-kind meals
in the target population as a whole, or two
meals per eligible employee. Assuming
that the provision of two meals with a
given cost per eligible employee results in
a value that is so small as to make accounting for it unreasonable or administratively
impracticable, Taxpayer may treat all of
the in-kind meals in the meal and entertainment expense account as de minimis
fringe benefits not subject to the 50%
deduction disallowance of § 274(n)(1),
subject, however, to a pro rata reduction
to the extent that any in-kind meals are
evaluated under employee-measured frequency and fail to qualify as de minimis
fringes.
.03 Limitations.
(1) This revenue procedure does not authorize the use of statistical sampling to
substantiate meal and entertainment expenses as required by § 274(d).
(2) This revenue procedure does not authorize the use of statistical sampling to determine a taxpayer’s liability for employment taxes or whether an amount is excludable from a taxpayer’s income.
(3) This revenue procedure does not establish the correctness of a taxpayer’s interpretation of § 274(n) or characterization
of meal and entertainment expenses as expenses excepted from § 274(n)(1).
(4) This revenue procedure does not
preclude the Internal Revenue Service
from raising or pursuing any income, employment, or other tax issues identified in
the review of a statistical sample.

May 17, 2004

SECTION 5. EFFECTIVE DATE
This revenue procedure is effective for
taxable years ending on or after May 3,
2004. However, with respect to the use of
statistical sampling by a taxpayer for a taxable year ending before May 3, 2004, for
which the applicable period of limitations
has not expired, the Service will permit,
but not require, application of this revenue
procedure.

and Accounting). For further information
regarding this revenue procedure, contact Ms. Fisher at (202) 622–4970 (not
a toll-free call). For further information
regarding Appendices A, B and C, contact Ed Cohen of the Large and Mid-Size
Business Division at (212) 719–6693 (not
a toll-free call).
APPENDIX A
SAMPLING PLAN STANDARDS

SECTION 6. PAPERWORK
REDUCTION ACT
The collection of information contained in this revenue procedure has been
reviewed and approved by the Office
of Management and Budget in accordance with the Paperwork Reduction Act
(44 U.S.C. 3507) under control number
1545–1847.
An agency may not conduct or sponsor,
and a person is not required to respond
to, a collection of information unless the
collection of information displays a valid
OMB control number.
The collection of information in this
revenue procedure is in Appendix B. This
information is required to ensure compliance with the statistical sampling methodology contained in this revenue procedure.
The information will be used to evaluate
compliance with the procedures described
in this revenue procedure. The collection
of information is mandatory. The likely
recordkeepers are businesses or other forprofit institutions.
The estimated total annual recordkeeping burden is 3200 hours. The estimated
annual burden per recordkeeper varies
from six to ten hours, depending on individual circumstances, with an estimated
average of eight hours. The estimated
number of recordkeepers is 400.
Books or records relating to a collection
of information must be retained as long
as their contents may become material in
the administration of any internal revenue
law. Generally tax returns and tax return
information are confidential, as required
by 26 U.S.C. 6103.
DRAFTING INFORMATION
The principal author of this revenue
procedure is Kari L. Fisher of the Office
of Associate Chief Counsel (Income Tax

May 17, 2004

The statistical sampling must be conducted in accordance with the following
methodology.
1. Statistical (probability) sampling
methodology may not include the use of
judgment sampling.
2. Taxpayers may apply the results of a
statistical sample only to the taxable years
included in the sample.
3. A statistical sample may include data
from no more than three consecutive taxable years.
4. Data from a taxable year may be
included in only one statistical sample.
5. The estimated amount of expenses
not subject to the § 274(n)(1) limitation
must be based on a statistical (probability) sample, in which each sampling unit
has a known (non-zero) chance of selection, using either a simple random sampling method or stratified random sampling method.
6. In general, the computation of the
estimated amount of expenses not subject
to the § 274(n)(1) limitation must be at the
least advantageous 95% one-sided confidence limit. The “least advantageous”
confidence limit is either the upper or
lower limit that results in the least benefit
to the taxpayer. However, if the precision
of the change in the estimated deductible
amount of expenses not subject to the
§ 274(n)(1) limitation (see paragraph 9
below) divided by the change in the estimated deductible amount of expenses not
subject to the § 274(n)(1) limitation does
not exceed 10%, the point estimate may
be used in place of the least advantageous
confidence limit. All strata for which
“substantially all” of the population sampling units are sampled will be treated as
100% strata. That is, the overall point estimate and its precision will be estimated by
treating all 100% strata appropriately for
the sample design used. Also, the calcu-

