---
title: "Estimation methods in output analysis"
subject: "Simulation and Modeling"
chapter: 8
key: "semester_8/simulation_and_modeling:estimation-methods-output"
source: https://www.bctengineer.com/q/semester_8/simulation_and_modeling/estimation-methods-output
site: BCT Engineering
---

# Estimation methods in output analysis

Simulation and Modeling · Chapter 8: Analysis of simulation output

- Asked in: 2073 Magh, 5 marks; 2071 Bhadra, 5 marks (asked 2 times)
- Video: [Simulation Modeling 88 What Is Output Analysis?](https://www.youtube.com/watch?v=AHTy59JuExA) — İsmail Başoğlu
- Answer checked by Claude Opus 5.5 (high effort) on 2026-10-14
- Page: https://www.bctengineer.com/q/semester_8/simulation_and_modeling/estimation-methods-output
- Whole chapter: https://www.bctengineer.com/md/semester_8/simulation_and_modeling/chapter-8

## Question

How can you use estimation methods in analysis of simulation output? Explain with example.

## Short answer

Estimation uses point estimates (sample mean) and interval estimates (confidence interval) from independent replications. For five replications with average delay 2.30 min and S=0.354, the 95% CI is 2.30 ± 0.44 min (1.86, 2.74). Steady-state methods like batch means handle correlated data.

## Answer

Because a simulation output is a random sample, a performance measure θ (such as mean waiting time) can only be **estimated**. Estimation methods turn the output data into a point estimate and an interval estimate with a stated confidence.

#### Point estimate
For n observations Y_1 ... Y_n, the sample mean Ȳ = ΣY_i / n estimates θ. Sample variance S² = Σ(Y_i - Ȳ)² / (n - 1) measures variability. For a time-persistent measure, use the time-weighted average.

#### Interval estimate (confidence interval)
For terminating simulations, make R independent replications, giving one summary value Y_r from each. Then

Ȳ ± t(α/2, R-1) · S / √R

where t is from the Student's t-table. The interval says that with probability 1 - α the true mean lies inside it.

#### Estimation for steady state
Within one long run the observations are correlated, so the usual formula is invalid. Methods used:
- **Replication with deletion**: independent replications with warm-up removed.
- **Batch means**: split the run into k batches; use batch means as nearly independent observations in the formula above.
- **Regenerative method**: use cycles that start from the same state (such as an empty system).

#### Example
Five replications of a bank model give average delays: 2.1, 2.5, 1.9, 2.8, 2.2 min.
- Ȳ = 11.5 / 5 = 2.30
- S² = (0.04 + 0.04 + 0.16 + 0.25 + 0.01) / 4 = 0.125, S = 0.354
- For 95% confidence, α = 0.05, degrees of freedom = 4, t(0.025, 4) = 2.776
- Half-width = 2.776 × 0.354 / √5 = 0.44
- **95% CI: 2.30 ± 0.44, i.e. (1.86, 2.74) min**

#### Precision
To get half-width ε, the required replications are about R ≥ (t · S / ε)². For ε = 0.1, R is about 50. A narrow interval means a precise estimate; the interval is narrowed by more replications or longer runs.

## Check yourself

The answer's key points as multiple-choice questions, with the correct option and why.

1. For R independent replications, which interval formula is used?
   A. Mean +/- z x S
   B. Mean +/- t(alpha/2, R-1) x S / sqrt(R)
   C. Mean +/- S x R
   D. Mean +/- t(alpha/2, R) x S
   Answer: B. The t-based interval uses R-1 degrees of freedom and the standard error S/sqrt(R). (Key point: Confidence interval formula)

2. Why can the usual CI formula not be applied directly to observations within one steady-state run?
   A. The observations are autocorrelated
   B. The run is too short
   C. The mean is unknown
   D. t-tables do not cover large n
   Answer: A. Observations in one run are correlated, so methods like batch means, replication with deletion or regeneration are needed. (Key point: Steady-state estimation)

3. For five replications with Ybar = 2.30, S = 0.354, t = 2.776, what is the 95% half-width?
   A. 0.16
   B. 0.98
   C. 0.44
   D. 0.35
   Answer: C. 2.776 x 0.354 / sqrt(5) = 0.44. (Key point: Example calculation)

## Related in Simulation and Modeling

- [Types of output analysis; infinite population](https://www.bctengineer.com/question.md?key=semester_8%2Fsimulation_and_modeling%3Aoutput-analysis-types-infinite) — Simulation and Modeling, chapter 8
- [Simulation run statistics](https://www.bctengineer.com/question.md?key=semester_8%2Fsimulation_and_modeling%3Asimulation-run-statistics) — Simulation and Modeling, chapter 8, asked 2×

## Related in other subjects

- [GIC simulation of HPF at ωo = 4000 rad/s](https://www.bctengineer.com/question.md?key=semester_5%2Ffilter_design%3Agic-hpf-4000-simulation) — Filter Design, chapter 8
- [GIC simulation of HPF with Kf = 2000](https://www.bctengineer.com/question.md?key=semester_5%2Ffilter_design%3Agic-hpf-kf-2000-simulation) — Filter Design, chapter 8, asked 2×
- [Petrol pump queue simulation](https://www.bctengineer.com/question.md?key=semester_4%2Fdata_structure_and_algorithm%3Apetrol-pump-simulation) — Data Structure and Algorithm, chapter 2
- [Storm water estimation and its limitations](https://www.bctengineer.com/question.md?key=semester_6%2Fsanitary_engineering%3Astorm-water-limitations) — Sanitary Engineering, chapter 2