920

lation of the denominator for the relative
precision will exclude all 100% strata. For
this revenue procedure, “substantially all”
is defined as 80% or more.
7. Recognizing that many methods
exist to estimate population values from
the sample data, the Service will consider
acceptable only the following estimators.
Variable estimators permitted include the
mean (also known as the direct projection
method), difference (using “paired variables”), (combined) ratio (using a variable
of interest and a “correlated” variable), and
(combined) regression (using a variable
of interest and a “correlated” variable).
The first variable used for the difference,
ratio and regression estimators must be
the variable used in the mean estimator.
The second variable used for the difference, ratio and regression estimators must
be a variable that can be paired with the
first variable and should be related to the
first variable. For example, in a typical
audit-sampling situation, the first variable
would be the audited value of a transaction and the second variable would be
the originally reported value of the same
transaction. Since the latter two variable
methods are statistically biased, there must
be a demonstration that the bias is negligible before the Service will accept the
method.
8. Variable sampling plans must use the
qualifying final estimate with the smallest
overall standard error as an absolute value
(for example, the size of the estimate is
irrelevant in the determination of the reported value).
9. Variable sampling plans must calculate confidence limits by addition and
subtraction of the precision of the estimate from the point estimate in which the
determination of precision proceeds by
multiplication of the standard error by (i)
the 95% one-sided confidence coefficient
based on the Student’s t-distribution with
the appropriate degrees of freedom, or (ii)
1.645 (the normal distribution), assuming
the sample size is at least 100 in each
non–100% stratum.
10. For either the (combined) ratio or
regression methods, to demonstrate little
statistical bias exists, the following applies
after excluding all strata tested on 100%
basis (the entire population of a stratum is
selected for evaluation).
a. The total sample size of all strata
must be at least 100 units.

2004-20 I.R.B.

b. Each stratum for a population estimate should contain at least 30 sample
units.
c. The coefficient of variation of the
paired variable must be 15% or less. The
coefficient of variation of the paired variable (y) is defined as the standard error of
the total “y” variables divided by point estimate of the total “y” variables when the
“y” variables are commonly the reported
values in accounting situations.
d. The coefficient of variation of the
primary variable of interest, represented by
either the corrected value or the difference
between the reported and corrected values
in common accounting situations, must be
15% or less. The coefficient of variation
for the corrected value (x) is defined as
the standard error of the total “x” variables divided by point estimate of the total “x” variables when the “x” variables are
commonly the corrected values in accounting situations. The coefficient of variation
for the difference (d) between the reported
and corrected values (x-y) is defined as
the smaller of the standard error of the total “x-y” or total “d” variables divided by
the amount equaling total population value
represented by “Y” plus point estimate of
the total “x-y” or total “d” variables or the
standard error of the total “x-y” or total
“d” variables divided by the total “x-y” or
total “d” variables when the “x-y” variables are commonly the difference (“d”)
between the reported (“y”) and corrected
(“x”) values in accounting situations.
e.
For only the (combined) ratio
method, the reported values of units must
be of the same sign.
11. When sampling the same expense
accounts for multiple taxable years, if a

single projection does not materially affect other computations that are more appropriately made on a yearly basis, it is
permissible to combine the accounts into
one population. There should be allocation of the combined result by a reasonable
method determined prior to the selection of
the sampling units.
12. A written sampling plan is required
prior to the execution of a sample. A plan
must include the following:
a. The objective of the plan including a
description of the value for estimation and
the applicable taxable year(s);
b. Population definition and reconciliation of the population to the tax return;
c. Definition of the sampling frame;
d. Definition of the sampling unit;
e. Source of the random numbers, the
starting point or seed, and the method of
selection;
f. Sample size, along with supporting
factors in the determination;
g. Method to associate random numbers to the frame;
h. Steps to ensure that the serialization
of the frame is independent of the drawing
of random numbers;
i. Steps for evaluating the sampling
unit; and
j. The estimator that was used for appraising the sample.
APPENDIX B

aspects of the sample plan and execution.
The execution of the sample must include
information for each of the following
items:
1. The seed or starting point of the
random numbers;
2. The pairing of random numbers to
the frame along with supporting information to retrace the process;
3. List of sampling units selected and
the results of the evaluation of each unit;
4. Supporting documentation such as
notes, invoices, purchase orders, project
descriptions, etc., which support the conclusion reached about each sample item;
5. The calculation of the projected estimate(s) to the population, including computation of the standard error of the estimate(s);
6. A statement describing any slips or
blemishes in the execution of the sampling
procedure and any pertinent decision rules;
and
7. Computation of all associated adjustments.
APPENDIX C
TECHNICAL FORMULAS
The formulas below are included to
clarify the statistical sampling terms used
and to ensure consistent application of
the procedures described in the revenue
procedure.

SAMPLING DOCUMENTATION
STANDARDS
The taxpayer must retain adequate
documentation to support the statistical
application, sample unit findings, and all

UNSTRATIFIED (SIMPLE RANDOM SAMPLE)
MEAN ESTIMATOR

STRATIFIED
MEAN ESTIMATOR

Sample Mean of Audited Amounts

Estimate of Total Audited Amount

2004-20 I.R.B.

921

May 17, 2004

UNSTRATIFIED (SIMPLE RANDOM SAMPLE)
MEAN ESTIMATOR

STRATIFIED
MEAN ESTIMATOR

Estimated Standard Deviation of the Audited Amount

Estimated Standard Error of the Total Audited Amount

Achieved Precision of the Total Audited Amount

UNSTRATIFIED (SIMPLE RANDOM SAMPLE)
DIFFERENCE ESTIMATOR

STRATIFIED
DIFFERENCE ESTIMATOR

Estimate of Total Difference

Estimate of Total Audited Amount

Estimated Standard Deviation of the Difference Amount

Estimated Standard Error of the Difference Amount

Achieved Precision of the Difference Amount

May 17, 2004

922

2004-20 I.R.B.

UNSTRATIFIED (SIMPLE RANDOM SAMPLE)
RATIO ESTIMATOR

STRATIFIED
COMBINED RATIO ESTIMATOR

Estimated Ratio of Audited Amount to Recorded Amount

Estimate of Total Audited Amount

Estimated Standard Deviation of the Ratio

Estimated Standard Deviation of the Ratio in ith Stratum

Estimated Standard Error of the Ratio Amounts

Achieved Precision of the Ratio Amounts

UNSTRATIFIED (SIMPLE RANDOM SAMPLE)
REGRESSION ESTIMATOR

STRATIFIED
COMBINED REGRESSION ESTIMATOR

Estimated Regression Coefficient

Estimate of Total Audited Amount

2004-20 I.R.B.

923

May 17, 2004

UNSTRATIFIED (SIMPLE RANDOM SAMPLE)
REGRESSION ESTIMATOR

STRATIFIED
COMBINED REGRESSION ESTIMATOR

Estimated Standard Deviation of the Regression Amounts

Estimated Covariance between the Audited and Recorded Amounts in i

th

Stratum

Estimated Standard Deviation between the Audited and Recorded Amounts in i

th

Stratum

Estimated Standard Error of the Audited and Recorded Amounts

Achieved Precision of the Audited and Recorded Amounts

Definition of Symbols

TERM

DEFINITION

n

Sample Size

N

Population Size

x

The value of the sampling unit that is being used as the primary variable of interest. In audit sampling,
this would be the audited (or revised) value of the transaction.

y

The value of the sampling unit that is being used as the “paired” variable that is related to the variable
of interest. In audit sampling, this would be the reported (or original) value of the transaction.

d

The value of the sampling unit that is the difference between “paired” variable (y) and the variable
of interest (x). That is, d = x – y. In audit sampling, this would be the difference (or the change)
of each transaction’s value.

X

The total value of the primary variable of interest. In audit sampling, this would be the estimated total
audited value of the population. Typically, this value is not known for the entire population and is
estimated based on the probability sample selected.

May 17, 2004

924

2004-20 I.R.B.

TERM

DEFINITION

Y

The total value of the variable that is paired with variable of interest. In audit sampling, this would
be the total reported value of the population. Typically, this value is known for the entire population
and may be estimated based on the probability sample selected.

D

The total value of the difference between the “paired” variable and the variable of interest. In audit
sampling, this would be the estimated total difference of the population. Typically, this value is not
known for the entire population and is estimated based on the probability sample selected.

UR

The confidence coefficient which is based on either the Student’s t-distribution or the normal
distribution. For example, a 95% one-sided confidence coefficient based on the normal distribution is
1.645. This term is often referred to as the t-value and the z-value.

2004-20 I.R.B.

925

May 17, 2004